To see the other types of publications on this topic, follow the link: Camera motion estimation.
Dissertations / Theses on the topic 'Camera motion estimation'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Camera motion estimation.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Kim, Jae-Hak, and Jae-Hak Kim@anu edu au. "Camera Motion Estimation for Multi-Camera Systems." The Australian National University. Research School of Information Sciences and Engineering, 2008. http://thesis.anu.edu.au./public/adt-ANU20081211.011120.
Full textAbstract:
The estimation of motion of multi-camera systems is one of the most important tasks in computer vision research. Recently, some issues have been raised about general camera models and multi-camera systems. Using many cameras as a single camera is studied [60], and the epipolar geometry constraints of general camera models is theoretically derived. Methods for calibration, including a self-calibration method for general camera models, are studied [78, 62]. Multi-camera systems are an example of practically implementable general camera models and they are widely used in many applications nowadays because of both the low cost of digital charge-coupled device (CCD) cameras and the high resolution of multiple images from the wide field of views. To our knowledge, no research has been conducted on the relative motion of multi-camera systems with non-overlapping views to obtain a geometrically optimal solution. ¶
In this thesis, we solve the camera motion problem for multi-camera systems by using linear methods and convex optimization techniques, and we make five substantial and original contributions to the field of computer vision. First, we focus on the problem of translational motion of omnidirectional cameras, which are multi-camera systems, and present a constrained minimization method to obtain robust estimation results. Given known rotation, we show that bilinear and trilinear relations can be used to build a system of linear equations, and singular value decomposition (SVD) is used to solve the equations. Second, we present a linear method that estimates the relative motion of generalized cameras, in particular, in the case of non-overlapping views. We also present four types of generalized cameras, which can be solvable using our proposed, modified SVD method. This is the first study finding linear relations for certain types of generalized cameras and performing experiments using our proposed linear method. Third, we present a linear 6-point method (5 points from the same camera and 1 point from another camera) that estimates the relative motion of multi-camera systems, where cameras have no overlapping views. In addition, we discuss the theoretical and geometric analyses of multi-camera systems as well as certain critical configurations where the scale of translation cannot be determined. Fourth, we develop a global solution under an L∞ norm error for the relative motion problem of multi-camera systems using second-order cone programming. Finally, we present a fast searching method to obtain a global solution under an L∞ norm error for the relative motion problem of multi-camera systems, with non-overlapping views, using a branch-and-bound algorithm and linear programming (LP). By testing the feasibility of LP at the earlier stage, we reduced the time of computation of solving LP.¶
We tested our proposed methods by performing experiments with synthetic and real data. The Ladybug2 camera, for example, was used in the experiment on estimation of the translation of omnidirectional cameras and in the estimation of the relative motion of non-overlapping multi-camera systems. These experiments showed that a global solution using L∞ to estimate the relative motion of multi-camera systems could be achieved.
2
Kim, Jae-Hak. "Camera motion estimation for multi-camera systems /." View thesis entry in Australian Digital Theses Program, 2008. http://thesis.anu.edu.au/public/adt-ANU20081211.011120/index.html.
Full text
3
Srestasathiern, Panu. "Line Based Estimation of Object Space Geometry and Camera Motion." The Ohio State University, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=osu1345401748.
Full text
4
Hannuksela, J. (Jari). "Camera based motion estimation and recognition for human-computer interaction." Doctoral thesis, University of Oulu, 2008. http://urn.fi/urn:isbn:9789514289781.
Full textAbstract:
Abstract
Communicating with mobile devices has become an unavoidable part of our daily life. Unfortunately, the current user interface designs are mostly taken directly from desktop computers. This has resulted in devices that are sometimes hard to use. Since more processing power and new sensing technologies are already available, there is a possibility to develop systems to communicate through different modalities. This thesis proposes some novel computer vision approaches, including head tracking, object motion analysis and device ego-motion estimation, to allow efficient interaction with mobile devices.
For head tracking, two new methods have been developed. The first method detects a face region and facial features by employing skin detection, morphology, and a geometrical face model. The second method, designed especially for mobile use, detects the face and eyes using local texture features. In both cases, Kalman filtering is applied to estimate the 3-D pose of the head. Experiments indicate that the methods introduced can be applied on platforms with limited computational resources.
A novel object tracking method is also presented. The idea is to combine Kalman filtering and EM-algorithms to track an object, such as a finger, using motion features. This technique is also applicable when some conventional methods such as colour segmentation and background subtraction cannot be used. In addition, a new feature based camera ego-motion estimation framework is proposed. The method introduced exploits gradient measures for feature selection and feature displacement uncertainty analysis. Experiments with a fixed point implementation testify to the effectiveness of the approach on a camera-equipped mobile phone.
The feasibility of the methods developed is demonstrated in three new mobile interface solutions. One of them estimates the ego-motion of the device with respect to the user's face and utilises that information for browsing large documents or bitmaps on small displays. The second solution is to use device or finger motion to recognize simple gestures. In addition to these applications, a novel interactive system to build document panorama images is presented.
The motion estimation and recognition techniques presented in this thesis have clear potential to become practical means for interacting with mobile devices. In fact, cameras in future mobile devices may, for the most of time, be used as sensors for self intuitive user interfaces rather than using them for digital photography.
5
Kurz, Christian [Verfasser], and Hans-Peter [Akademischer Betreuer] Seidel. "Constrained camera motion estimation and 3D reconstruction / Christian Kurz. Betreuer: Hans-Peter Seidel." Saarbrücken : Saarländische Universitäts- und Landesbibliothek, 2014. http://d-nb.info/1063330734/34.
Full text
6
Hughes, Lloyd Haydn. "Enhancing mobile camera pose estimation through the inclusion of sensors." Thesis, Stellenbosch : Stellenbosch University, 2014. http://hdl.handle.net/10019.1/95917.
Full textAbstract:
Thesis (MSc)--Stellenbosch University, 2014.ENGLISH ABSTRACT: Monocular structure from motion (SfM) is a widely researched problem, however many of the existing approaches prove to be too computationally expensive for use on mobile devices. In this thesis we investigate how inertial sensors can be used to increase the performance of SfM algorithms on mobile devices. Making use of the low cost inertial sensors found on most mobile devices we design and implement an extended Kalman filter (EKF) to exploit their complementary nature, in order to produce an accurate estimate of the attitude of the device. We make use of a quaternion based system model in order to linearise the measurement stage of the EKF, thus reducing its computational complexity. We use this attitude estimate to enhance the feature tracking and camera localisation stages in our SfM pipeline. In order to perform feature tracking we implement a hybrid tracking algorithm which makes use of Harris corners and an approximate nearest neighbour search to reduce the search space for possible correspondences. We increase the robustness of this approach by using inertial information to compensate for inter-frame camera rotation. We further develop an efficient bundle adjustment algorithm which only optimises the pose of the previous three key frames and the 3D map points common between at least two of these frames. We implement an optimisation based localisation algorithm which makes use of our EKF attitude estimate and the tracked features, in order to estimate the pose of the device relative to the 3D map points. This optimisation is performed in two steps, the first of which optimises only the translation and the second optimises the full pose. We integrate the aforementioned three sub-systems into an inertial assisted pose estimation pipeline. We evaluate our algorithms with the use of datasets captured on the iPhone 5 in the presence of a Vicon motion capture system for ground truth data. We find that our EKF can estimate the device’s attitude with an average dynamic accuracy of ±5°. Furthermore, we find that the inclusion of sensors into the visual pose estimation pipeline can lead to improvements in terms of robustness and computational efficiency of the algorithms and are unlikely to negatively affect the accuracy of such a system. Even though we managed to reduce execution time dramatically, compared to typical existing techniques, our full system is found to still be too computationally expensive for real-time performance and currently runs at 3 frames per second, however the ever improving computational power of mobile devices and our described future work will lead to improved performance. From this study we conclude that inertial sensors make a valuable addition into a visual pose estimation pipeline implemented on a mobile device.
