To see the other types of publications on this topic, follow the link: Histogram oriented.
Dissertations / Theses on the topic 'Histogram oriented'
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 'Histogram oriented.'
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
Lienemann, Matthew A. "Automated Multi-Modal Search and Rescue using Boosted Histogram of Oriented Gradients." DigitalCommons@CalPoly, 2015. https://digitalcommons.calpoly.edu/theses/1507.
Full textAbstract:
Unmanned Aerial Vehicles (UAVs) provides a platform for many automated tasks and with an ever increasing advances in computing, these tasks can be more complex. The use of UAVs is expanded in this thesis with the goal of Search and Rescue (SAR), where a UAV can assist fast responders to search for a lost person and relay possible search areas back to SAR teams. To identify a person from an aerial perspective, low-level Histogram of Oriented Gradients (HOG) feature descriptors are used over a segmented region, provided from thermal data, to increase classification speed. This thesis also introduces a dataset to support a Bird’s-Eye-View (BEV) perspective and tests the viability of low level HOG feature descriptors on this dataset. The low-level feature descriptors are known as Boosted Histogram of Oriented Gradients (BHOG) features, which discretizes gradients over varying sized cells and blocks that are trained with a Cascaded Gentle AdaBoost Classifier using our compiled BEV dataset. The classification is supported by multiple sensing modes with color and thermal videos to increase classification speed. The thermal video is segmented to indicate any Region of Interest (ROI) that are mapped to the color video where classification occurs. The ROI decreases classification time needed for the aerial platform by eliminating a per-frame sliding window. Testing reveals that with the use of only color data iv and a classifier trained for a profile of a person, there is an average recall of 78%, while the thermal detection results with an average recall of 76%. However, there is a speed up of 2 with a video of 240x320 resolution. The BEV testing reveals that higher resolutions are favored with a recall rate of 71% using BHOG features, and 92% using Haar-Features. In the lower resolution BEV testing, the recall rates are 42% and 55%, for BHOG and Haar-Features, respectively.
2
Kuřátko, Jiří. "Počítání lidí ve videu." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2016. http://www.nusl.cz/ntk/nusl-255470.
Full textAbstract:
This master's thesis prepared the programme which is able to follow the trajectories of the movement of people and based on this to create various statistics. In practice it is an effective marketing tool which can be used for instance for customer flow analyses, optimal evaluation of opening hours, visitor traffic analyses and for a lot of other benefits. Histograms of oriented gradients, SVM classificator and optical flow monitoring were used to solve this problem. The method of multiple hypothesis tracking was selected for the association data. The system's quality was evaluated from the video footage of the street with the large concentration of pedestrians and from the school's camera system, where the movement in the corridor was monitored and the number of people counted.
3
Dvořák, Michal. "Detekce a rozpoznání dopravního značení." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2015. http://www.nusl.cz/ntk/nusl-221299.
Full textAbstract:
The goal of this thesis is the utilization of computer vision methods, in a way that will lead to detection and identification of traffic signs in an image. The final application is to analyze video feed from a video camcorder placed in a vehicle. With focus placed on effective utilization of computer resources in order to achieve real time identification of signs in a video stream.
4
Vajhala, Rohith, Rohith Maddineni, and Preethi Raj Yeruva. "Weapon Detection In Surveillance Camera Images." Thesis, Blekinge Tekniska Högskola, Institutionen för tillämpad signalbehandling, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-13565.
Full textAbstract:
Now a days, Closed Circuit Television (CCTV) cameras are installedeverywhere in public places to monitor illegal activities like armedrobberies. Mostly CCTV footages are used as post evidence after theoccurrence of crime. In many cases a person might be monitoringthe scene from CCTV but the attention can easily drift on prolongedobservation. Eciency of CCTV surveillance can be improved by in-corporation of image processing and object detection algorithms intomonitoring process.The object detection algorithms, previously implemented in CCTVvideo analysis detect pedestrians, animals and vehicles. These algo-rithms can be extended further to detect a person holding weaponslike rearms or sharp objects like knives in public or restricted places.In this work the detection of weapon from CCTV frame is acquiredby using Histogram of Oriented Gradients (HOG) as feature vector andarticial neural networks performing back-propagation algorithm forclassication.As a weapon in the hands of a human is considered to be greaterthreat as compared to a weapon alone, in this work the detection ofhuman in an image prior to a weapon detection has been found advan-tageous. Weapon detection has been performed using three methods.In the rst method, the weapon in the image is detected directly with-out human detection. Second and third methods use HOG and back-ground subtraction methods for detection of human prior to detectionof a weapon. A knife and a gun are considered as weapons of inter-est in this work. The performance of the proposed detection methodswas analysed on test image dataset containing knives, guns and im-ages without weapon. The accuracy rate 84:6% has been achievedby a single-class classier for knife detection. A gun and a knife havebeen detected by the three-class classier with an accuracy rate 83:0%.
5
Němec, Jiří. "Detekce pohybujících se objektů ve video sekvenci." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2012. http://www.nusl.cz/ntk/nusl-412865.
Full textAbstract:
This thesis deals with methods for the detection of people and tracking objects in video sequences. An application for detection and tracking of players in video recordings of sport activities, e.g. hockey or basketball matches, is proposed and implemented. The designed application uses the combination of histograms of oriented gradients and classification based on SVM (Support Vector Machines) for detecting players in the picture. Moreover, a particle filter is used for tracking detected players. The whole system was fully tested and the results are shown in the graphs and tables with verbal descriptions.
6
Černín, Jan. "Vizuální detekce osob v komerčních aplikacích." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2012. http://www.nusl.cz/ntk/nusl-219704.
Full textAbstract:
The aim of the master thesis is to derive and implement image porcessing methods for people detection and tracking in images or videos. The overall solution was chosen as a combination of modern approaches and methods which were recently presented. The proposed algorithm is able to create trajectory of the person moving in indoor building spaces even under influence of full or partial occlusion for a short period of time. The scene of interest is surveyed by a static camera having direct view on targets. Selected methods are implemented in C# programming language based on OpenCV library. Graphical user interface was created to show the final output of algorithm.
7
Chrápek, David. "Učení a detekce objektů různých tříd v obraze." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2012. http://www.nusl.cz/ntk/nusl-236481.
Full textAbstract:
This paper is focused on object learning and recognizing in the image and in the image stream. More specifically on learning and recognizing humans or theirs parts in case they are partly occluded, with possible usage on robotic platforms. This task is based on features called Histogram of Oriented Gradients (HOG) which can work quite well with different poses the human can be in. The human is split into several parts and those parts are detected individually. Then a system of voting is introduced in which detected parts votes for the final positions of found people. For training the detector a linear SVM is used. Then the Kalman filter is used for stabilization of the detector in case of detecting from image stream.
8
Memarzadeh, Milad. "Automated 2D Detection and Localization of Construction Resources in Support of Automated Performance Assessment of Construction Operations." Thesis, Virginia Tech, 2012. http://hdl.handle.net/10919/76908.
Full textAbstract:
This study presents two computer vision based algorithms for automated 2D detection of construction workers and equipment from site video streams. The state-of-the-art research proposes semi-automated detection methods for tracking of construction workers and equipment. Considering the number of active equipment and workers on jobsites and their frequency of appearance in a camera's field of view, application of semi-automated techniques can be time-consuming. To address this limitation, two new algorithms based on Histograms of Oriented Gradients and Colors (HOG+C), 1) HOG+C sliding detection window technique, and 2) HOG+C deformable part-based model are proposed and their performance are compared to the state-of-the-art algorithm in computer vision community. Furthermore, a new comprehensive benchmark dataset containing over 8,000 annotated video frames including equipment and workers from different construction projects is introduced. This dataset contains a large range of pose, scale, background, illumination, and occlusion variation. The preliminary results with average performance accuracies of 100%, 92.02%, and 89.69% for workers, excavators, and dump trucks respectively, indicate the applicability of the proposed methods for automated activity analysis of workers and equipment from single video cameras. Unlike other state-of-the-art algorithms in automated resource tracking, these methods particularly detects idle resources and does not need manual or semi-automated initialization of the resource locations in 2D video frames.<br>Master of Science
9
Novák, Pavel. "Vyhledávání objektů v obraze na základě předlohy." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2014. http://www.nusl.cz/ntk/nusl-220583.
Full textAbstract:
This Thesis is focused to Image Object Detection using Template. Main Benefit of this Work is a new Method for sympthoms extraction from Histogram of Oriented Gradients using set of Comparators. In this used Work Methods of Image comparing and Sympthoms extraction are described. Main Part is given to Histogram of Oriented Gradients Method. We came out from this Method. In this Work is used small training Data Set (100 pcs.) verified by X-Validation, followed by tests on real Sceneries. Achieved success Rate using X-Validation is 98%. for SVM Algorithm.
10
Vídeňský, František. "Počítačová podpora rozpoznávání a klasifikace rodových erbů." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2017. http://www.nusl.cz/ntk/nusl-363773.
Full textAbstract:
This master thesis describes the design and development of the system for detection and recognition of whole coat of arms as well as each heraldic parts. In the thesis are presented methods of computer vision for segmentation and detection of an object and selected methods that are the most suitable. Most of the heraldic parts are segmented using a convolution neural networks and the rest using active contours. The Histogram of the gradient method was selected for coats of arms detection in an image. For training and functionality verification is used my own data set. The resulting system can serve as an auxiliary tool used in auxiliary sciences of history.
11
Olejár, Adam. "Měření výšky postavy v obraze." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2015. http://www.nusl.cz/ntk/nusl-220426.
Full textAbstract:
The aim of this paper is a summary of the theory necessary for a modification, detection of person and the height calculation of the detected person in the image. These information were then used for implementation of the algoritm. The first half reveals teoretical problems and solutions. Shows the basic methods of image preprocessing and discusses the basic concepts of plane and projective geometry and transformations. Then describes the distortion, that brings into the picture imperfections of optical systems of cameras and the possibilities of removing them. Explains HOG algorithm and the actual method of calculating height of person detected in the image. The second half describes algoritm structure and statistical evaluation.
12
Svoboda, Tomáš. "Detekce, lokalizace a rozpoznání dopravních značek." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2011. http://www.nusl.cz/ntk/nusl-236958.
Full textAbstract:
This master's thesis deals with the localization, detection and recognition of traffic signs. The possibilities of selection of areas with possible traffic signs occurrence are analysed. The properties of different kinds of features used for traffic signs recognition are described next. It focuses on the features based on histogram of oriented gradients. Some possible classifiers are discussed, in the first place the cascade of support vector machines, which are used in resulting system. A description of the system implementation and data sets for 5 types of traffic signs is part of this thesis. Many experiments were accomplished with created system. The results of the experiments are very good. New datasets were acquired from approximately 9 hours of processed video sequences. There are about 13 500 images in these datasets.
13
Perez, Eder de Almeida. "Descritor de movimento baseado em tensor e histograma de gradientes." Universidade Federal de Juiz de Fora (UFJF), 2012. https://repositorio.ufjf.br/jspui/handle/ufjf/3549.
Full textAbstract:
Submitted by Renata Lopes (renatasil82@gmail.com) on 2017-03-06T15:14:46Z
No. of bitstreams: 1
ederdealmeidaperez.pdf: 749381 bytes, checksum: 7338f694cc850057100e730b520d74eb (MD5)<br>Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2017-03-06T20:25:35Z (GMT) No. of bitstreams: 1
ederdealmeidaperez.pdf: 749381 bytes, checksum: 7338f694cc850057100e730b520d74eb (MD5)<br>Made available in DSpace on 2017-03-06T20:25:35Z (GMT). No. of bitstreams: 1
ederdealmeidaperez.pdf: 749381 bytes, checksum: 7338f694cc850057100e730b520d74eb (MD5)
Previous issue date: 2012-08-24<br>CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior<br>O reconhecimento de padrões de movimentos tem se tornado um campo de pesquisa muito
atrativo nos últimos anos devido, entre outros fatores, à grande massificação de dados em
vídeos e a tendência na criação de interfaces homem-máquina que utilizam expressões
faciais e corporais. Esse campo pode ser considerado um dos requisitos chave para análise
e entendimento de vídeos.
Neste trabalho é proposto um descritor de movimentos baseado em tensores de 2a
ordem e histogramas de gradientes (HOG - Histogram of Oriented Gradients). O cálculo
do descritor é rápido, simples e eficaz. Além disso, nenhum aprendizado prévio é necessário
sendo que a adição de novas classes de movimentos ou novos vídeos não necessita de
mudanças ou que se recalculem os descritores já existentes. Cada quadro do vídeo é
particionado e em cada partição calcula-se o histograma de gradientes no espaço e no
tempo. A partir daí calcula-se o tensor do quadro e o descritor final é formado por uma
série de tensores de cada quadro.
O descritor criado é avaliado classificando-se as bases de vídeos KTH e Hollywood2,
utilizadas na literatura atual, com um classificador Máquina Vetor Suporte (SVM). Os
resultados obtidos na base KTH são próximos aos descritores do estado da arte que utilizam
informação local do vídeo. Os resultados obtidos na base Hollywood2 não superam
o estado da arte, mas são próximos o suficiente para concluirmos que o método proposto
é eficaz. Apesar de a literatura apresentar descritores que possuem resultados superiores
na classificação, suas abordagens são complexas e de alto custo computacional.<br>The motion pattern recognition has become a very attractive research field in recent years
due to the large amount of video data and the creation of human-machine interfaces that
use facial and body expressions. This field can be considered one of the key requirements
for analysis and understanding in video.
This thesis proposes a motion descriptor based on second order tensor and histograms
of oriented gradients. The calculation of the descriptor is fast, simple and effective.
Furthermore, no prior knowledge of data basis is required and the addition of new classes
of motion and videos do not need to recalculate the existing descriptors. The frame of a
video is divided into a grid and the histogram of oriented gradients is computed in each
cell. After that, the frame tensor is computed and the final descriptor is built by a series
of frame tensors.
The descriptor is evaluated in both KTH and Hollywood2 data basis, used in the
current literature, with a Support Vector Machine classifier (SVM). The results obtained
on the basis KTH are very close to the descriptors of the state-of-the-art that use local
information of the video. The results obtained on the basis Hollywood2 not outweigh the
state-of-the-art but are close enough to conclude that the proposed method is effective.
Although the literature presents descriptors that have superior results, their approaches
are complex and with computational cost.
14
Venkatrayappa, Darshan. "Image matching using rotating filters." Thesis, Montpellier, 2015. http://www.theses.fr/2015MONTS200/document.
Full textAbstract:
De nos jours les algorithmes de vision par ordinateur abondent dans les applications de vidéo-surveillance, de reconstruction 3D, de véhicules autonomes, d'imagerie médicale, etc… La détection et la mise en correspondance d'objets dans les images constitue une étape clé dans ces algorithmes.Les méthodes les plus communes pour la mise en correspondance d'objets ou d'images sont basées sur des descripteurs locaux, avec tout d'abord la détection de points d'intérêt, puis l'extraction de caractéristiques de voisinages des points d'intérêt, et enfin la construction des descripteurs d'image.Dans cette thèse, nous présentons des contributions au domaine de la mise en correspondance d'images par l'utilisation de demi filtres tournants. Nous suivons ici trois approches : la première présente un nouveau descripteur à faible débit et une stratégie de mise en correspondance intégrés à une plateforme vidéo. Deuxièmement, nous construisons un nouveau descripteur local en intégrant la réponse de demi filtres tournant dans un histogramme de gradient orienté (HOG) ; enfin nous proposons une nouvelle approche pour la construction d'un descripteur utilisant des statistiques du second ordre. Toutes ces trois approches apportent des résultats intéressants et prometteurs.Mots-clés : Demi filtres tournants, descripteur local d'image, mise en correspondance, histogramme de gradient orienté (HOG), Différence de gaussiennes<br>Nowadays computer vision algorithms can be found abundantly in applications relatedto video surveillance, 3D reconstruction, autonomous vehicles, medical imaging etc. Image/object matching and detection forms an integral step in many of these algorithms.The most common methods for Image/object matching and detection are based on localimage descriptors, where interest points in the image are initially detected, followed byextracting the image features from the neighbourhood of the interest point and finally,constructing the image descriptor. In this thesis, contributions to the field of the imagefeature matching using rotating half filters are presented. Here we follow three approaches:first, by presenting a new low bit-rate descriptor and a cascade matching strategy whichare integrated on a video platform. Secondly, we construct a new local image patch descriptorby embedding the response of rotating half filters in the Histogram of Orientedgradient (HoG) framework and finally by proposing a new approach for descriptor constructionby using second order image statistics. All the three approaches provides aninteresting and promising results by outperforming the state of art descriptors.Key-words: Rotating half filters, local image descriptor, image matching, Histogram of Orientated Gradients (HoG), Difference of Gaussian (DoG)
15
Klos, Dominik. "Počítání tlakových lahví v obraze." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2014. http://www.nusl.cz/ntk/nusl-236055.
Full textAbstract:
This thesis deals with an automatic counting of cylinders placed on the back of a truck using images taken by a camera mounted above the car. To achieve this goal, an SVM classifier based on HOG image descriptors has been trained to detect the cylinders. Further, a tracking method based on optical flow estimation has been designed to track the cylinders through image sequences. The result of the thesis is an application that counts bottles with precision 93,08 % placed on the truck and visualizes results of the detection.
16
Дрозд, В. П. "Застосування гістограми орієнтованих градієнтів (HOG) для виявлення пішохода на зображенні". Thesis, Сумський державний університет, 2014. http://essuir.sumdu.edu.ua/handle/123456789/39124.
Full textAbstract:
Проблема виявлення пішохода полягає в тому, що люди дуже різноманітні за статурою та можуть приймати різні пози, у зображення можуть бути різні спотворення. Існує ряд методів для виявлення
пішохода: методи основані на Haar wavelet признаках, нейронні мережі, гістограми направлених градієнтів та інші. В даній роботі пропонується розгляд варіанту застосування HOG.
17
Deaney, Mogammat Waleed. "A Comparison of Machine Learning Techniques for Facial Expression Recognition." University of the Western Cape, 2018. http://hdl.handle.net/11394/6412.
Full textAbstract:
Magister Scientiae - MSc (Computer Science)<br>A machine translation system that can convert South African Sign Language (SASL)
video to audio or text and vice versa would be bene cial to people who use SASL to
communicate. Five fundamental parameters are associated with sign language gestures,
these are: hand location; hand orientation; hand shape; hand movement and facial
expressions.