AFRIKAANSE OPSOMMING: Enkel-kamera struktuur-vanaf-beweging (structure from motion, SfM) is ’n bekende navorsingsprobleem, maar baie van die bestaande benaderings is te berekeningsintensief vir gebruik op mobiele toestelle. In hierdie tesis ondersoek ons hoe traagheidsensors gebruik kan word om die prestasie van SfM algoritmes op mobiele toestelle te verbeter. Om van die lae-koste traagheidsensors wat op meeste mobiele toestelle gevind word gebruik te maak, ontwerp en implementeer ons ’n uitgebreide Kalman filter (extended Kalman filter, EKF) om hul komplementêre geaardhede te ontgin, en sodoende ’n akkurate skatting van die toestel se postuur te verkry. Ons maak van ’n kwaternioon-gebaseerde stelselmodel gebruik om die meetstadium van die EKF te lineariseer, en so die berekeningskompleksiteit te verminder. Hierdie afskatting van die toestel se postuur word gebruik om die fases van kenmerkvolging en kameralokalisering in ons SfM proses te verbeter. Vir kenmerkvolging implementeer ons ’n hibriede volgingsalgoritme wat gebruik maak van Harris-hoekpunte en ’n benaderde naaste-buurpunt-soektog om die soekruimte vir moontlike ooreenstemmings te verklein. Ons verhoog die robuustheid van hierdie benadering, deur traagheidsinligting te gebruik om vir kamerarotasies tussen raampies te kompenseer. Verder ontwikkel ons ’n doeltreffende bondelaanpassingsalgoritme wat slegs optimeer oor die vorige drie sleutelraampies, en die 3D punte gemeenskaplik tussen minstens twee van hierdie raampies. Ons implementeer ’n optimeringsgebaseerde lokaliseringsalgoritme, wat gebruik maak van ons EKF se postuurafskatting en die gevolgde kenmerke, om die posisie en oriëntasie van die toestel relatief tot die 3D punte in die kaart af te skat. Die optimering word in twee stappe uitgevoer: eerstens net oor die kamera se translasie, en tweedens oor beide die translasie en rotasie. Ons integreer die bogenoemde drie sub-stelsels in ’n pyplyn vir postuurafskatting met behulp van traagheidsensors. Ons evalueer ons algoritmes met die gebruik van datastelle wat met ’n iPhone 5 opgeneem is, terwyl dit in die teenwoordigheid van ’n Vicon bewegingsvasleggingstelsel was (vir die gelyktydige opneming van korrekte postuurdata). Ons vind dat die EKF die toestel se postuur kan afskat met ’n gemiddelde dinamiese akkuraatheid van ±5°. Verder vind ons dat die insluiting van sensors in die visuele postuurafskattingspyplyn kan lei tot verbeterings in terme van die robuustheid en berekeningsdoeltreffendheid van die algoritmes, en dat dit waarskynlik nie die akkuraatheid van so ’n stelsel negatief beïnvloed nie. Al het ons die uitvoertyd drasties verminder (in vergelyking met tipiese bestaande tegnieke) is ons volledige stelsel steeds te berekeningsintensief vir intydse verwerking op ’n mobiele toestel en hardloop tans teen 3 raampies per sekonde. Die voortdurende verbetering van mobiele toestelle se berekeningskrag en die toekomstige werk wat ons beskryf sal egter lei tot ’n verbetering in prestasie. Uit hierdie studie kan ons aflei dat traagheidsensors ’n waardevolle toevoeging tot ’n visuele postuurafskattingspyplyn kan maak.
7
Fathollahi, Ghezelghieh Mona. "Estimation of Human Poses Categories and Physical Object Properties from Motion Trajectories." Scholar Commons, 2017. http://scholarcommons.usf.edu/etd/6835.
Full textAbstract:
Despite the impressive advancements in people detection and tracking, safety is still a key barrier to the deployment of autonomous vehicles in urban environments [1]. For example, in non-autonomous technology, there is an implicit communication between the people crossing the street and the driver to make sure they have communicated their intent to the driver. Therefore, it is crucial for the autonomous car to infer the future intent of the pedestrian quickly. We believe that human body orientation with respect to the camera can help the intelligent unit of the car to anticipate the future movement of the pedestrians. To further improve the safety of pedestrians, it is important to recognize whether they are distracted, carrying a baby, or pushing a shopping cart. Therefore, estimating the fine- grained 3D pose, i.e. (x,y,z)-coordinates of the body joints provides additional information for decision-making units of driverless cars.
In this dissertation, we have proposed a deep learning-based solution to classify the categorized body orientation in still images. We have also proposed an efficient framework based on our body orientation classification scheme to estimate human 3D pose in monocular RGB images.
Furthermore, we have utilized the dynamics of human motion to infer the body orientation in image sequences. To achieve this, we employ a recurrent neural network model to estimate continuous body orientation from the trajectories of body joints in the image plane.
The proposed body orientation and 3D pose estimation framework are tested on the largest 3D pose estimation benchmark, Human3.6m (both in still images and video), and we have proved the efficacy of our approach by benchmarking it against the state-of-the-art approaches.
Another critical feature of self-driving car is to avoid an obstacle. In the current prototypes the car either stops or changes its lane even if it causes other traffic disruptions. However, there are situations when it is preferable to collide with the object, for example a foam box, rather than take an action that could result in a much more serious accident than collision with the object. In this dissertation, for the first time, we have presented a novel method to discriminate between physical properties of these types of objects such as bounciness, elasticity, etc. based on their motion characteristics . The proposed algorithm is tested on synthetic data, and, as a proof of concept, its effectiveness on a limited set of real-world data is demonstrated.
8
Almatrafi, Mohammed Mutlaq. "Optical Flow for Event Detection Camera." University of Dayton / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1576188397203882.
Full text
9
Lee, Hong Yun. "Deep Learning for Visual-Inertial Odometry: Estimation of Monocular Camera Ego-Motion and its Uncertainty." The Ohio State University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=osu156331321922759.
Full text
10
Ekström, Marcus. "Road Surface Preview Estimation Using a Monocular Camera." Thesis, Linköpings universitet, Datorseende, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-151873.
Full textAbstract:
Recently, sensors such as radars and cameras have been widely used in automotives, especially in Advanced Driver-Assistance Systems (ADAS), to collect information about the vehicle's surroundings. Stereo cameras are very popular as they could be used passively to construct a 3D representation of the scene in front of the car. This allowed the development of several ADAS algorithms that need 3D information to perform their tasks. One interesting application is Road Surface Preview (RSP) where the task is to estimate the road height along the future path of the vehicle. An active suspension control unit can then use this information to regulate the suspension, improving driving comfort, extending the durabilitiy of the vehicle and warning the driver about potential risks on the road surface. Stereo cameras have been successfully used in RSP and have demonstrated very good performance. However, the main disadvantages of stereo cameras are their high production cost and high power consumption. This limits installing several ADAS features in economy-class vehicles. A less expensive alternative are monocular cameras which have a significantly lower cost and power consumption. Therefore, this thesis investigates the possibility of solving the Road Surface Preview task using a monocular camera. We try two different approaches: structure-from-motion and Convolutional Neural Networks.The proposed methods are evaluated against the stereo-based system. Experiments show that both structure-from-motion and CNNs have a good potential for solving the problem, but they are not yet reliable enough to be a complete solution to the RSP task and be used in an active suspension control unit.
11
Josefsson, Mattias. "3D camera with built-in velocity measurement." Thesis, Linköpings universitet, Datorseende, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-68632.
Full textAbstract:
In today's industry 3D cameras are often used to inspect products. The camera produces both a 3D model and an intensity image by capturing a series of profiles of the object using laser triangulation. In many of these setups a physical encoder is attached to, for example, the conveyor belt that the product is travelling on. The encoder is used to get an accurate reading of the speed that the product has when it passes through the laser. Without this, the output image from the camera can be distorted due to a variation in velocity. In this master thesis a method for integrating the functionality of this physical encoder into the software of the camera is proposed. The object is scanned together with a pattern, with the help of this pattern the object can be restored to its original proportions.I dagens industri används ofta 3D-kameror för att inspektera produkter. Kameran producerar en 3D-modell samt en intensitetsbild genom att sätta ihop en serie av profilbilder av objektet som erhålls genom lasertriangulering. I många av dessa uppställningar används en fysisk encoder som återspeglar hastigheten på till exempel transportbandet som produkten ligger på. Utan den här encodern kan bilden som kameran fångar bli förvrängd på grund av hastighetsvariationer. I det här examensarbetet presenteras en metod för att integrera funktionaliteten av encodern in i kamerans mjukvara. För att göra detta krävs att ett mönster placeras längs med objektet som ska bli skannat. Mönstret återfinns i bilden fångad av kameran och med hjälp av detta mönster kan hastigheten bestämmas och objektets korrekta proportioner återställas.
12
Lam, Hong Kwai. "Automatic white balancing for digital camera and fast motion vector re-estimation for arbitrary downscaling of compressed video /." View abstract or full-text, 2004. http://library.ust.hk/cgi/db/thesis.pl?ELEC%202004%20LAMH.
Full textAbstract:
Thesis (M. Phil.)--Hong Kong University of Science and Technology, 2004.Includes bibliographical references (leaves 55-58). Also available in electronic version. Access restricted to campus users.
13
Fallqvist, Marcus. "Automatic Volume Estimation Using Structure-from-Motion Fused with a Cellphone's Inertial Sensors." Thesis, Linköpings universitet, Datorseende, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-144194.
Full textAbstract:
The thesis work evaluates a method to estimate the volume of stone and gravelpiles using only a cellphone to collect video and sensor data from the gyroscopesand accelerometers. The project is commissioned by Escenda Engineering withthe motivation to replace more complex and resource demanding systems with acheaper and easy to use handheld device. The implementation features popularcomputer vision methods such as KLT-tracking, Structure-from-Motion, SpaceCarving together with some Sensor Fusion. The results imply that it is possible toestimate volumes up to a certain accuracy which is limited by the sensor qualityand with a bias.I rapporten framgår hur volymen av storskaliga objekt, nämligen grus-och stenhögar,kan bestämmas i utomhusmiljö med hjälp av en mobiltelefons kamerasamt interna sensorer som gyroskop och accelerometer. Projektet är beställt avEscenda Engineering med motivering att ersätta mer komplexa och resurskrävandesystem med ett enkelt handhållet instrument. Implementationen använderbland annat de vanligt förekommande datorseendemetoderna Kanade-Lucas-Tommasi-punktspårning, Struktur-från-rörelse och 3D-karvning tillsammans medenklare sensorfusion. I rapporten framgår att volymestimering är möjligt mennoggrannheten begränsas av sensorkvalitet och en bias.
14
Deigmoeller, Joerg. "Intelligent image cropping and scaling." Thesis, Brunel University, 2011. http://bura.brunel.ac.uk/handle/2438/4745.
Full textAbstract:
Nowadays, there exist a huge number of end devices with different screen properties for watching television content, which is either broadcasted or transmitted over the internet. To allow best viewing conditions on each of these devices, different image formats have to be provided by the broadcaster. Producing content for every single format is, however, not applicable by the broadcaster as it is much too laborious and costly. The most obvious solution for providing multiple image formats is to produce one high resolution format and prepare formats of lower resolution from this. One possibility to do this is to simply scale video images to the resolution of the target image format. Two significant drawbacks are the loss of image details through ownscaling and possibly unused image areas due to letter- or pillarboxes. A preferable solution is to find the contextual most important region in the high-resolution format at first and crop this area with an aspect ratio of the target image format afterwards. On the other hand, defining the contextual most important region manually is very time consuming. Trying to apply that to live productions would be nearly impossible. Therefore, some approaches exist that automatically define cropping areas. To do so, they extract visual features, like moving reas in a video, and define regions of interest (ROIs) based on those. ROIs are finally used to define an enclosing cropping area. The extraction of features is done without any knowledge about the type of content. Hence, these approaches are not able to distinguish between features that might be important in a given context and those that are not. The work presented within this thesis tackles the problem of extracting visual features based on prior knowledge about the content. Such knowledge is fed into the system in form of metadata that is available from TV production environments. Based on the extracted features, ROIs are then defined and filtered dependent on the analysed content. As proof-of-concept, this application finally adapts SDTV (Standard Definition Television) sports productions automatically to image formats with lower resolution through intelligent cropping and scaling. If no content information is available, the system can still be applied on any type of content through a default mode. The presented approach is based on the principle of a plug-in system. Each plug-in represents a method for analysing video content information, either on a low level by extracting image features or on a higher level by processing extracted ROIs. The combination of plug-ins is determined by the incoming descriptive production metadata and hence can be adapted to each type of sport individually. The application has been comprehensively evaluated by comparing the results of the system against alternative cropping methods. This evaluation utilised videos which were manually cropped by a professional video editor, statically cropped videos and simply scaled, non-cropped videos. In addition to and apart from purely subjective evaluations, the gaze positions of subjects watching sports videos have been measured and compared to the regions of interest positions extracted by the system.
15
Efstratiou, Panagiotis. "Skeleton Tracking for Sports Using LiDAR Depth Camera." Thesis, KTH, Medicinteknik och hälsosystem, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-297536.
Full textAbstract:
Skeletal tracking can be accomplished deploying human pose estimation strategies. Deep learning is shown to be the paramount approach in the realm where in collaboration with a ”light detection and ranging” depth camera the development of a markerless motion analysis software system seems to be feasible. The project utilizes a trained convolutional neural network in order to track humans doing sport activities and to provide feedback after biomechanical analysis. Implementations of four filtering methods are presented regarding movement’s nature, such as kalman filter, fixedinterval smoother, butterworth and moving average filter. The software seems to be practicable in the field evaluating videos at 30Hz, as it is demonstrated by indoor cycling and hammer throwing events. Nonstatic camera behaves quite well against a standstill and upright person while the mean absolute error is 8.32% and 6.46% referential to left and right knee angle, respectively. An impeccable system would benefit not only the sports domain but also the health industry as a whole.Skelettspårning kan åstadkommas med hjälp av metoder för uppskattning av mänsklig pose. Djupinlärningsmetoder har visat sig vara det främsta tillvägagångssättet och om man använder en djupkamera med ljusdetektering och varierande omfång verkar det vara möjligt att utveckla ett markörlöst system för rörelseanalysmjukvara. I detta projekt används ett tränat neuralt nätverk för att spåra människor under sportaktiviteter och för att ge feedback efter biomekanisk analys. Implementeringar av fyra olika filtreringsmetoder för mänskliga rörelser presenteras, kalman filter, utjämnare med fast intervall, butterworth och glidande medelvärde. Mjukvaran verkar vara användbar vid fälttester för att utvärdera videor vid 30Hz. Detta visas genom analys av inomhuscykling och släggkastning. En ickestatisk kamera fungerar ganska bra vid mätningar av en stilla och upprättstående person. Det genomsnittliga absoluta felet är 8.32% respektive 6.46% då vänster samt höger knävinkel användes som referens. Ett felfritt system skulle gynna såväl idrottssom hälsoindustrin.
16
Szolgay, Daniel. "Video event detection and visual data pro cessing for multimedia applications." Thesis, Bordeaux 1, 2011. http://www.theses.fr/2011BOR14313/document.
Full textAbstract:
Cette thèse (i) décrit une procédure automatique pour estimer la condition d'arrêt des méthodes de déconvolution itératives basées sur un critère d'orthogonalité du signal estimé et de son gradient à une itération donnée; (ii) présente une méthode qui décompose l'image en une partie géométrique (ou "cartoon") et une partie "texture" en utilisation une estimation de paramètre et une condition d'arrêt basées sur la diffusion anisotropique avec orthogonalité, en utilisant le fait que ces deux composantes. "cartoon" et "texture", doivent être indépendantes; (iii) décrit une méthode pour extraire d'une séquence vidéo obtenue à partir de caméra portable les objets de premier plan en mouvement. Cette méthode augmente la compensation de mouvement de la caméra par une nouvelle estimation basée noyau de la fonction de probabilité de densité des pixels d'arrière-plan. Les méthodes présentées ont été testées et comparées aux algorithmes de l'état de l'artThis dissertation (i) describes an automatic procedure for estimating the stopping condition of non-regularized iterative deconvolution methods based on an orthogonality criterion of the estimated signal and its gradient at a given iteration; (ii) presents a decomposition method that splits the image into geometric (or cartoon) and texture parts using anisotropic diffusion with orthogonality based parameter estimation and stopping condition, utilizing the theory that the cartoon and the texture components of an image should be independent of each other; (iii) describes a method for moving foreground object extraction in sequences taken by wearable camera, with strong motion, where the camera motion compensated frame differencing is enhanced with a novel kernel-based estimation of the probability density function of the background pixels. The presented methods have been thoroughly tested and compared to other similar algorithms from the state-of-the-art
17
Zins, Matthieu. "Color Fusion and Super-Resolution for Time-of-Flight Cameras." Thesis, Linköpings universitet, Datorseende, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-141956.
Full textAbstract:
The recent emergence of time-of-flight cameras has opened up new possibilities in the world of computer vision. These compact sensors, capable of recording the depth of a scene in real-time, are very advantageous in many applications, such as scene or object reconstruction. This thesis first addresses the problem of fusing depth data with color images. A complete process to combine a time-of-flight camera with a color camera is described and its accuracy is evaluated. The results show that a satisfying precision is reached and that the step of calibration is very important. The second part of the work consists of applying super-resolution techniques to the time-of-flight camera in order to improve its low resolution. Different types of super-resolution algorithms exist but this thesis focuses on the combination of multiple shifted depth maps. The proposed framework is made of two steps: registration and reconstruction. Different methods for each step are tested and compared according to the improvements reached in term of level of details, sharpness and noise reduction. The results obtained show that Lucas-Kanade performs the best for the registration and that a non-uniform interpolation gives the best results in term of reconstruction. Finally, a few suggestions are made about future work and extensions for our solutions.
18
Schmidt, Eric. "Measuring the Speed of a Floorball Shot Using Trajectory Detection and Distance Estimation With a Smartphone Camera : Using OpenCV and Computer Vision on an iPhone to Detect the Speed of a Floorball Shot." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-190823.
Full textAbstract:
This thesis describes the possibilities of using smartphones and their cameras in combination with modern computer vision algorithms to track and measure the speed of a floorball. Previous research within the area is described and an explanation is given as to why an implementation using three-frame temporal differencing to detect objects in motion works best to detect and track the ball. 100 floorball shots were recorded and measured using a speedometer radar and two different smartphones, one running the application and the other recording each shot. The video recording for each shot was then used to manually create a baseline for speed comparison. A second experiment was later conducted to analyse the sensitivity and effect on the determined ball size in the floorball shot analysis. The results from the first experiment show that the speedometer radar results in average deviate by 12% from the speed baseline. The speedshooting application however has results that, on average, deviate from the speed baseline by 6%. Furthermore, the results show that a faulty ball size detection is the major cause of error in the speedshooting application. The main conclusion that can be drawn from this is that it is possible to use a smartphone and computer vision methodologies to determine the speed of a floorball shot. In fact, it is even possible to do so with greater accuracy than the radar used in the experiments in this thesis. However, to prove the accuracy of the application for normal use, further testing needs to be conducted in new experiment conditions, for example by recording shots at higher speeds than those recorded in the experiments in this thesis.
19
Dušek, Stanislav. "Určení parametrů pohybu ze snímků kamery." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2009. http://www.nusl.cz/ntk/nusl-217782.
Full textAbstract:
This thesis describe about determination of camera motion parameters in plane. At first there are introduce the basics of motion tracking, is focused to find out displacement between two input images. Below is describe the algorithm GoodFeatruresToTrack, which find out the most significant point in a first image. The point is search out the good point, which will be easy to track in next image, reduce the data volume and prepare the input information (array of significant point) for the algorithm Lucas-Kanade optical flow. In second part is deal with processing and utilization estimations optical flow. There is median filtration, below is describe computation of homogenous transformation, which describe all affine transformation in affine space. As the result are coordinates, which describe the shift between the two input images as X-axis and Y-axis value. The project used the library Open Computer Vision.
20
Verplaetse, Christopher James. "Inertial-optical motion-estimating camera for electronic cinematrography." Thesis, Massachusetts Institute of Technology, 1997. http://hdl.handle.net/1721.1/29128.