The aim of this research is to recognise facial expressions and to compare both feature
descriptors and machine learning techniques. This research used the Design Science
Research (DSR) methodology. A DSR artefact was built which consisted of two phases.
The rst phase compared local binary patterns (LBP), compound local binary patterns
(CLBP) and histogram of oriented gradients (HOG) using support vector machines
(SVM). The second phase compared the SVM to arti cial neural networks (ANN) and
random forests (RF) using the most promising feature descriptor|HOG|from the rst
phase. The performance was evaluated in terms of accuracy, robustness to classes,
robustness to subjects and ability to generalise on both the Binghamton University 3D
facial expression (BU-3DFE) and Cohn Kanade (CK) datasets. The evaluation rst
phase showed HOG to be the best feature descriptor followed by CLBP and LBP. The
second showed ANN to be the best choice of machine learning technique closely followed
by the SVM and RF.
18
Vojvoda, Jakub. "Sledování více osob ve videu z jedné kamery." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2016. http://www.nusl.cz/ntk/nusl-255308.
Full textAbstract:
Multiple person detection and tracking is challenging problem with high application potential. The difficulty of the problem is caused mainly by complexity of scene and large variations in articulation and appearance of person. The aim of this work is to design and implement system capable of detecting and tracking people in video from static mono-camera. For this purpose, an online method for tracking has been proposed based on tracking-by-detection approach. The method combines detection, tracking and fusion of responses to achieve accurate results. The implementation was evaluated on available dataset and the results show that it is suitable to use for this task. A method for motion segmentation was proposed and implemented to improve the tracking results. Furthermore, implementation of detector based on histogram of oriented gradients was accelerated by taking advantage of graphics processing unit (GPU).
19
Norris, Michael K. "INCORPORATING HISTOGRAMS OF ORIENTED GRADIENTS INTO MONTE CARLO LOCALIZATION." DigitalCommons@CalPoly, 2016. https://digitalcommons.calpoly.edu/theses/1629.
Full textAbstract:
This work presents improvements to Monte Carlo Localization (MCL) for a mobile robot using computer vision. Solutions to the localization problem aim to provide fine resolution on location approximation, and also be resistant to changes in the environment. One such environment change is the kidnapped/teleported robot problem, where a robot is suddenly transported to a new location and must re-localize. The standard method of "Augmented MCL" uses particle filtering combined with addition of random particles under certain conditions to solve the kidnapped robot problem. This solution is robust, but not always fast. This work combines Histogram of Oriented Gradients (HOG) computer vision with particle filtering to speed up the localization process.
The major slowdown in Augmented MCL is the conditional addition of random particles, which depends on the ratio of a short term and long term average of particle weights. This ratio does not change quickly when a robot is kidnapped, leading the robot to believe it is in the wrong location for a period of time. This work replaces this average-based conditional with a comparison of the HOG image directly in front of the robot with a cached version. This resulted in a speedup ranging from from 25.3% to 80.7% (depending on parameters used) in localization time over the baseline Augmented MCL.
20
Ercis, Firat. "Comparison Of Histograms Of Oriented Optical Flowbased Action Recogniton Methods." Master's thesis, METU, 2012. http://etd.lib.metu.edu.tr/upload/12615060/index.pdf.
Full textAbstract:
In the task of human action recognition in uncontrolled video, motion features are used widely
in order to achieve subject and appearence invariance. We implemented 3 Histograms of
Oriented Optical Flow based method which have a common motion feature extraction phase.
We compute an optical flow field over each frame of the video. Then those flow vectors
are histogrammed due to angle values to represent each frame with a histogram. In order to
capture local motions, The bounding box of the subject is divided into grids and the angle
histograms of all grids are concetanated to obtain the final motion feature vector. Motion
Features are supplied to 3 dierent classification system alternatives containing clustering
combined with HMM, clustering with K-nearest neighbours and average histograms methods.
Three methods are implemented and results are evaluated over Weizmann and KTH datasets.
21
Leoputra, Wilson Suryajaya. "Video foreground extraction for mobile camera platforms." Thesis, Curtin University, 2009. http://hdl.handle.net/20.500.11937/1384.
Full textAbstract:
Foreground object detection is a fundamental task in computer vision with many applications in areas such as object tracking, event identification, and behavior analysis. Most conventional foreground object detection methods work only in a stable illumination environments using fixed cameras. In real-world applications, however, it is often the case that the algorithm needs to operate under the following challenging conditions: drastic lighting changes, object shape complexity, moving cameras, low frame capture rates, and low resolution images. This thesis presents four novel approaches for foreground object detection on real-world datasets using cameras deployed on moving vehicles.The first problem addresses passenger detection and tracking tasks for public transport buses investigating the problem of changing illumination conditions and low frame capture rates. Our approach integrates a stable SIFT (Scale Invariant Feature Transform) background seat modelling method with a human shape model into a weighted Bayesian framework to detect passengers. To deal with the problem of tracking multiple targets, we employ the Reversible Jump Monte Carlo Markov Chain tracking algorithm. Using the SVM classifier, the appearance transformation models capture changes in the appearance of the foreground objects across two consecutives frames under low frame rate conditions. In the second problem, we present a system for pedestrian detection involving scenes captured by a mobile bus surveillance system. It integrates scene localization, foreground-background separation, and pedestrian detection modules into a unified detection framework. The scene localization module performs a two stage clustering of the video data.In the first stage, SIFT Homography is applied to cluster frames in terms of their structural similarity, and the second stage further clusters these aligned frames according to consistency in illumination. This produces clusters of images that are differential in viewpoint and lighting. A kernel density estimation (KDE) technique for colour and gradient is then used to construct background models for each image cluster, which is further used to detect candidate foreground pixels. Finally, using a hierarchical template matching approach, pedestrians can be detected.In addition to the second problem, we present three direct pedestrian detection methods that extend the HOG (Histogram of Oriented Gradient) techniques (Dalal and Triggs, 2005) and provide a comparative evaluation of these approaches. The three approaches include: a) a new histogram feature, that is formed by the weighted sum of both the gradient magnitude and the filter responses from a set of elongated Gaussian filters (Leung and Malik, 2001) corresponding to the quantised orientation, which we refer to as the Histogram of Oriented Gradient Banks (HOGB) approach; b) the codebook based HOG feature with branch-and-bound (efficient subwindow search) algorithm (Lampert et al., 2008) and; c) the codebook based HOGB approach.In the third problem, a unified framework that combines 3D and 2D background modelling is proposed to detect scene changes using a camera mounted on a moving vehicle. The 3D scene is first reconstructed from a set of videos taken at different times. The 3D background modelling identifies inconsistent scene structures as foreground objects. For the 2D approach, foreground objects are detected using the spatio-temporal MRF algorithm. Finally, the 3D and 2D results are combined using morphological operations.The significance of these research is that it provides basic frameworks for automatic large-scale mobile surveillance applications and facilitates many higher-level applications such as object tracking and behaviour analysis.
22
Khan, Rizwan Ahmed. "Détection des émotions à partir de vidéos dans un environnement non contrôlé." Thesis, Lyon 1, 2013. http://www.theses.fr/2013LYO10227/document.
Full textAbstract:
Dans notre communication quotidienne avec les autres, nous avons autant de considération pour l’interlocuteur lui-même que pour l’information transmise. En permanence coexistent en effet deux modes de transmission : le verbal et le non-verbal. Sur ce dernier thème intervient principalement l’expression faciale avec laquelle l’interlocuteur peut révéler d’autres émotions et intentions. Habituellement, un processus de reconnaissance d’émotions faciales repose sur 3 étapes : le suivi du visage, l’extraction de caractéristiques puis la classification de l’expression faciale. Pour obtenir un processus robuste apte à fournir des résultats fiables et exploitables, il est primordial d’extraire des caractéristiques avec de forts pouvoirs discriminants (selon les zones du visage concernées). Les avancées récentes de l’état de l’art ont conduit aujourd’hui à diverses approches souvent bridées par des temps de traitement trop couteux compte-tenu de l’extraction de descripteurs sur le visage complet ou sur des heuristiques mathématiques et/ou géométriques.En fait, aucune réponse bio-inspirée n’exploite la perception humaine dans cette tâche qu’elle opère pourtant régulièrement. Au cours de ces travaux de thèse, la base de notre approche fut ainsi de singer le modèle visuel pour focaliser le calcul de nos descripteurs sur les seules régions du visage essentielles pour la reconnaissance d’émotions. Cette approche nous a permis de concevoir un processus plus naturel basé sur ces seules régions émergentes au regard de la perception humaine. Ce manuscrit présente les différentes méthodologies bio-inspirées mises en place pour aboutir à des résultats qui améliorent généralement l’état de l’art sur les bases de référence. Ensuite, compte-tenu du fait qu’elles se focalisent sur les seules parties émergentes du visage, elles améliorent les temps de calcul et la complexité des algorithmes mis en jeu conduisant à une utilisation possible pour des applications temps réel<br>Communication in any form i.e. verbal or non-verbal is vital to complete various daily routine tasks and plays a significant role inlife. Facial expression is the most effective form of non-verbal communication and it provides a clue about emotional state, mindset and intention. Generally automatic facial expression recognition framework consists of three step: face tracking, feature extraction and expression classification. In order to built robust facial expression recognition framework that is capable of producing reliable results, it is necessary to extract features (from the appropriate facial regions) that have strong discriminative abilities. Recently different methods for automatic facial expression recognition have been proposed, but invariably they all are computationally expensive and spend computational time on whole face image or divides the facial image based on some mathematical or geometrical heuristic for features extraction. None of them take inspiration from the human visual system in completing the same task. In this research thesis we took inspiration from the human visual system in order to find from where (facial region) to extract features. We argue that the task of expression analysis and recognition could be done in more conducive manner, if only some regions are selected for further processing (i.e.salient regions) as it happens in human visual system. In this research thesis we have proposed different frameworks for automatic recognition of expressions, all getting inspiration from the human vision. Every subsequently proposed addresses the shortcomings of the previously proposed framework. Our proposed frameworks in general, achieve results that exceeds state-of-the-artmethods for expression recognition. Secondly, they are computationally efficient and simple as they process only perceptually salient region(s) of face for feature extraction. By processing only perceptually salient region(s) of the face, reduction in feature vector dimensionality and reduction in computational time for feature extraction is achieved. Thus making them suitable for real-time applications
23
Dočekal, Martin. "Porovnání klasifikačních metod." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2019. http://www.nusl.cz/ntk/nusl-403211.