Full text
21
Zhang, Chunxiao. "Estimation of 3D human motion kinematics model from multiple cameras." Thesis, University of Central Lancashire, 2009. http://clok.uclan.ac.uk/19932/.
Full textAbstract:
Estimation of articulated human motion based on video sequences acquired from multiple synchronised cameras is an active and challenging research area. This is mainly due to the need of high dimensional non-linear models to describe the human motion, cluttered data, and occlusions present in the captured images. Although many diverse techniques have been proposed to solve this problem, none of the existing solutions is fully satisfactory. In this thesis, upper body motion tracking and full body motion tracking based on the annealed particle filter (APP) approach are presented. To successfully implement a body motion tracking algorithm, the first requirement is to prepare and pre-process the data. The work performed in this area includes calibration of multiple cameras, colour image segmentation to extract body silhouettes from the cluttered background, and visual hull reconstruction to provide voxels representing a human volume in 3D space. The second requirement is to build the models. Two set of models are proposed in this thesis. The first set is for upper body tracking and it contains point models and two-segment articulated arm models; the second set is for full body tracking and it contains five articulated chains as a full human model. The final requirement is to design a measurement method for aligning the models to the data. Two novel measurement methods are proposed for the motion tracking: one is based on a combination of different penalties tailored to each body part based on the percentage of the 3D to 2D projected body points, falling inside and outside the body silhouette, and the other is based on the symmetrical property of the intensity profile obtained from the body silhouette bisected by the 3D to 2D projection of the estimated skeletal model. Various evaluations were carried out to demonstrate the effectiveness of the algorithms implemented and the excellent performance of the proposed methods for upper body and full body motion tracking. These include the accuracy analysis of cameras calibration and image segmentation; the accuracy and speed of APF applied to the articulated arm model in tracking of the infra-red marker based human motion data; as well as the visual and quantitative assessments of the final results obtained from the proposed upper body and full body motion tracking.
22
Oreifej, Omar. "Robust Subspace Estimation Using Low-Rank Optimization. Theory and Applications in Scene Reconstruction, Video Denoising, and Activity Recognition." Doctoral diss., University of Central Florida, 2013. http://digital.library.ucf.edu/cdm/ref/collection/ETD/id/5684.
Full textAbstract:
In this dissertation, we discuss the problem of robust linear subspace estimation using low-rank optimization and propose three formulations of it. We demonstrate how these formulations can be used to solve fundamental computer vision problems, and provide superior performance in terms of accuracy and running time. Consider a set of observations extracted from images (such as pixel gray values, local features, trajectories...etc). If the assumption that these observations are drawn from a liner subspace (or can be linearly approximated) is valid, then the goal is to represent each observation as a linear combination of a compact basis, while maintaining a minimal reconstruction error. One of the earliest, yet most popular, approaches to achieve that is Principal Component Analysis (PCA). However, PCA can only handle Gaussian noise, and thus suffers when the observations are contaminated with gross and sparse outliers. To this end, in this dissertation, we focus on estimating the subspace robustly using low-rank optimization, where the sparse outliers are detected and separated through the `1 norm. The robust estimation has a two-fold advantage: First, the obtained basis better represents the actual subspace because it does not include contributions from the outliers. Second, the detected outliers are often of a specific interest in many applications, as we will show throughout this thesis. We demonstrate four different formulations and applications for low-rank optimization. First, we consider the problem of reconstructing an underwater sequence by removing the turbulence caused by the water waves. The main drawback of most previous attempts to tackle this problem is that they heavily depend on modelling the waves, which in fact is ill-posed since the actual behavior of the waves along with the imaging process are complicated and include several noise components; therefore, their results are not satisfactory. In contrast, we propose a novel approach which outperforms the state-of-the-art. The intuition behind our method is that in a sequence where the water is static, the frames would be linearly correlated. Therefore, in the presence of water waves, we may consider the frames as noisy observations drawn from a the subspace of linearly correlated frames. However, the noise introduced by the water waves is not sparse, and thus cannot directly be detected using low-rank optimization. Therefore, we propose a data-driven two-stage approach, where the first stage “sparsifies” the noise, and the second stage detects it. The first stage leverages the temporal mean of the sequence to overcome the structured turbulence of the waves through an iterative registration algorithm. The result of the first stage is a high quality mean and a better structured sequence; however, the sequence still contains unstructured sparse noise. Thus, we employ a second stage at which we extract the sparse errors from the sequence through rank minimization. Our method converges faster, and drastically outperforms state of the art on all testing sequences. Secondly, we consider a closely related situation where an independently moving object is also present in the turbulent video. More precisely, we consider video sequences acquired in a desert battlefields, where atmospheric turbulence is typically present, in addition to independently moving targets. Typical approaches for turbulence mitigation follow averaging or de-warping techniques. Although these methods can reduce the turbulence, they distort the independently moving objects which can often be of great interest. Therefore, we address the problem of simultaneous turbulence mitigation and moving object detection. We propose a novel three-term low-rank matrix decomposition approach in which we decompose the turbulence sequence into three components: the background, the turbulence, and the object. We simplify this extremely difficult problem into a minimization of nuclear norm, Frobenius norm, and L1 norm. Our method is based on two observations: First, the turbulence causes dense and Gaussian noise, and therefore can be captured by Frobenius norm, while the moving objects are sparse and thus can be captured by L1 norm. Second, since the object's motion is linear and intrinsically different than the Gaussian-like turbulence, a Gaussian-based turbulence model can be employed to enforce an additional constraint on the search space of the minimization. We demonstrate the robustness of our approach on challenging sequences which are significantly distorted with atmospheric turbulence and include extremely tiny moving objects. In addition to robustly detecting the subspace of the frames of a sequence, we consider using trajectories as observations in the low-rank optimization framework. In particular, in videos acquired by moving cameras, we track all the pixels in the video and use that to estimate the camera motion subspace. This is particularly useful in activity recognition, which typically requires standard preprocessing steps such as motion compensation, moving object detection, and object tracking. The errors from the motion compensation step propagate to the object detection stage, resulting in miss-detections, which further complicates the tracking stage, resulting in cluttered and incorrect tracks. In contrast, we propose a novel approach which does not follow the standard steps, and accordingly avoids the aforementioned difficulties. Our approach is based on Lagrangian particle trajectories which are a set of dense trajectories obtained by advecting optical flow over time, thus capturing the ensemble motions of a scene. This is done in frames of unaligned video, and no object detection is required. In order to handle the moving camera, we decompose the trajectories into their camera-induced and object-induced components. Having obtained the relevant object motion trajectories, we compute a compact set of chaotic invariant features, which captures the characteristics of the trajectories. Consequently, a SVM is employed to learn and recognize the human actions using the computed motion features. We performed intensive experiments on multiple benchmark datasets, and obtained promising results. Finally, we consider a more challenging problem referred to as complex event recognition, where the activities of interest are complex and unconstrained. This problem typically pose significant challenges because it involves videos of highly variable content, noise, length, frame size ... etc. In this extremely challenging task, high-level features have recently shown a promising direction as in [53, 129], where core low-level events referred to as concepts are annotated and modeled using a portion of the training data, then each event is described using its content of these concepts. However, because of the complex nature of the videos, both the concept models and the corresponding high-level features are significantly noisy. In order to address this problem, we propose a novel low-rank formulation, which combines the precisely annotated videos used to train the concepts, with the rich high-level features. Our approach finds a new representation for each event, which is not only low-rank, but also constrained to adhere to the concept annotation, thus suppressing the noise, and maintaining a consistent occurrence of the concepts in each event. Extensive experiments on large scale real world dataset TRECVID Multimedia Event Detection 2011 and 2012 demonstrate that our approach consistently improves the discriminativity of the high-level features by a significant margin.Ph.D.
Doctorate
Electrical Engineering and Computing
Engineering and Computer Science
Computer Engineering
23
Lao, Yizhen. "3D Vision Geometry for Rolling Shutter Cameras." Thesis, Université Clermont Auvergne (2017-2020), 2019. http://www.theses.fr/2019CLFAC009/document.
Full textAbstract:
De nombreuses caméras CMOS modernes sont équipées de capteurs Rolling Shutter (RS). Ces caméras à bas coût et basse consommation permettent d’atteindre de très hautes fréquences d’acquisition. Dans ce mode d’acquisition, les lignes de pixels sont exposées séquentiellement du haut vers le bas de l'image. Par conséquent, les images capturées alors que la caméra et/ou la scène est en mouvement présentent des distorsions qui rendent les algorithmes classiques au mieux moins précis, au pire inutilisables en raison de singularités ou de configurations dégénérées. Le but de cette thèse est de revisiter la géométrie de la vision 3D avec des caméras RS en proposant des solutions pour chaque sous-tâche du pipe-line de Structure-from-Motion (SfM).Le chapitre II présente une nouvelle méthode de correction du RS en utilisant les droites. Contrairement aux méthodes existantes, qui sont itératives et font l’hypothèse dite Manhattan World (MW), notre solution est linéaire et n’impose aucune contrainte sur l’orientation des droites 3D. De plus, la méthode est intégrée dans un processus de type RANSAC permettant de distinguer les courbes qui sont des projections de segments droits de celles qui correspondent à de vraies courbes 3D. La méthode de correction est ainsi plus robuste et entièrement automatisée.Le chapitre III revient sur l'ajustement faisceaux ou bundle adjustment (BA). Nous proposons un nouvel algorithme basé sur une erreur de projection dans laquelle l’index de ligne des points projetés varie pendant l’optimisation afin de garder une cohérence géométrique contrairement aux méthodes existantes qui considère un index fixe (celui mesurés dans l’image). Nous montrons que cela permet de lever la dégénérescence dans le cas où les directions de scan des images sont trop proches (cas très communs avec des caméras embraquées sur un véhicule par exemple). Dans le chapitre VI nous étendons le concept d'homographie aux cas d’images RS en démontrant que la relation point-à-point entre deux images d’un nuage de points coplanaires pouvait s’exprimer sous la forme de 3 à 7 matrices de taille 3X3 en fonction du modèle de mouvement utilisé. Nous proposons une méthode linéaire pour le calcul de ces matrices. Ces dernières sont ensuite utilisées pour résoudre deux problèmes classiques en vision par ordinateur à savoir le calcul du mouvement relatif et le « mosaïcing » dans le cas RS.Dans le chapitre V nous traitons le problème de calcul de pose et de reconstruction multi-vues en établissant une analogie avec les méthodes utilisées pour les surfaces déformables telles que SfT (Structure-from-Template) et NRSfM (Non Rigid Structure-from-Motion). Nous montrons qu’une image RS d’une scène rigide en mouvement peut être interprétée comme une image Global Shutter (GS) d’une surface virtuellement déformée (par l’effet RS). La solution proposée pour estimer la pose et la structure 3D de la scène est ainsi composée de deux étapes. D’abord les déformations virtuelles sont d’abord calculées grâce à SfT ou NRSfM en assumant un modèle GS classique (relaxation du modèle RS). Ensuite, ces déformations sont réinterprétées comme étant le résultat du mouvement durant l’acquisition (réintroduction du modèle RS). L’approche proposée présente ainsi de meilleures propriétés de convergence que les approches existantesMany modern CMOS cameras are equipped with Rolling Shutter (RS) sensors which are considered as low cost, low consumption and fast cameras. In this acquisition mode, the pixel rows are exposed sequentially from the top to the bottom of the image. Therefore, images captured by moving RS cameras produce distortions (e.g. wobble and skew) which make the classic algorithms at best less precise, at worst unusable due to singularities or degeneracies. The goal of this thesis is to propose a general framework for modelling and solving structure from motion (SfM) with RS cameras. Our approach consists in addressing each sub-task of the SfM pipe-line (namely image correction, absolute and relative pose estimation and bundle adjustment) and proposing improvements.The first part of this manuscript presents a novel RS correction method which uses line features. Unlike existing methods, which uses iterative solutions and make Manhattan World (MW) assumption, our method R4C computes linearly the camera instantaneous-motion using few image features. Besides, the method was integrated into a RANSAC-like framework which enables us to detect curves that correspond to actual 3D straight lines and reject outlier curves making image correction more robust and fully automated.The second part revisits Bundle Adjustment (BA) for RS images. It deals with a limitation of existing RS bundle adjustment methods in case of close read-out directions among RS views which is a common configuration in many real-life applications. In contrast, we propose a novel camera-based RS projection algorithm and incorporate it into RSBA to calculate reprojection errors. We found out that this new algorithm makes SfM survive the degenerate configuration mentioned above.The third part proposes a new RS Homography matrix based on point correspondences from an RS pair. Linear solvers for the computation of this matrix are also presented. Specifically, a practical solver with 13 point correspondences is proposed. In addition, we present two essential applications in computer vision that use RS homography: plane-based RS relative pose estimation and RS image stitching. The last part of this thesis studies absolute camera pose problem (PnP) and SfM which handle RS effects by drawing analogies with non-rigid vision, namely Shape-from-Template (SfT) and Non-rigid SfM (NRSfM) respectively. Unlike all existing methods which perform 3D-2D registration after augmenting the Global Shutter (GS) projection model with the velocity parameters under various kinematic models, we propose to use local differential constraints. The proposed methods outperform stat-of-the-art and handles configurations that are critical for existing methods
24
Šimetka, Vojtěch. "3D Rekonstrukce historických míst z obrázků na Flickru." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2015. http://www.nusl.cz/ntk/nusl-234976.
Full textAbstract:
Tato práce popisuje problematiku návrhu a vývoje aplikace pro rekonstrukci 3D modelů z 2D obrazových dat, označované jako bundle adjustment. Práce analyzuje proces 3D rekonstrukce a důkladně popisuje jednotlivé kroky. Prvním z kroků je automatizované získání obrazové sady z internetu. Je představena sada skriptů pro hromadné stahování obrázků ze služeb Flickr a Google Images a shrnuty požadavky na tyto obrázky pro co nejlepší 3D rekonstrukci. Práce dále popisuje různé detektory, extraktory a párovací algoritmy klíčových bodů v obraze s cílem najít nejvhodnější kombinaci pro rekonstrukci budov. Poté je vysvětlen proces rekonstrukce 3D struktury, její optimalizace a jak je tato problematika realizovaná v našem programu. Závěr práce testuje výsledky získané z implementovaného programu pro několik různých datových sad a porovnává je s výsledky ostatních podobných programů, představených v úvodu práce.
25
Svoboda, Ondřej. "Analýza vlastností stereokamery ZED ve venkovním prostředí." Master's thesis, Vysoké učení technické v Brně. Fakulta strojního inženýrství, 2019. http://www.nusl.cz/ntk/nusl-399416.
Full textAbstract:
The Master thesis is focused on analyzing stereo camera ZED in the outdoor environment. There is compared ZEDfu visual odometry with commonly used methods like GPS or wheel odometry. Moreover, the thesis includes analyses of SLAM in the changeable outdoor environment, too. The simultaneous mapping and localization in RTAB-Map were processed separately with SIFT and BRISK descriptors. The aim of this master thesis is to analyze the behaviour ZED camera in the outdoor environment for future implementation in mobile robotics.
26
Magerand, Ludovic. "Calcul de pose dynamique avec les caméras CMOS utilisant une acquisition séquentielle." Thesis, Clermont-Ferrand 2, 2014. http://www.theses.fr/2014CLF22534/document.
Full textAbstract:
En informatique, la vision par ordinateur s’attache à extraire de l’information à partir de caméras. Les capteurs de celles-ci peuvent être produits avec la technologie CMOS que nous retrouvons dans les appareils mobiles en raison de son faible coût et d’un encombrement réduit. Cette technologie permet d’acquérir rapidement l’image en exposant les lignes de l’image de manière séquentielle. Cependant cette méthode produit des déformations dans l’image s’il existe un mouvement entre la caméra et la scène filmée. Cet effet est connu sous le nom de «Rolling Shutter» et de nombreuses méthodes ont tenté de corriger ces artefacts. Plutôt que de le corriger, des travaux antérieurs ont développé des méthodes pour extraire de l’information sur le mouvement à partir de cet effet. Ces méthodes reposent sur une extension de la modélisation géométrique classique des caméras pour prendre en compte l’acquisition séquentielle et le mouvement entre le capteur et la scène, considéré uniforme. À partir de cette modélisation, il est possible d’étendre le calcul de pose habituel (estimation de la position et de l’orientation de la scène par rapport au capteur) pour estimer aussi les paramètres du mouvement. Dans la continuité de cette démarche, nous présenterons une généralisation à des mouvements non-uniformes basée sur un lissage des dérivées des paramètres de mouvement. Ensuite nous présenterons une modélisation polynomiale du «Rolling Shutter» et une méthode d’optimisation globale pour l’estimation de ces paramètres. Correctement implémenté, cela permet de réaliser une mise en correspondance automatique entre le modèle tridimensionnel et l’image. Pour terminer nous comparerons ces différentes méthodes tant sur des données simulées que sur des données réelles et concluronsComputer Vision, a field of Computer Science, is about extracting information from cameras. Their sensors can be produced using the CMOS technology which is widely used on mobile devices due to its low cost and volume. This technology allows a fast acquisition of an image by sequentially exposin the scan-line. However this method produces some deformation in the image if there is a motion between the camera and the filmed scene. This effect is known as Rolling Shutter and various methods have tried to remove these artifacts. Instead of correcting it, previous works have shown methods to extract information on the motion from this effect. These methods rely on a extension of the usual geometrical model of cameras by taking into account the sequential acquisition and the motion, supposed uniform, between the sensor and the scene. From this model, it’s possible to extend the usual pose estimation (estimation of position and orientation of the camera in the scene) to also estimate the motion parameters. Following on from this approach, we will present an extension to non-uniform motions based on a smoothing of the derivatives of the motion parameters. Afterwards, we will present a polynomial model of the Rolling Shutter and a global optimisation method to estimate the motion parameters. Well implemented, this enables to establish an automatic matching between the 3D model and the image. We will conclude with a comparison of all these methods using either simulated or real data
27
Hennebert, Christine. "Analyse d'une scène dynamique avec une caméra en mouvement : système de détection de cibles mobiles." Grenoble INPG, 1996. http://www.theses.fr/1996INPG0140.