Full textAbstract:
This thesis deals with a comparison of classification methods. At first, these classification methods based on machine learning are described, then a classifier comparison system is designed and implemented. This thesis also describes some classification tasks and datasets on which the designed system will be tested. The evaluation of classification tasks is done according to standard metrics. In this thesis is presented design and implementation of a classifier that is based on the principle of evolutionary algorithms.
24
Chavali, Gautam Krishna, Sai Kumar N. V. Bhavaraju, Tushal Adusumilli, and VenuGopal Puripanda. "Micro-Expression Extraction For Lie Detection Using Eulerian Video (Motion and Color) Magnication." Thesis, Blekinge Tekniska Högskola, Institutionen för tillämpad signalbehandling, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-3467.
Full textAbstract:
Lie-detection has been an evergreen and evolving subject. Polygraph techniques have been the most popular and successful technique till date. The main drawback of the polygraph is that good results cannot be attained without maintaining a physical contact, of the subject under test. In general, this physical contact would induce extra consciousness in the subject. Also, any sort of arousal in the subject triggers false positives while performing the traditional polygraph based tests. With all these drawbacks in the polygraph, also, due to rapid developments in the fields of computer vision and artificial intelligence, with newer and faster algorithms, have compelled mankind to search and adapt to contemporary methods in lie-detection. Observing the facial expressions of emotions in a person without any physical contact and implementing these techniques using artificial intelligence is one such method. The concept of magnifying a micro expression and trying to decipher them is rather premature at this stage but would evolve in future. Magnification using EVM technique has been proposed recently and it is rather new to extract these micro expressions from magnified EVM based on HOG features. Till date, HOG features have been used in conjunction with SVM, and generally for person/pedestrian detection. A newer, simpler and contemporary method of applying EVM with HOG features and Back-propagation Neural Network jointly has been introduced and proposed to extract and decipher the micro-expressions on the face. Micro-expressions go unnoticed due to its involuntary nature, but EVM is used to magnify them and makes them noticeable. Emotions behind the micro-expressions are extracted and recognized using the HOG features \& Back-Propagation Neural Network. One of the important aspects that has to be dealt with human beings is a biased mind. Since, an investigator is also a human and, he too, has to deal with his own assumptions and emotions, a Neural Network is used to give the investigator an unbiased start in identifying the true emotions behind every micro-expression. On the whole, this proposed system is not a lie-detector, but helps in detecting the emotions of the subject under test. By further investigation, a lie can be detected.<br>This thesis uses a magnification technique to magnify the subtle, faint and spontaneous facial muscle movements or more precisely, micro-expressions. This magnification would help a system in classifying them and estimating the emotion behind them. This technique additionally magnifies the color changes, which could be used to extract the pulse without a physical contact with the subject. The results are presented in a GUI.<br>Gautam: +46(0)739528573, +91-9701534064 Tushal: +46(0)723219833, +91-9000242241 Venu: +46(0)734780266, +91-9298653191 Sai: +91-9989410111
25
Wang, Benjamin. "Lip Detection and Adaptive Tracking." DigitalCommons@CalPoly, 2017. https://digitalcommons.calpoly.edu/theses/1695.
Full textAbstract:
Performance of automatic speech recognition (ASR) systems utilizing only acoustic information degrades significantly in noisy environments such as a car cabins. Incorporating audio and visual information together can improve performance in these situations. This work proposes a lip detection and tracking algorithm to serve as a visual front end to an audio-visual automatic speech recognition (AVASR) system.
Several color spaces are examined that are effective for segmenting lips from skin pixels. These color components and several features are used to characterize lips and to train cascaded lip detectors. Pre- and post-processing techniques are employed to maximize detector accuracy. The trained lip detector is incorporated into an adaptive mean-shift tracking algorithm for tracking lips in a car cabin environment. The resulting detector achieves 96.8% accuracy, and the tracker is shown to recover and adapt in scenarios where mean-shift alone fails.
26
Albertini, Federica. "Development and evaluation of an OCR system for industrial applications." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2016.
Find full textAbstract:
Questa tesi descrive il lavoro portato a termine durante un tirocinio di sei mesi svolto in Datalogic ADC, presso la sede di Pasadena, California. Durante questa esperienza sono stata coinvolta nella concretizzazione di un vero e proprio prodotto industriale: un software di riconoscimento ottico di caratteri (OCR) basato sugli istogrammi di gradienti orientati (HOG).
L'oggetto del lavoro di tesi comprende l'implementazione di un algoritmo di OCR in grado di leggere una o più righe di testo all'interno di una stessa regione di interesse garantendo velocità e accuratezza richieste in ambito industriale.
E’ possibile suddividere la realizzazione in 3 momenti: l'analisi del prototipo precedentemente realizzato, l'implementazione del nuovo prodotto e la fase finale di test per confrontarlo con i migliori algoritmi allo stato dell'arte.
Un'attenta fase di studio ha portato alla rielaborazione e ottimizzazione del precedente modello, al fine di porre le basi per la concretizzazione del nuovo tool. In seguito, integrando funzioni apposite al soddisfacimento dei requisiti, una prima versione del
prodotto è stata realizzata con particolare attenzione a modularità e correttezza del codice.
Il progetto è stato poi ulteriormente esteso al funzionamento con rappresentazione fixed-point per renderlo integrabile su smart camera: questa modifica, resa necessaria dalla mancanza di floating-point unit sui sistemi embedded, ha richiesto l'implementazione di un' apposita libreria di gestione.
A seguire, per testare robustezza e affidabilità dell'algoritmo, sono stati effettuati test su dataset forniti da reali clienti. Una finale fase di benchmark, confrontando il lavoro svolto con un noto tool commerciale allo stato dell'arte, è stata portata a termine al fine
di prevedere un possibile impatto sul mercato.
I risultati degli esperimenti condotti hanno portato ad interessanti risultati che potranno essere utilizzati per futuri sviluppi e miglioramenti del software OCR.
27
BARBACENA, Marcell Manfrin. "Impacto da redução de taxa de transmissão de fluxos de vídeos na eficácia de algoritmo para detecção de pessoas." Universidade Federal de Campina Grande, 2014. http://dspace.sti.ufcg.edu.br:8080/jspui/handle/riufcg/413.
Full textAbstract:
Submitted by Johnny Rodrigues (johnnyrodrigues@ufcg.edu.br) on 2018-04-18T15:01:39Z
No. of bitstreams: 1
MARCELL MANFRIN BARBACENA - DISSERTAÇÃO PPGCC 2014..pdf: 1468565 bytes, checksum: b94d20ffdace21ece654986ffd8fbb63 (MD5)<br>Made available in DSpace on 2018-04-18T15:01:39Z (GMT). No. of bitstreams: 1
MARCELL MANFRIN BARBACENA - DISSERTAÇÃO PPGCC 2014..pdf: 1468565 bytes, checksum: b94d20ffdace21ece654986ffd8fbb63 (MD5)
Previous issue date: 2014<br>Impulsionadas pela crescente demanda por sistemas de segurança para proteção do indivíduo e da propriedade nos dias atuais, várias pesquisas têm sido desenvolvidas com foco na implantação de sistemas de vigilância por vídeo com ampla cobertura. Um dos problemas de pesquisa em aberto nas áreas de visão computacional e redes de computadores envolvem a escalabilidade desses sistemas, principalmente devido ao aumento do número de câmeras transmitindo vídeos em tempo real para monitoramento e processamento. Neste contexto, o objetivo geral deste trabalho é avaliar o impacto que a redução da taxa de transmissão dos fluxos de vídeos impõe na eficácia dos algoritmos de detecção de pessoas utilizados em sistemas inteligentes de videovigilância. Foram realizados experimentos utilizando vídeos em alta resolução no contexto de vigilância com tomadas externas e com um algoritmo de detecção de pessoas baseado em histogramas de gradientes orientados, nos quais se coletou, como medida de eficácia do algoritmo, a métrica de área sob a curva de precisão e revocação para, em sequência, serem aplicados os testes estatísticos de Friedman e de comparações múltiplas com um controle na aferição das hipóteses levantadas. Os resultados obtidos indicaram que é possível uma redução da taxa de transmissão em mais de 70% sem que haja redução da eficácia do algoritmo de detecção de pessoas.<br>Motivated by the growing demand for security systems to protect persons and properties in
the nowadays, several researches have been developed focusing on the deployment of widearea
video coverage surveillance systems. One open research problem in the areas of
computer vision and computer networks involves the scalability of these systems, mainly due
to the increasing number of cameras transmitting real-time video for monitoring and
processing. In this context, the aim of this study was to evaluate the impact that transmission
data-rate reduction of video streams imposes on the effectiveness of people detection
algorithms used in intelligent video surveillance systems. With a proposed experimental
design, experiments were performed using high-resolution wide-area external coverage video
surveillance and using an algorithm for people detection based on histograms of oriented
gradients. As a measure of effectiveness of the people detection algorithm, the metric of area
under the precision-recall curve was collected and statistical tests of Friedman and multiple
comparisons with a control were applied to evaluate the hypotheses. The results indicated that
it is possible to reduce transmission rate by more than 70% without decrease in the
effectiveness of the people detection algorithm.