Full textAbstract:
Cette these traite de la detection d'objets mobiles dans des sequences d'images monoculaires acquises a l'aide d'un capteur en mouvement. Nous proposons une methodologie dediee a la detection de petits objets mobiles dans des images de scenes exterieures reelles dans le domaine visible ou infrarouge. De facon a pouvoir detecter des objets de tres faible vitesse apparente, nous privilegions une analyse de l'information sur un intervalle temporel etendu. Nous avons fait le choix de compenser le mouvement apparent dominant du au deplacement du capteur pour plusieurs images consecutives dans le but de former une sous-sequence de quelques images dans laquelle le capteur semble virtuellement fixe. Nous avons egalement developpe une technique de structuration d'une scene exterieure selon ses differents plans de profondeur pour traiter les cas ou le mouvement 2d du au deplacemente du capteur ne peut pas etre globalement modelise et compense. Cette etape de segmentation s'appuie sur une modelisation hierarchique a deux niveaux de modeles, l'un local (niveau pixel) et l'autre global (niveau region). Une decomposition temporelle adequate est ensuite utilisee pour renforcer le signal correspondant aux objets en mouvement dans la sous-sequence d'images. Le probleme de la detection des objets mobiles est formule comme un probleme d'etiquetage impliquant une regularisation statistique a l'aide de champs de markov. Ce cadre permet de traduire des connaissances a priori contextuelles sur les primitives correspondant aux objets mobiles a detecter. L'ensemble de notre methode a ete evalue et valide sur des sequences d'images variees, representatives de nombreuses situations reelles complexes
28
Vestin, Albin, and Gustav Strandberg. "Evaluation of Target Tracking Using Multiple Sensors and Non-Causal Algorithms." Thesis, Linköpings universitet, Reglerteknik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-160020.
Full textAbstract:
Today, the main research field for the automotive industry is to find solutions for active safety. In order to perceive the surrounding environment, tracking nearby traffic objects plays an important role. Validation of the tracking performance is often done in staged traffic scenarios, where additional sensors, mounted on the vehicles, are used to obtain their true positions and velocities. The difficulty of evaluating the tracking performance complicates its development. An alternative approach studied in this thesis, is to record sequences and use non-causal algorithms, such as smoothing, instead of filtering to estimate the true target states. With this method, validation data for online, causal, target tracking algorithms can be obtained for all traffic scenarios without the need of extra sensors. We investigate how non-causal algorithms affects the target tracking performance using multiple sensors and dynamic models of different complexity. This is done to evaluate real-time methods against estimates obtained from non-causal filtering. Two different measurement units, a monocular camera and a LIDAR sensor, and two dynamic models are evaluated and compared using both causal and non-causal methods. The system is tested in two single object scenarios where ground truth is available and in three multi object scenarios without ground truth. Results from the two single object scenarios shows that tracking using only a monocular camera performs poorly since it is unable to measure the distance to objects. Here, a complementary LIDAR sensor improves the tracking performance significantly. The dynamic models are shown to have a small impact on the tracking performance, while the non-causal application gives a distinct improvement when tracking objects at large distances. Since the sequence can be reversed, the non-causal estimates are propagated from more certain states when the target is closer to the ego vehicle. For multiple object tracking, we find that correct associations between measurements and tracks are crucial for improving the tracking performance with non-causal algorithms.
29
"Multiple camera pose estimation." Thesis, 2008. http://library.cuhk.edu.hk/record=b6074556.
Full textAbstract:
Additionally, we suggest a new formulation for the perspective camera projection matrix. In particular, regarding how the 3 x 3 rotation matrix, R, of the camera should be incorporated into the 3 x 4 camera projection matrix, P. We show that the incorporated rotation should neither be the camera rotation R nor its transpose, but a reversed (left-handed) version of it. The fundamental matrix between a pair of stereo cameras is reformulated more accurately accordingly. This is extremely useful when we want to calculate the fundamental matrix accurately from the stereo camera matrices. It is especially true when the feature correspondences are too few for robust methods, such as RANSAC, to operate. We expect that this new model would have an impact on various applications.Furthermore, the process of estimating the rotation and translation parameters between a stereo pair from the essential matrix is investigated. This is an essential step for our multi-camera pose estimation method. We show that there are 16 solutions based on the singular value decomposition (not four or eight as previously thought). We also suggest a checking step to ascertain that the proposed algorithm will come up with accurate results. The checking step ensures the accuracy of the fundamental matrix calculated using the pose obtained. This provides a speedy way to calibrate a stereo rig. Our proposed theories are supported by the real and synthetic data experiments reported in this thesis.
In this thesis, we solve the pose estimation problem for robot motion by placing multiple cameras on the robot. In particular, we use four cameras arranged as two back-to-back stereo pairs combined with the Extended Kalman Filter (EKF). The EKF is used to provide a frame by frame recursive solution suitable for the real-time application at hand. The reason for using multiple cameras is that the pose estimation problem is more constrained for multiple cameras than for a single camera. Their use is further justified by the drop in price which is accompanied by the remarkable increase in accuracy. Back-to-back cameras are used since they are likely to have a larger field of view, provide more information, and capture more features. In this way, they are more likely to disambiguate the pose translation and rotation parameters. Stereo information is used in self-initialization and outlier rejection. Simple yet efficient methods have been proposed to tackle the problem of long-sequence drift. Our approaches have been compared, under different motion patterns, to other methods in the literature which use a single camera. Both the simulations and the real experiments show that our approaches are the most robust and accurate among them all as well as fast enough to realize the real-time requirement of robot navigation.
Mohammad Ehab Mohammad Ragab.
"April 2008."
Adviser: K. H. Wong.
Source: Dissertation Abstracts International, Volume: 70-03, Section: B, page: 1763.
Thesis (Ph.D.)--Chinese University of Hong Kong, 2008.
Includes bibliographical references (p. 138-148) and index.
Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web.
Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web.
Abstracts in English and Chinese.
School code: 1307.
30
Li, Kun-Hung, and 李昆鴻. "Feature-Based Motion Estimation for Underwater Towed Camera." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/20216010484193983786.
Full textAbstract:
碩士國立中山大學
海下科技暨應用海洋物理研究所
102
When TowCam (Towed Camera System) is under the deep sea exploration, its moving track and heading always have different direction with degree of α caused by the current. This situation will make images shot by the camera mounted on the vehicle to difficultly be processed by the photo mosaicking method and get the deformed or unaccepted mosaic results. In this thesis, we used the SURF (speeded-up robust feature) algorithm to extract the critical point of the shot image to estimate the declination between the heading and the track for future development of visual servo control of TowCam. The images shot by the Twist-Pair TowCam (TP-TowCam) were also used to check the reliable of estimated algorithm in the filed experiment test and to find the best Hessian threshold value of SURF algorithm for the estimation. The results of algorithm showed the good estimation even in the turbid condition and the acceptable displacement of moving vehicle in the unit time was also increased, indicating the improvement of evaluation.
31
Lai, Chien-Ming, and 賴建明. "A Study on Camera Motion Estimation in MPEG Video." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/97174028743945158542.
Full textAbstract:
碩士國立成功大學
工程科學系碩博士班
95
Camera motion estimation is very important from a video processing view. Video application, including object segmentation and tracking, mosaic and content-based video indexing and retrieval, based on the video content should represent motion efficiently. Since, to decode MPEG video and estimate camera motion is extremely time-consuming. To obtain efficient estimates of camera motion by directly processing data easily obtained from MPEG-compressed video becomes more important. In this thesis, two main concerns of camera motion estimation from motion vector are addressed. Firstly, we introduce the connection from a GOP to next GOP by B-frame bidirectional reference. Secondly, we propose a 2-pass camera motion estimation to cope with outliers caused by the uncertainty of motion vectors directly from MPEG video format. Experiment results show that the 2-pass camera motion estimation method is reliable. Finally, we have developed a mosaic system by applying the proposed method.
32
Hsiao, Ching-Chun, and 蕭晴駿. "Model-Based Pose Estimation for Multi-Camera Motion Capture System." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/79385950596603901992.
Full text
33
Liu, Jen-Chu, and 劉仁竹. "Nonlinear filters for Single Camera Based Motion and Shape Estimation." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/15495303298361539559.
Full textAbstract:
碩士國立臺灣海洋大學
輪機工程系
97
The accurate of estimating motion and shape of a moving object is a challenging task because of great variety of noise such as electronic component and influence of external environment etc. In order to alleviate the noise problem, this paper use kalman filter to reduces noise in the streaming video to get more accurate estimation in feature point on the object. Extended Kalman filter have to neglect higher-order derivatives in the nonlinear system to get linearization. However, it will cause unsteady condition. The Unscented Kalman filter uses a deterministic sampling approach to capture the mean and covariance estimates with a minimal set of sample points. UKF can be accurate to the second order for any nonlinearity, avoiding Jacobian’s computation. This paper uses a deterministic sampling of UKF with rigid body motion dynamics, shape dynamics, optical flow dynamics to estimate feature points on the moving object. Results obtained shows that UKF is accurate and reliable to get motion and shape of the object.
34
E, Yen-Chi, and 鄂彥齊. "Ego-motion Estimation Based on RGB-D Camera and Inertial Sensor." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/01115649228044152260.
Full textAbstract:
碩士國立臺灣大學
資訊網路與多媒體研究所
103
Ego-motion estimation has a wide variety of applications in robot control and automation. Proper local estimation of ego-motion benefits to recognize surrounding environment and recover the trajectory traversed for autonomous robot. In this thesis, we present a system that estimates ego-motion by fusing key frame based visual odometry and inertial measurements. The hardware of the system includes a RGB-D camera for capturing color and depth images and an Inertial Measurement Unit (IMU) for acquiring inertial measurements. Motion of camera between two consecutive images is estimated by finding correspondences of visual features. Rigidity constraints are used to efficiently remove outliers from a set of initial correspondence. Moreover, we apply random sample consensus (RANSAC) to handle the effect of the remaining outliers in the motion estimation step. These strategies are reasonable to insure that the remaining correspondences which involved in motion estimation almost contain inliers. Several experiments with different kind of camera movements are performed to show that the robustness and accuracy of the ego-motion estimation algorithm, and the ability of our system to handle the real scene data correctly.