28
Hussain, Sibt Ul. "Apprentissage machine pour la détection des objets." Phd thesis, Université de Grenoble, 2011. http://tel.archives-ouvertes.fr/tel-00722632.
Full textAbstract:
Le but de cette thèse est de développer des méthodes pratiques plus performantes pour la détection d'instances de classes d'objets de la vie quotidienne dans les images. Nous présentons une famille de détecteurs qui incorporent trois types d'indices visuelles performantes - histogrammes de gradients orientés (Histograms of Oriented Gradients, HOG), motifs locaux binaires (Local Binary Patterns, LBP) et motifs locaux ternaires (Local Ternary Patterns, LTP) - dans des méthodes de discrimination efficaces de type machine à vecteur de support latent (Latent SVM), sous deux régimes de réduction de dimension - moindres carrées partielles (Partial Least Squares, PLS) et sélection de variables par élagage de poids SVM (SVM Weight Truncation). Sur plusieurs jeux de données importantes, notamment ceux du PASCAL VOC2006 et VOC2007, INRIA Person et ETH Zurich, nous démontrons que nos méthodes améliorent l'état de l'art du domaine. Nos contributions principales sont : Nous étudions l'indice visuelle LTP pour la détection d'objets. Nous démontrons que sa performance est globalement mieux que celle des indices bien établies HOG et LBP parce qu'elle permet d'encoder à la fois la texture locale de l'objet et sa forme globale, tout en étant résistante aux variations d'éclairage. Grâce à ces atouts, LTP fonctionne aussi bien pour les classes qui sont caractérisées principalement par leurs structures que pour celles qui sont caractérisées par leurs textures. En plus, nous démontrons que les indices HOG, LBP et LTP sont bien complémentaires, de sorte qu'un jeux d'indices étendu qui intègre tous les trois améliore encore la performance. Les jeux d'indices visuelles performantes étant de dimension assez élevée, nous proposons deux méthodes de réduction de dimension afin d'améliorer leur vitesse et réduire leur utilisation de mémoire. La première, basée sur la projection moindres carrés partielles, diminue significativement le temps de formation des détecteurs linéaires, sans réduction de précision ni perte de vitesse d'exécution. La seconde, fondée sur la sélection de variables par l'élagage des poids du SVM, nous permet de réduire le nombre d'indices actives par un ordre de grandeur avec une réduction minime, voire même une petite augmentation, de la précision du détecteur. Malgré sa simplicité, cette méthode de sélection de variables surpasse toutes les autres approches que nous avons mis à l'essai.
29
Bui, Manh-Tuan. "Vision-based multi-sensor people detection system for heavy machines." Thesis, Compiègne, 2014. http://www.theses.fr/2014COMP2156/document.
Full textAbstract:
Ce travail de thèse a été réalisé dans le cadre de la coopération entre l’Université de Technologie de Compiègne (UTC) et le Centre Technique des Industries Mécaniques (CETIM). Nous présentons un système de détection de personnes pour l’aide à la conduite dans les engins de chantier. Une partie du travail a été dédiée à l’analyse du contexte de l’application, ce qui a permis de proposer un système de perception composé d’une caméra monoculaire fisheye et d’un Lidar. L’utilisation des caméras fisheye donne l’avantage d’un champ de vision très large avec en contrepartie, la nécessité de gérer les fortes distorsions dans l’étape de détection. A notre connaissance, il n’y a pas eu de recherches dédiées au problème de la détection de personnes dans les images fisheye. Pour cette raison, nous nous sommes concentrés sur l’étude et la quantification de l’impact des distorsions radiales sur l’apparence des personnes dans les images et nous avons proposé des approches adaptatives pour gérer ces spécificités. Nos propositions se sont inspirées de deux approches de l’état de l’art pour la détection des personnes : les histogrammes de gradient orientés (HOG) et le modèle des parties déformables (DPM). Tout d’abord, en enrichissant la base d’apprentissage avec des imagettes fisheye artificielles, nous avons pu montrer que les classificateurs peuvent prendre en compte les distorsions dans la phase d’apprentissage. Cependant, adapter les échantillons d’entrée, n’est pas la solution optimale pour traiter le problème de déformation de l’apparence des personnes dans les images. Nous avons alors décidé d’adapter l’approche de DPM pour prendre explicitement en compte le modèle de distorsions. Il est apparu que les modèles déformables peuvent être modifiés pour s’adapter aux fortes distorsions des images fisheye, mais ceci avec un coût de calculatoire supérieur. Dans cette thèse, nous présentons également une approche de fusion Lidar/camera fisheye. Une architecture de fusion séquentielle est utilisée et permet de réduire les fausses détections et le coût calculatoire de manière importante. Un jeu de données en environnement de chantier a été construit et différentes expériences ont été réalisées pour évaluer les performances du système. Les résultats sont prometteurs, à la fois en terme de vitesse de traitement et de performance de détection<br>This thesis has been carried out in the framework of the cooperation between the Compiègne University of Technology (UTC) and the Technical Centre for Mechanical Industries (CETIM). In this work, we present a vision-based multi-sensors people detection system for safety on heavy machines. A perception system composed of a monocular fisheye camera and a Lidar is proposed. The use of fisheye cameras provides an advantage of a wide field-of-view but yields the problem of handling the strong distortions in the detection stage.To the best of our knowledge, no research works have been dedicated to people detection in fisheye images. For that reason, we focus on investigating and quantifying the strong radial distortions impacts on people appearance and proposing adaptive approaches to handle that specificity. Our propositions are inspired by the two state-of-the-art people detection approaches : the Histogram of Oriented Gradient (HOG) and the Deformable Parts Model (DPM). First, by enriching the training data set, we prove that the classifier can take into account the distortions. However, fitting the training samples to the model, is not the best solution to handle the deformation of people appearance. We then decided to adapt the DPM approach to handle properly the problem. It turned out that the deformable models can be modified to be even better adapted to the strong distortions of the fisheye images. Still, such approach has adrawback of the high computation cost and complexity. In this thesis, we also present a framework that allows the fusion of the Lidar modality to enhance the vision-based people detection algorithm. A sequential Lidar-based fusion architecture is used, which addresses directly the problem of reducing the false detections and computation cost in vision-based-only system. A heavy machine dataset have been also built and different experiments have been carried out to evaluate the performances of the system. The results are promising, both in term of processing speed and performances
30
Yu, Chieh-chun, and 余杰群. "Speed-Up Parametric-Oriented and Contast Limited Histogram Equalization." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/6964bw.
Full textAbstract:
碩士<br>國立臺灣科技大學<br>電機工程系<br>102<br>In this thesis, Two regional contrast enhancement schemes are proposed. The first one, termed adaptive parametric-oriented histogram equalization (APOHE), is proposed to effectively generate artifact-free regional contrast enhanced images. First, the grayscale histogram of a specific region is modeled with multiple Gaussian distributions adjusted by two user-defined parameters (α,β) for yielding good contrast. In which, to improve processing efficiency, the required mean and variance of these Gaussian distributions can be rapidly derived through the concept of integral image. In addition, the adaptively corrected POHE (AcPOHE) is also proposed to further improve the contrast with a limited trade-off on computations. Experimental results demonstrate good practical values of the proposed method, and thus it can be applied for various applications such as pattern recognition, biometrics analysis system and surveillance system. Comparing with former speed-oriented methods, good contrast and artifact-free results can be achieved simultaneously.
Although regional contrast enhancement methods can obtain richer details as expected, the noises accompanied with the images are enhanced as well, in particular those homogeneous regions. To solve this issue, the contrast limited adaptive histogram equalization (CLAHE) is proposed. The method utilizes the AHE structure with restricted slope of the transformation function for the reduction of noises. Yet, massive computational complexity is its major deficiency. To cope with this, a method termed integral CLAHE (ICLAHE) is proposed to specifically address this issue. In this method, the concept of integral image and the property during pdf clipping are both exploited for less computations from the original O(M^2×P^2) to O((L+1)×P^2) for images of size P×Pand contextual region size M×M. Compared with state-of-the-arts regional contrast enhancement methods, the proposed method is not merely the simplest method of providing less halo effect and noises, but offering richer distinguishable textual details. As a result, a great potential of the proposed method on medical imaging is demonstrated.
31
Bing-Chang, Kuo, and 郭秉璋. "Histogram of Oriented Gradients based Arm Gesture Recognition Research." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/22769053839918102755.
Full textAbstract:
碩士<br>國立臺灣師範大學<br>資訊工程研究所<br>100<br>In recently classroom environment, there are more and more teachers using electronic devices to help them easy to understand what students think and how students act. In all gestures, raising hand is the most popular way that students interacting with teachers. In this research, we provided a raising hand recognition system to help teacher to handle all students’ behavior. We use camera in complex background and monitor multiple people. To propose a system that can satisfy all environments and will not re-train after changing environments, we separate the system into two parts: people segmentation and gesture recognition.
In people segmentation part, we use k-means clustering to extract skin color and then use motion to remove skin-liked background. In gesture recognition part, we use histogram of oriented gradient to get the gesture feature and then use SVM to classify. Finally in experimental part, we test 3 scenes to verify our method. When we use the same case to train and test, the correct rate is average 91%. Even we use different day for training/testing, the correct rate can also reach 80%.
32
Chen, Kuan-Yu, and 陳冠宇. "Hardware Implementation of Histogram of Oriented Gradients on Zynq." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/43948624554223648679.
Full textAbstract:
碩士<br>輔仁大學<br>電機工程學系碩士班<br>104<br>Histogram of Oriented Gradients is a highly important research topic in image processing. One of the extensions of Histogram of Oriented Gradients, pedestrian detection algorithm, has been widely applied in areas that are closely related with people’s life, for example, visual surveillance and driver assistance. In the past, restrained by the complexity of its computation, Histogram of Oriented Gradients was forced to be only implemented on personal computer which caused disadvantages, such as power waste and limited application. We proposed to utilize FPGA to operate Histogram of Oriented Gradients on Zynq ZC702 development board. Through High Level Synthesis, we are able to use C-code to accelerate the design of IP core. In our solution, we have found through Pipeline of FPGA, the speed of computing Histogram of Gradients has increased 510 times compare to the speed of software architecture computation on the ZC702 development board in full HD image.
33
CHEN-WEI, KUO, and 郭. 振韋. "Identification of aquarium fish using histogram of oriented gradient." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/q9fkdb.
Full textAbstract:
碩士<br>輔仁大學<br>資訊工程學系碩士班<br>106<br>There are numerous kinds of ornamental fish; I have always wondered the species of fish although I have the habit of fishkeeping for years. In general, the features, sizes, and the colors are the key factors to distinguish fish species; therefore, I have developed a user-friendly system to distinguish fish species. This research uses the image processing technique to progress the images of fish, applies the Histogram of Oriented Gradient to extract the features, and further uses the Support Vector Machine to classify the systems. Indeed, the prototype faced some challenges, for instance, the background of the photo was too complicated, and the pattern of fish was not clear enough for the system to process and distinguish. Hence, we use the online Background Burner for complicated photo background, which saves time and enhances the image recognition. On the other hand, we use the exponential transformation method to improve the image contrast, which significantly increases the patterns of the ornamental fish. As a result, the enhancements successfully raise the distinguish rate to about 90%, which is much more accurate than other ornamental fish distinguish systems.
34
Su, Cing-De, and 蘇慶德. "Vehicle Detection Algorithm Based on Modified Gradient Oriented Histogram Feature." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/4329xy.
Full textAbstract:
碩士<br>國立雲林科技大學<br>電子工程系<br>104<br>In recent years, the public safety and home security are more and more important. The surveillance system will be becoming a hot industry. Therefore, this thesis proposed a modified gradient oriented histogram feature to identify vehicle for effective traffic control.
This proposed method is divided into two parts. The first part is vehicle algorithm which use positive and negative samples to be input images in the training. The principal direction and the direction histogram are used for classification characteristics. Each pixel in the oriented image is represented by an angle bin, and 8*8 pixels for a cell histogram calculated is the presented by a 6*6 cell direction histogram. According the direction histogram, the maximal number of direction is the principal direction. The modified histogram orientation gradient (MHOG) feature is obtained by overlapping two cell in the cell direction histogram. The training parameters are obtained by inputting the MHOG features to SVM. When the principal direction of input image is same with the principal direction of training image, and the decision function of SVM is 1. Then, the window image will be a vehicle image.
Experimental results show that the vehicle detect algorithm to achieve 98% which is better than SVM by HOG Feature detection. And average executing velocity of our method increase 40% in computer.
35
WANG, CHIA-CHENG, and 王嘉誠. "Handwritten digits recognition using histogram of oriented gradient(HOG) features." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/2htjrt.
Full textAbstract:
碩士<br>輔仁大學<br>資訊工程學系碩士班<br>106<br>Convolutional neural network has a variety of applications in image recognition, and this type of neural network is effective for training features provided by the images from training data. The MNIST handwritten dataset is often used in training convolutional neural networks.
In this study, we will train a multi-layer fully connected convolutional neural network on data we collected by using histogram of oriented gradient(HOG) to extract gradient features of the MNIST handwritten dataset. With five HOG features extracted datasets, proposed method has achieved an accuracy of 99.07% on the test data, and an accuracy of 98.88% on the validation data. In order to evaluate the performance of the trained model, we randomly generate 101 images with random noise. Each image contains 8 to 10 digits with random size and angle. The generated digits have different fonts from the MNIST handwritten dataset, our recognition test was able to scan the correct number of digits, and the trained model correctly identified 86.14% of the digits.
36
Pathak, Rahul. "Study of Human Detection Algorithms using Histogram of Oriented Gradients." Thesis, 2016. http://ethesis.nitrkl.ac.in/9285/1/2016_MT_RPathak.pdf.
Full textAbstract:
This work targets on the human detection in static images from the view of computer vision. The interest of such type detectors resides in their many applications like automotive safety, video surveillance, to control the crowd or automatic indexing of image. Detecting humans is a challenging example as humans can adopt various articulated poses, in various backgrounds under the condition of variation in illumination and color. We study and develop a HOG plus SVM based system to find a solution for robust detection as proposed by Dalal & Triggs. The HOG descriptor proposed by Dalal & Triggs turns out to be robust to small changes in the contour of image, location and direction and also for significant variation in illumination and color. HOGs performs equally well for other classes but here we are specifically considering upright humans.
37
Wu, Szu-Wei, and 吳思蔚. "Oriented Local Histogram Equalization Features and Its Application to Face Recognition." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/30115814217570120687.
Full textAbstract:
碩士<br>國立臺灣大學<br>資訊工程學研究所<br>98<br>In this paper, we propose a novel image preprocessing method which enhances local oriented contrast of facial images by using oriented local histogram equalization (OLHE), and apply it on face recognition. This method preserves local oriented information by performing local histogram equalization (LHE) with asymmetric kernels. In order to extract the feature on a facial image, we concatenate results which are processed by using eight different orientations of OLHE, called 8-oriented OLHE feature. We expect that the result of face recognitions will be better, because the feature contains local information and orientations, and our inference is proved by the experimental results. The key advantages of the method are its less computational complexity, invariance on illumination changes and can be integrated easily with other face recognition algorithms.
We demonstrate the integrations of OLHE with Sparse Representation-based Classification (SRC) which is a holistic face recognition algorithm, and Facial Trait Code (FTC) which is part-based face recognition algorithm. Furthermore, we propose Sparse Representation Facial Trait Code (SRFTC) which is an integration of the FTC and SRC. This novel method combines advantages of these two algorithms and decreases the influence of shorts effectively. Based on the experiments on AR database, we obtain 99.3% recognition rate on holistic face recognition algorithm and 99.8% recognition rate on part-based face recognition algorithm.
38
Yu-XiangSu and 蘇郁翔. "Moving Object Detection Based on Weighted Histogram of Oriented Uniform Gradient." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/p88vj9.
Full text
39
HUNG, CHE-PING, and 洪哲斌. "A Study of a Support Vector Machine Recognition System Based on Histogram of Oriented Gradient." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/hafcxa.
Full textAbstract:
碩士<br>國立高雄科技大學<br>電機工程系<br>107<br>Image recognition is fundamental and crucial study for automation systems. In this thesis, Histogram of Oriented Gradient (HOG) combined with support vector machine is implemented for image recognition. HOG is calculated by the image graph separated into connected small area called by cells. In the cells, the gradient of pixel number and the edge of HOG are then collected. Finally, the HOG is combined to construct the fea-ture descriptor. Support vector machine is an algorithm of machine learning, whose ob-jective is to search an optimal hyperplane for the separation of sets in high or infinite di-mensional space.
Finally, the combination of HOG and support vector machine for image recognition is demonstrated for the experiments of handwritten number identification based on data sets. In addition, extra test sets are included in the demonstration experiments.
40
Lai, Bo-Syun, and 賴柏勳. "Classified-Filter-based Post-Compensation Scheme for Color Filter Array Demosaicing and Speed-Up Parametric-Oriented Histogram Equalization." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/8ty86r.