35
Tsao, Tai-Chia, and 曹太嘉. "Omni-Directional Lane Detection and Vehicle Motion Estimation with Multi-Camera Vision." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/vtbhp4.
Full textAbstract:
碩士國立臺北科技大學
電機工程系研究所
96
Driver assistant system has been an active research topic in intelligent transportation systems. It could be used to provide surrounding dynamics. It can also be integrated into an adaptive cruise control system. This paper presents an omnidirectional lane detection and vehicle motion estimation system. The system employs a multi-camera vision and vehicle detection system to detect the surrounding vehicles. Based on the detected vehicles, the system uses inverse perspective projection and motion estimate techniques to estimate the motion of surrounding vehicles in Cartesian space and to build a bird’s eye view map. To make the vehicle motion estimation more accurate and reliable, Kalman filter, Extended Kalman filter, and particle filter have been used to estimate the motion of surrounding the vehicles. Meanwhile, the system integrates a lane detection technique to detect the lane lines and reconstruct them in Cartesian space to complete the bird’s eye view map with surrounding traffic. Our approach has been successfully validated in real traffic environments by performing experiments with 6 CCD cameras mounted onboard a highway vehicle.
36
Wan, Yi-Chen, and 萬宜蓁. "Algorithm and Architecture Design of RANSAC-Based Camera Motion Estimation for Action Recognition." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/tj8vb7.
Full textAbstract:
碩士國立臺灣大學
電子工程學研究所
106
Camera motion is one of the most challenges in action recognition in the real world. Improved Dense Trajectories introduced the concept of Warped Optical Flow which use RANSAC (Random Sample Consensus Algorithm) to approximate the camera motion and cancel out camera motion from the optical flow. The work significantly improved the performance of action recognition. This thesis proposes the real-time hardware architecture called Homography Estimation Processor using RANSAC for action recognition or other general systems. We use the SVD-based linear solver with the re-estimation method which provides the numerical stability and robust estimation. The system throughput is improved by hardware technique, including mesh-connected array architecture for SVD, pipelining and parallelization architectures. We also provide the flexibility using the folded technique in conjunction with parallelized architectures that can be easily configured to a different specification. The synthesis result of our proposed design using 40 nm TSMC technology is the gate count of 808.94 k and the SRAM size of 15.75 k Byte. The proposed Homography Estimation Processor can support 1000 matches and 2000 iterations with the throughput of at least 30 fps, and speeds up at least 73.17 times compared to software.
37
"Temporal Coding of Cortical Neural Signals and Camera Motion Estimation in Target Tracking." Doctoral diss., 2012. http://hdl.handle.net/2286/R.I.14715.
Full textAbstract:
abstract: This dissertation includes two parts. First it focuses on discussing robust signal processing algorithms, which lead to consistent performance under perturbation or uncertainty in video target tracking applications. Projective distortion plagues the quality of long sequence mosaicking which results in loosing important target information. Some correction techniques require prior information. A new algorithm is proposed in this dissertation to this very issue. Optimization and parameter tuning of a robust camera motion estimation as well as implementation details are discussed for a real-time application using an ordinary general-purpose computer. Performance evaluations on real-world unmanned air vehicle (UAV) videos demonstrate the robustness of the proposed algorithms. The second half of the dissertation addresses neural signal analysis and modeling. Neural waveforms were recorded from rats' motor cortical areas while rats performed a learning control task. Prior to analyzing and modeling based on the recorded neural signal, neural action potentials are processed to detect neural action potentials which are considered the basic computation unit in the brain. Most algorithms rely on simple thresholding, which can be subjective. This dissertation proposes a new detection algorithm, which is an automatic procedure based on signal-to-noise ratio (SNR) from the neural waveforms. For spike sorting, this dissertation proposes a classification algorithm based on spike features in the frequency domain and adaptive clustering method such as the self-organizing map (SOM). Another major contribution of the dissertation is the study of functional interconnectivity of neurons in an ensemble. These functional correlations among neurons reveal spatial and temporal statistical dependencies, which consequently contributes to the understanding of a neuronal substrate of meaningful behaviors. This dissertation proposes a new generalized yet simple method to study adaptation of neural ensemble activities of a rat's motor cortical areas during its cognitive learning process. Results reveal interesting temporal firing patterns underlying the behavioral learning process.Dissertation/Thesis
Ph.D. Electrical Engineering 2012
38
Liou, Yun-Jung, and 劉允中. "An Improved CamShift Algorithm Based on Adaptive Motion Estimation for Multiple Camera Systems." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/78721416340903036566.
Full textAbstract:
碩士淡江大學
電機工程學系碩士班
100
Smart video surveillance has been developed for a long time, and many approaches to track moving objects have been proposed in recent years. The research of good tracking algorithms becomes one of the main streams for the smart video surveillance research. Multiple moving object tracking is a fundamental task on smart video surveillance systems, because it provides a focus of attention for further investigation. Video surveillance using multiple cameras system has attracted increasing interest in recent years. Moving objects occlusion is a key operation using correspondence between multiple cameras for surveillance system. In this thesis, the current state-of-the-art in moving objects tracker for multiple cameras surveillance has been surveyed. An efficient modified adaptive CamShift structure is proposed to further reduce the computational cost and increase the object tracking information in occlusion image. In this work, a new CamShift approach, directional prediction for adaptive CamShift algorithm, is proposed to improve the tracking accuracy rate. According to the characteristic of the center-based motion vector distribution for the real-world video sequence, this thesis employs an adaptive pattern (ASP) search to refine the central area search. Furthermore for estimation in large motion situations, the strategy of the adaptive CamShift search can preserve good performance. Experimental results indicate that the accuracy rate of the adaptive CamShift algorithm is better than that of the CamShift algorithm. Furthermore, the proposed method has given an average accuracy rate of 90%, and the operation speed can reach 12 FPS with frame size of 320
39
Diviš, Jiří. "Visual odometry from omnidirectional camera." Master's thesis, 2013. http://www.nusl.cz/ntk/nusl-328572.
Full textAbstract:
We present a system that estimates the motion of a robot relying solely on images from onboard omnidirectional camera (visual odometry). Compared to other visual odometry hardware, ours is unusual in utilizing high resolution, low frame-rate (1 to 3 Hz) omnidirectional camera mounted on a robot that is propelled using continuous tracks. We focus on high precision estimates in scenes, where objects are far away from the camera. This is achieved by utilizing omnidirectional camera that is able to stabilize the motion estimates between camera frames that are known to be ill-conditioned for narrow field of view cameras. We employ feature based-approach for estimation camera motion. Given our hardware, possibly high ammounts of camera rotation between frames can occur. Thus we use techniques of feature matching rather than feature tracking.
40
Diviš, Jiří. "Visual odometry from omnidirectional camera." Master's thesis, 2012. http://www.nusl.cz/ntk/nusl-305129.
Full textAbstract:
We present a system that estimates the motion of a robot relying solely on images from onboard omnidirectional camera (visual odometry). Compared to other visual odometry hardware, ours is unusual in utilizing high resolution, low frame-rate (1 to 3 Hz) omnidirectional camera mounted on a robot that is propelled using continuous tracks. We focus on high precision estimates in scenes, where objects are far away from the camera. This is achieved by utilizing omnidirectional camera that is able to stabilize the motion estimates between camera frames that are known to be ill-conditioned for narrow field of view cameras and the fact that low frame-rate of the imaging system allows us to focus computational resources on utilizing high resolution images. We employ feature based-approach for estimation camera motion. Given our hardware, possibly high ammounts of camera rotation between frames can occur. Thus we use techniques of feature matching rather than feature tracking.
41
Hong, Kai-Chen, and 洪楷宸. "The Study of Ego-motion Estimation for a Moving Object with Monocular Camera using Visual Odometry." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/x64wny.
Full textAbstract:
碩士國立交通大學
電控工程研究所
107
Visual odometry is the process of estimating the ego-motion of a moving object. In other words, visual odometry is the process of determining the position of a moving object. Then, the SLAM system is considered to be the best method for spatial positioning technology in the visual field. However, the SLAM system is quite large (the front-end: visual odometry, the back-end: optimization of the ego-motion estimation error), If the system need to perform other arithmetic processing at the same time, it will face challenges in terms of real-time. There are two contributions of this thesis. First, this thesis proposes an algorithm called image series from ego-motion estimation. Through the processing of the algorithm, even if the optimization of the ego-motion estimation error is not relied on by the back-end of the SLAM system, the estimation of the ego-motion of a moving object can be appropriately performed. Second, the system proposed in this paper can achieve a well balance between real-time, processing speed, lightness, and accuracy.
42
Chien, Shao-Yu, and 簡紹羽. "Background depth estimation based on camera motion and its application to 2D-to-3D stereoscopic video conversion." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/40125316147337511936.