Full textAbstract:
碩士<br>國立臺灣科技大學<br>電機工程系<br>100<br>In this thesis, two contributions are delivered, including Classified-Filter-based Post-Compensation Scheme for Color Filter Array Demosaicing, and Speed-Up Parametric-Oriented Histogram Equalization.
In the first half, a classified-filter-based post-compensation scheme for color filter array (CFA) demosaicing is proposed. This technique can be used for improving the image quality of the interpolated result obtained by any former demosaicing method. First, each pixel is classified according to its neighborhood’s magnitude and angle. Then, different Least-Mean-Square (LMS) filters are trained for dealing pixels of various characteristics. As documented in the experimental results, the proposed scheme can substantially boost the image quality; in addition, a better visual perception can be obtained. Notably, the proposed method can be considered as effective post-compensation by applying for any former schemes to yield an even better image quality.
In the second half, two local contrast enhancement methods, namely Parametric-Oriented Histogram Equalization (POHE) and the Correct POHE (CPOHE), are proposed to effectively acquire the enhanced results while maintaining high accuracy on the contrast. The grayscale distribution of a specific region in an image can be modeled with a kernel function such as the Gaussian, thus the corresponding estimated cdf can be regarded the transformation function for contrast enhancement. However, the required parameters are still required by accessing all of the pixels, and thus consuming additional computations. To cope with this, the concept of integral image is adopted to effectively derive the required parameters. For further improving the local contrast, the distortion induced from the aforementioned cdf is analyzed, and it is further corrected by the proposed CPOHE through the concepts of classification and regression. In the experimental results, some former well-known methods are adopted for comparison, and it also demonstrates that the proposed methods provide high practical value for some active territories such as medical imaging and computer vision.
41
CHEN, TING-AN, and 陳亭安. "Real-time Intelligent Multi-object Recognition System Design Based on Generic Fourier Descriptor and Histogram of Oriented Gradients." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/y35236.
Full textAbstract:
碩士<br>國立交通大學<br>電控工程研究所<br>108<br>In recent years, object image recognition has been a popular issue and lots of algorithms and applications are proposed. This thesis proposes a real-time multi-object recognition system based on generic Fourier descriptor and histogram of oriented gradients algorithms. The proposed system includes three parts, pre-processing, feature extraction and object recognition. First, during the period of pre-processing, the background of an input image is removed and only the objects to be recognized retain in the image. Second, generic Fourier descriptor is adopted to extract shape features of objects, and histogram of oriented gradients is used due to its invariance of geometric and photometric transformations for object orientations. Finally, the neural network classifier designed by the back-propagation algorithm is utilized to fulfill the proposed object recognition system. From the experimental results, the system could recognize objects in real-time with high accuracy rate, which verifies the effectiveness and efficiency of the proposed real-time detection system.
42
Wei-KangFan and 范維康. "Multiple People Smile Intensity Estimation Using Multi-Region Histogram of Oriented Gradients with Discriminative Classification of Smiling Face Clues." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/44070641536023317279.
Full textAbstract:
碩士<br>國立成功大學<br>電機工程學系碩博士班<br>100<br>With the advancement of technology, it is common for people to work with personal computers. However, people work under pressure with long hours and pile up stress in the nervous condition without awareness. There are many products and devices are developed to detect the health of body but less for the mental health. It is natural for people to convey their happiness with smiling faces. Therefore, based on the human natural, the thesis proposed a system which can remind people to sooth the nervous mental state by detecting and recording the appearance of smiling face to care the mental health of people. Smiling face detection can be categorized to the facial expression recognition (FER). There are several researches about FER in the field of image and video processing. According to the feature extraction manners, the FER system can be divided into geometric-based, appearance-based approaches and the hybrid-based approaches. All of the approaches have their own advantages and disadvantages. In order to detect the smiling face without disturbing the users, the system makes a tradeoff between the accuracy rate and computation power. The thesis proposed a new hybrid-based feature called multi-region histogram of oriented gradients (MRHOGs) which adopts the active shape model (ASM) for region extraction preprocessing, and shape characteristics for smiling face detection. The MRHOGs can represent both the orientation histogram and spatial information for the shapes of facial features which are also the major clues for humans to recognize the expressions. According to the characteristics of MRHOGs, the discriminative classification smiling face clues is designed for smiling face intensity estimation. The support vector machines (SVMs) are trained to detect the smiling face clues in the input image. By integrating the discriminative smiling face clues, the smiling face intensity can be estimated. The experiments were hold on JAFFE and FERET database and the worst case that smiles a little can also achieve the accuracy rate of 80%. There are higher accuracy rates for other clear smiling faces. Moreover, the method does not convolute the image with filter banks or need a large number of iteration to obtain the precise face model, which make the vector size smaller and computational power less to achieve a real-time system.
43
Βλαχοστάθης, Σωτήριος. "Ανίχνευση ανθρώπου και παρακολούθηση της κίνησής του". Thesis, 2014. http://hdl.handle.net/10889/8221.
Full textAbstract:
Η διάδοση της χρήσης των υπολογιστών σε όλο και περισσότερους τομείς της καθημερινής μας ζωής, καθώς και η τεχνολογική εξέλιξη στην επιστήμη των υπολογιστών είχε σαν φυσικό επακόλουθο τη δημιουργία αλγορίθμων που έχουν στόχο την ανίχνευση και την αναγνώριση ανθρώπων με ακρίβεια καθώς και την παρακολούθηση τους.
Τέτοιοι αλγόριθμοι εφαρμόζονται κυρίως σε συστήματα οπτικής επιτήρησης που είναι ζωτικής σημασίας σε διάφορους τομείς της καθημερινότητας.
Αντικείμενο της παρούσας διπλωματικής εργασίας είναι η υλοποίηση ενός συστήματος ανίχνευσης, με τη χρήση του αλγόριθμου Histogram of Oriented Gradient (HOG), ταξινόμησης με χρήση Supported Vector Machines και παρακολούθησης ανθρώπου σε ακολουθία εικόνων, με χρήση αλγορίθμων υπολογιστικής όρασης όπως είναι ο αλγόριθμος φιλτραρίσματος σωματιδίων (Particle Filtering).<br>The widespread use of computers in more and more areas of our everyday life and the technological development in computer science as a natural consequence was the creation of algorithms that aim to detect and identify people accurately and monitor them. Such algorithms, are applied mainly in visual surveillance systems and is of vital importance in various areas of everyday life. The subject of this thesis is to implement a detection system using the algorithm Histogram of Oriented Gradient (HOG) as well, sort using Supported Vector Machines and the human tracking in image sequence, using computer vision algorithms such as Particle Filtering algorithm.
44
Duarte, Rafael Alves. "Identity Recognition using Facial Appearance and Shape Information." Master's thesis, 2016. http://hdl.handle.net/10316/81567.
Full textAbstract:
Dissertação de Mestrado Integrado em Engenharia Electrotécnica e de Computadores apresentada à Faculdade de Ciências e Tecnologia<br>Esta tese centra-se no reconhecimento de identidade através de imagens RGBD, sendo que para tal vão ser utilizados dois métodos distintos em simultâneo: 'Constrained Local Models' (CLM) e Codificação Esparsa.Os CLMs são métodos populares desenhados para localizar os pontos característicos de cada face. Estes combinam um conjunto de detectores locais, um para cada ponto, com uma estratégia de optimização global, que maximiza a pontuação de todos os detectores em simultâneo.Pretende-se desenvolver uma extensão do algoritmo 'Constrained Local Models' que permite a utilização de múltiplas fontes de informação, entre as quais dados provenientes de sensores RGBD. Este tipo de informação permite combinar as tradicionais imagens RGB com imagens de profundidade, tendo como intuito mitigar algumas lacunas dos métodos tradicionais e aumentar a sua robustez, uma vez que as imagens de profundidade são insensíveis às condições de luminosidade, reflectem geometria e contornos da forma. Neste contexto, introduziu-se a possibilidade de utilizar vectores normais, como descritor de profundidade, na formulação CLM. Na pratica utilizar-se-ão detectores lineares que recorrem a Histograma Orientado a Vectores Normais (HONV).No que recai sobre reconhecimento facial, irá ser utilizada a codificação esparsa, devido à sua crescente popularidade junto da comunidade cientifica de Visão por Computadores, devido tanto às suas capacidades de representação, de classificação, de minimização de sobrecarga computacional, assim como à sua capacidade de lidar com oclusão.A codificação esparsa baseia-se na utilização de um dicionário aprendido à priori, para encontrar uma combinação linear esparsa de átomos, ou elementos, que mais fielmente recriam a imagem original. Será deste modo possível validar a existência de um individuo no dicionário (base de dados) tornando, assim, a codificação esparsa num potencial candidato para efectuar o desejado reconhecimento facial.Ambos os métodos serão desenvolvidos e testados em OpenCV/C++ juntamente com uma câmara Kinect, uma vez que esta tem a capacidade de capturar tanto imagens a cores como de profundidade.Para concretizar o objectivo criar-se-á uma base de dados de fotos, utilizando uma amostra de dezanove voluntários, em que a cada um será solicitadoque faça sete expressões faciais e cinco poses diferentes. Esta será usada com o intuito de criar os modelos faciais deformáveis, e paralelamente,originará um dicionário com o intuito de habilitar o computador a fazer uma correspondência facial.Esta dissertação tem como objectivo verificar se há melhorias no processo de alinhamento em comparação com as imagens tradicionais de RGB; verificar se é possível combinar métodos de alinhamento com este género de reconhecimento facial; e por último, testar a viabilidade de um sistema desenvolvido em tempo real que efectua ambos os processos.<br>This thesis focus on identity recognition through RGBD images and for that effect two different methods will be used simultaneously: Constrained Local Models (CLM) and Sparse Coding.The CLMs are popular method designed to locate characteristics points in faces.They combine a set of local detectors (or patch experts), one for each landmark, with a global optimization strategy that maximize the score of all the detectors simultaneous.In this thesis, it was developed an extension of the Constrained Local Models algorithm that allows the use of multiples sources of information, like for example data from RGBD sensors. This type of information allow us to combine traditional RGB images with depth images with the intention of mitigating some drawbacks of traditional methods an augment his robustness, since the depth images are insensible to lightning conditions, reflect pure geometry and contours of the shape.In this context, it was introduced the possibility to use normal vectors, as depth descriptor, in the CLM formulation.In practice are use linear detectors which resort to the Histogram of Oriented Normal Vectors (HONV). Relatively to facial recognition, it will be used sparse coding, due to is rising popularity with the scientific community of Computers Vision, justified by its capabilities of both representation and classification, minimizing the computational overhead and its ability to deal with occlusion. The sparse coding is based in, using a prior leaned dictionary, finding the sparse linear combination of atoms, or elements, that most accurately recreate the original image.This will allow to validate the existence of an individual in the dictionary (database) thus making the sparse coding a potential candidate to perform the desired facial recognition.Both methods will be developed and tested in OpenCV/C++ along side with a Kinect camera, since it has the ability to capture both color images and depth images.To achieve the objective a photo database will be created, using nineteen individuals, where each one will be asked to make seven facial expressions and five different poses.This will be used in order to create the deformable face models, and in parallel, will originate a dictionary in order to enable the computer to make a face matching.This dissertation aims to verify if there is improvements in the alignment process compared with the traditional RGB images;see if it is possible to combine alignment methods with this kind of facial recognition;and finally, testing the feasibility of a developed system in real-time to perform both processes.
45
Chen, Shih-Yin, and 陳思穎. "A Study on Pedestrian Image Estimation Comparing of Underground MRT Station by Histogram of Oriented Gradient Method with ACF and PD." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/j992v7.
Full textAbstract:
碩士<br>中國文化大學<br>建築及都市設計學系<br>106<br>ABSTRACT
Monitoring complex and diverse traffic systems is important for safety maintenance, crime prevention, and information logging. However, for the rapid development of computer vision, image monitoring can not only be used to store images or human observation, but also to detect spatial object detection, traffic flow, object tracking and risk prevention. Public space can show characteristics of long-term and high-density activity gathering, short-term crowd staying, reduce the time cost of pedestrian crossing, increase the evacuation speed of people when danger occurs, risk prevention in potential disasters, etc. Therefore, the application of pedestrian detection technology in public spaces is quite important. This study used two methods of Aggregate Channel Features(ACF) and People Detector(PD). And these are the most basic and effective methods for detecting pedestrian traffic as a comparison of pedestrian image detection and counting methods.
In the early Navneet Dalal and Bill Triggs published a description of the Histogram of Oriented Gradient (HOG) applied to pedestrian detection. Later extensions such as: aggregation channel features, face detection, infrared image detection edge detection, optical flow detection, feature detection, image segmentation detection, local binary patterns, feature extraction, etc. Partial adjustment of ACF and PD code encoding to perform a big data of pedestrian flow data detection. Then explore the effectiveness of ACF and PD detection through the underground layer of the Taipei MRT.
Discuss the effectiveness of the identification techniques ACF and PD. Collect the survey data of the Taipei station's pedestrian flow, strengthen the speed and output of the code data to do multiple data detection. Propose the possible influence factors and establish the Matlab code for calculating the factor data. Relevant analysis and regression are assessed through relevant influencing factors and various factors. From the correlation analysis of the numerical segmentation of the error and pedestrian number. It can be known that the correlation analysis of the ACF detection is relatively stable and high. Use regression to check the brightness and correlation between the light source and the PD method. They are related to the PD method. ACF also has a correlation with brightness, but the light does not. The research method of this research has improved its effectiveness, and the prototype of the image recognition technology human flow measurement system can improve the maintenance of public space security.
Keywords: Image detection, People Detector, Histogram of oriented gradient (HOG), Aggregate Channel Features (ACF)
46
Prabhu, Gayatri D. "Automated Detection and Counting of Pedestrians on an Urban Roadside." 2011. https://scholarworks.umass.edu/theses/708.
Full textAbstract:
This thesis implements an automated system that counts pedestrians with 85% accuracy. Two approaches have been considered and evaluated in terms of count accuracy, cost and ease of deployment. The first approach employs the Autoscope Solo Terra, a traffic camera which is widely used to monitor vehicular traffic. The Solo Terra supports an image processing-based detector that counts the number of objects crossing user-defined areas in the captured image. The count is updated based on the amount of movement across the selected regions. Therefore, a second approach has been considered that uses a histogram of oriented gradients (HoG), an advanced vision based algorithm proposed by Dalal et al. which distinguishes a pedestrian from a non-pedestrian based on an omega shape formed by the head and shoulders of a human being. The implemented detection software processes video frames that are streamed from a low-cost digital camera. The frames are divided into sub-regions which are scanned for an omega shape whenever movement is detected in those regions. It has been found that the HoG-based approach degrades in performance due to occlusion under dense pedestrian traffic conditions whereas the Solo Terra approach appears to be more robust. Undercounts and overcounts were encountered using the Solo Terra approach. To combat the disadvantages of both the approaches, they were integrated to form a single system where count is incremented predominantly using the Solo Terra. The HoG-based approach corrects the obtained count under certain conditions. A preliminary prototype of the integrated system has been verified.
47
Chuang, Cheng-Hsiung, and 莊振勛. "Monocular Multi-Human Detection Using Augmented Histograms of Oriented Gradients." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/64256216422030008275.
Full textAbstract:
碩士<br>國立臺灣大學<br>資訊工程學研究所<br>96<br>In this thesis we introduce an Augmented Histograms of Oriented Gradients (AHOG) feature for human detection from a non-static camera. This research tries to increase the discriminating power of original Histograms of Oriented Gradients (HOG) feature by adding human shape properties, such as contour distances, symmetry, gradient density, and shape approximation. The relations among AHOG features are characterized by the contour distances to the centroid of human. By observing on the biological structure of a human shape, we impose the symmetry property on every HOG feature and compute the similarity between feature itself and its symmetric pair so as to weigh HOG features. After that, the capability of describing human features is greatly improved when being compared with that of traditional one, especially when the moving humans are under consideration. Besides, we also augment the gradient density into AHOG to mitigate the influences caused by repetitive backgrounds. Moreover, we reject the false detections via an elliptical verifier learned when one tries to approximate a human shape. In the experiments, our proposed human detection method demonstrates highly reliable accuracy and provides the comparable performance to the state-of-the-art human detector on different databases.
48
Sung, Chung-Ming, and 宋崇銘. "The detection of QR codes with histograms of oriented gradients." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/83620218707935560551.
Full textAbstract:
碩士<br>義守大學<br>資訊工程學系<br>103<br>With the popularity of Smartphone, the applications of QR Code become more diverse. To store information and advertising sale, we can often find QR Codes in a periodical or on the poster. General users can utilize mobile phone''s application to decode QR Code easily. Such mobile application requires to get close to and point at the QR Code to read data. This study uses HOGs (Histograms of Oriented Gradients) to perform QR code detection. It aims to improve the recognition rate of QR Code in an image. When extracting HOG feature from input image, each pixel will be divided into nine directions with intensities, We then use feature information to identify the presence of QR Code in an image. Since a QR Code consists of black and white small boxes, through the HOG feature, information can easily recognized. To achieve this function, we use AdaBoost method to efficiently classify the existence of QR codes.
49
Chuang, Cheng-Hsiung. "Monocular Multi-Human Detection Using Augmented Histograms of Oriented Gradients." 2007. http://www.cetd.com.tw/ec/thesisdetail.aspx?etdun=U0001-2207200818083700.
Full text
50
Kuo, Pei-Jung, and 郭沛融. "Implementing Histograms of Oriented Gradients for Pedestrian Detection by FPGA." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/2sutds.
Full textAbstract:
碩士<br>國立臺北科技大學<br>電子工程系<br>106<br>A high precision and fast pedestrian detection system is always playing an important role in applications of driver assistant, surveilance systems. Recently, these kind of technology become more popular and widely used in our life. However, implementing a human detection system needs a reliable feature extraction algorithm to conquer interference from different kind of environments. As a result, our paper used Histogram of Oriented Gradient (HOG) algorithm to extract feature from computer vision images. Although HOG is so good at handling those issues, it still has a deadly disadvantage, it takes too much computation time.
In order to achieve a fast and reliable pedestrian detection system, we used FPGA to implement HOG algorithm and simplified those complicated formula such as square root and arctangent operations. At last, we implement the proposed method on Altera Stratix IV platform with PCI Express interface and achieved 207 MHz operating frequency.