Full textAbstract:
碩士國立中正大學
電機工程所
97
The stereo display technology has become mature in recent years. The use of stereo display, in combination with 3D image/video contents, really makes the viewers immersed in reality. There are many methods for getting stereo video. A practical, low-cost, and fast way is to use the original 2-D video, in combination with depth conversion, to generate 3-D video. Therefore, in this thesis, we would like to develop a system to convert existing 2-D videos to their 3-D versions for stereo display. In this thesis, it is assumed that the camera has slow motion, which is used to estimate the disparity/depth information of static backgrounds. For the moving foreground objects, we combine several depth cues from the image to estimate their depth information. Finally, we fuse the background and foreground depth information to get the whole depth map. In our conversion system, we first detect region of moving objects for each image. For two images captured from two different time instants, we explore the spatial correlation to calculate the motion parallax information, and estimate a disparity plane to each segmented region. Based on the similarity of depth information in temporal domain, depth outliers can be corrected. For moving objects, we compute several depth cues, such as motion parallax, atmospheric perspective and texture gradients, by which the depth is assigned. Also we assume that the depth at the bottom of the foreground will be similar to the background depth at the same image position. Based on this, the depths of foreground and background can be fused to get the whole depth map. With the depth map, the stereo image pair can be synthesized for display. Experimental results show that the synthesized 3D video presents a good depth perception, but with slight depth discontinuity along vertical direction. Subject tests show that our synthesized 3D video and the real captured 3D video have similar depth perception.
43
Lou, Hui. "Acquiring 3D Full-body Motion from Noisy and Ambiguous Input." Thesis, 2012. http://hdl.handle.net/1969.1/ETD-TAMU-2012-05-11159.
Full textAbstract:
Natural human motion is highly demanded and widely used in a variety of applications such as video games and virtual realities. However, acquisition of full-body motion remains challenging because the system must be capable of accurately capturing a wide variety of human actions and does not require a considerable amount of time and skill to assemble. For instance, commercial optical motion capture systems such as Vicon can capture human motion with high accuracy and resolution while they often require post-processing by experts, which is time-consuming and costly. Microsoft Kinect, despite its high popularity and wide applications, does not provide accurate reconstruction of complex movements when significant occlusions occur. This dissertation explores two different approaches that accurately reconstruct full-body human motion from noisy and ambiguous input data captured by commercial motion capture devices.
The first approach automatically generates high-quality human motion from noisy data obtained from commercial optical motion capture systems, eliminating the need for post-processing. The second approach accurately captures a wide variety of human motion even under significant occlusions by using color/depth data captured by a single Kinect camera. The common theme that underlies two approaches is the use of prior knowledge embedded in pre-recorded motion capture database to reduce the reconstruction ambiguity caused by noisy and ambiguous input and constrain the solution to lie in the natural motion space. More specifically, the first approach constructs a series of spatial-temporal filter bases from pre-captured human motion data and employs them along with robust statistics techniques to filter noisy motion data corrupted by noise/outliers. The second approach formulates the problem in a Maximum a Posterior (MAP) framework and generates the most likely pose which explains the observations as well as consistent with the patterns embedded in the pre-recorded motion capture database. We demonstrate the effectiveness of our approaches through extensive numerical evaluations on synthetic data and comparisons against results created by commercial motion capture systems. The first approach can effectively denoise a wide variety of noisy motion data, including walking, running, jumping and swimming while the second approach is shown to be capable of accurately reconstructing a wider range of motions compared with Microsoft Kinect.
44
Netramai, Chayakorn [Verfasser]. "Using mobile multi-camera unit for real-time 3D motion estimation and map building of indoor environment / von Chayakorn Netramai." 2011. http://d-nb.info/1013088387/34.
Full text
45
Chiang, Yi, and 江懿. "A Prioritized Gauss-Seidel Method for Dense Correspondence Estimation and Motion Segmentation in Crowded Urban Areas with a Moving Depth Camera." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/40104611508341776709.
Full textAbstract:
碩士國立臺灣大學
資訊工程學研究所
102
Dense RGB-D video motion segmentation is an important preprocessing module in computer vision, image processing and robotics. A motion segmentation algorithm based on an optimization framework which utilizes depth information only is presented in this thesis. The proposed optimization framework segments and estimates rigid motion parameters of each locally rigid moving objects with coherent motion. The proposed method also calculates dense point correspondences while performing segmentation. An efficient numerical algorithm based on Constrained Block Nonlinear Gauss-Seidel (CNLGS) algorithm [1] and Prioritized Step Search [2] is proposed to solve the optimization problem. It classifies variables including point correspondences into groups and determines the ordering of variables to optimize. We prove the proposed numerical algorithm to converge to a theoretical bound. The proposed algorithm works well with a moving camera in highly dynamic urban scenes with non-rigid moving objects.
46
Tsao, An-Ting, and 曹安廷. "Ego-motion estimation using optical flow fields observed from multiple cameras." Thesis, 1996. http://ndltd.ncl.edu.tw/handle/53743692521793352486.
Full text
47
Chen, Yu-Liang, and 陳瑜靚. "Estimating Camera Position based on Structure from Motion and Image Retrieval Techniques." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/3s496w.
Full textAbstract:
碩士元智大學
資訊工程學系
104
Camera pose estimation is an important research topic in computer vision. It is a fundamental and crucial step in the applications of augmented reality. Knowing camera pose, we can edit the content of an image such as generating a virtual object in the image. Currently, many camera pose estimation techniques have been developed focusing on small and indoor environment. For large and outdoor environments, camera pose estimation faces some problems such as poor applicability and high computational complexity. Due to this, in this thesis we develop a two-stage camera position estimation system for large outdoor environments where the SFM (Structure from Motion) and an image retrieval technique are integrated in the system. In the stage of SFM, The SURF features in each image are extracted and the 3D structure of the scene are reconstructed. After that, a matching table which maps 2D image features to corresponding 3D points is created for subsequent camera pose estimation. In the stage of image retrieval, a method with high retrieval precision, the CNN (convolutional neural network), is employed to extract similar images from the dataset. In addition, the locality sensitive hashing algorithm is also included in the system to improve the retrieval efficiency. The features in the query image are extracted and matched with the images returned by the retrieval technique. A set of 2D and 3D matching points is established from the matching table and the camera pose is estimated. A series of experiments are conducted and results are encouraging. The camera pose of a query image in a large outdoor environment can be accurately estimated which demonstrates the feasibility of developed system.
48
Chen, Chih-Ting, and 陳芝婷. "Ego Motion Estimation in a Scene with Moving Objects Using Stereo Cameras." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/75105273156349053462.
Full text
49
Schröder-Schetelig, Johannes. "Multimodal high-resolution mapping of contracting intact Langendorff-perfused hearts." Doctoral thesis, 2020. http://hdl.handle.net/21.11130/00-1735-0000-0005-1551-8.
Full text
50
Ndayikengurukiye, Didier. "Estimation de cartes d'énergie de hautes fréquences ou d'irrégularité de périodicité de la marche humaine par caméra de profondeur pour la détection de pathologies." Thèse, 2016. http://hdl.handle.net/1866/16178.
Full textAbstract:
Ce travail présente deux nouveaux systèmes simples
d'analyse de la marche humaine grâce à une caméra de profondeur
(Microsoft Kinect) placée devant un sujet marchant
sur un tapis roulant conventionnel, capables de détecter une marche
saine et celle déficiente. Le premier système repose sur le fait
qu'une marche normale présente typiquement un signal de profondeur
lisse au niveau de chaque pixel avec moins de hautes fréquences, ce qui
permet d'estimer une carte indiquant l'emplacement et l'amplitude
de l'énergie de haute fréquence (HFSE). Le second système analyse
les parties du corps qui ont un motif de mouvement
irrégulier, en termes de périodicité, lors de la marche. Nous
supposons que la marche d'un sujet sain présente partout dans le
corps, pendant les cycles de marche, un signal de profondeur
avec un motif périodique sans bruit. Nous estimons, à partir de la
séquence vidéo de chaque sujet, une carte montrant les zones
d'irrégularités de la marche (également appelées énergie de bruit
apériodique). La carte avec HFSE ou celle visualisant l'énergie de
bruit apériodique peut être utilisée comme un bon indicateur
d'une éventuelle pathologie, dans un outil de diagnostic précoce,
rapide et fiable, ou permettre de fournir des informations sur la
présence et l'étendue de la maladie ou des problèmes (orthopédiques,
musculaires ou neurologiques) du patient. Même si les
cartes obtenues sont informatives et très discriminantes pour une
classification visuelle directe, même pour un non-spécialiste, les
systèmes proposés permettent de détecter
automatiquement les individus en bonne santé et ceux avec des
problèmes locomoteurs.This work presents two new and simple human gait analysis systems based on a depth camera (Microsoft Kinect) placed in front of a subject walking on a conventional treadmill, capable of detecting a healthy gait from an impaired one. The first system presented relies on the fact that a normal walk typically exhibits a smooth motion (depth) signal, at each pixel with less high-frequency spectral energy content than an abnormal walk. This permits to estimate a map for that subject, showing the location and the amplitude of the high-frequency spectral energy (HFSE). The second system analyses the patient's body parts that have an irregular movement pattern, in terms of periodicity, during walking. Herein we assume that the gait of a healthy subject exhibits anywhere in the human body, during the walking cycles, a depth signal with a periodic pattern without noise. From each subject’s video sequence, we estimate a saliency color map showing the areas of strong gait irregularities also called aperiodic noise energy. Either the HFSE or aperiodic noise energy shown in the map can be used as a good indicator of possible pathology in an early, fast and reliable diagnostic tool or to provide information about the presence and extent of disease or (orthopedic, muscular or neurological) patient's problems. Even if the maps obtained are informative and highly discriminant for a direct visual classification, even for a non-specialist, the proposed systems allow us to automatically detect maps representing healthy individuals and those representing individuals with locomotor problems.