To see the other types of publications on this topic, follow the link: Finger detection.
Dissertations / Theses on the topic 'Finger detection'
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 'Finger detection.'
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
Ooi, Aik Teong. "Sequence-Specific DNA Detection Utilizing Custom-Designed Zinc Finger Proteins." Diss., The University of Arizona, 2007. http://hdl.handle.net/10150/194236.
Full textAbstract:
DNA diagnostics are important technologies in molecular and cellular biology. By allowing identification of specific sequences, DNA-based diagnostics potentially provide more accurate and rapid results than protein- or antigen-based diagnostics, primarily because phenotypic changes come much later than changes in genotype. Despite this advantage, there are fewer diagnostic or imaging systems that target DNA than those targeting proteins, antibodies, or antigens.Each type of DNA-based diagnostic has its own, unique set of limitations; however, most can be attributed to issues related to sequence restriction, signal detection, specificity, or some combination thereof. For example, while PCR-based methods allow amplification and assessment of specific DNA sequences, they lack the ability to report information of specific cells, or cell types, within the heterogeneous pool of cells typically found in a tumor biopsy. In addition, none of the currently available DNA detection methods has the potential to be utilized in living cells, a disadvantage which limits the potential applications.The work presented here describes the design and development of a new methodology for the detection of specific double-stranded DNA sequences. This detection method is based on the concept that two inactive fragments of a reporter protein, each coupled to engineered zinc finger DNA-binding motifs, are able to reassemble and form an active complex in the presence of a predefined DNA sequence. This system, designated sequence-enabled reassembly (SEER), can achieve single base-pair specificity, and has the potential to be utilized in living cells.In this dissertation, we discuss the efforts from constructing to refining the system, as well as the future applications of SEER in diagnostics and therapeutics. Chapter I will provide an introduction to DNA detection methods, on which the principles of the SEER system are based. Chapter II describes the design and construction of an enzymatic SEER system, SEER-LAC, using beta-lactamase as the enzyme. In Chapter III, we outline the in vitro characterization of the SEER-LAC system, followed by its optimization in Chapter IV. Chapter V illustrates the efforts to develop SEER system for mammalian cell culture applications. In the final chapter, the future developments and applications of SEER are discussed.
2
Henshaw, Katie(Katherine A. ). "Optical detection of finger pressure through utilization of nailbed color changes." Thesis, Massachusetts Institute of Technology, 2020. https://hdl.handle.net/1721.1/127927.
Full textAbstract:
Thesis: S.B., Massachusetts Institute of Technology, Department of Mechanical Engineering, May, 2020<br>Cataloged from the official PDF of thesis.<br>Includes bibliographical references (pages 14-15).<br>This thesis presents the theory and design of a sensor that detects a when a finger is pressed by visually examining a user's fingernail coloration. Unlike other finger-based controllers that primarily depend on covering the finger pad, this method of sensing allows for accurate measurements without impairing a user's tactile sense. First the color change of a fingernail is examined based on the underlying biological mechanisms of the finger. Then the hue, saturation, and value (HSV) coordinates of videos of the fingernails are analyzed in three different locations; the entire image, a segment of the rear of the fingernail, and a segment of the tip of the fingernail. The front of the fingernail, where a white band develops when pressure is applied to the finger, proved to have statistically significant increases in saturation and value for all test subjects. With these results a simple sensor was designed and tested that accurately sensed finger presses, however with a significant time lag. Finally, the mechanical design of such a sensor was proposed, leaving room for further study and development.<br>by Katie Henshaw.<br>S.B.<br>S.B. Massachusetts Institute of Technology, Department of Mechanical Engineering
3
Kim, Juhwa. "Multiplexed Detection of Double-Stranded Pathogenic DNA with Engineered Zinc Finger Proteins." TopSCHOLAR®, 2016. http://digitalcommons.wku.edu/theses/1616.
Full textAbstract:
The development of a new technology for the detection of doublestranded (ds) DNA enables multiple biomedical applications including identifying multiple pathogens simultaneously. We previously employed colorimetric SEquence-Enabled Reassembly with TEM-1 β-lacatamase (SEER-LAC) to detect specific bacterial DNA sequence. SEER-Lac consists of the two inactive β-lactamase fragments which of each attached to a zinc finger protein (ZFP) would reassemble into an active full-length enzyme upon ZFPs binding to its target DNA. Here, we engineered two pairs of ZFPs which of each recognizes shiga toxin in E. coli O157 and staphylococcal enterotoxin B in Staphylococus Aureus, respectively. Biotin was simply conjugated to the detection probe ZFP, which allows for generating chemiluminescent signal in streptavidin-HRP (Horseradish peroxidase) assay upon ZFPs binding to their target DNA. Our assay generates DNA-dependent signal and allows for a detection limit of 0.5 nM without DNA amplification or DNA labeling. Our system can be developed into a simple multiplexed detection diagnostic for multiplexed detection of dsDNA.
4
Chan, Gregory Electrical Engineering & Telecommunications Faculty of Engineering UNSW. "Early detection of blood loss using a noninvasive finger photoplethysmographic pulse oximetry waveform." Publisher:University of New South Wales. Electrical Engineering & Telecommunications, 2008. http://handle.unsw.edu.au/1959.4/42593.
Full textAbstract:
Delayed control of haemorrhage or blood loss has been recognised as a major contributor to preventable trauma deaths, but early detection of internal bleeding is difficult due to unreliability of heart rate (HR) and blood pressure (BP) as markers of volume status. This thesis explores a novel method of early blood loss detection using a noninvasive finger photoplethysmographic (PPG) pulse oximetry waveform that is normally utilised in pulse oximeters for estimating arterial oxygen saturation. Graded head-up tilt (n = 13) and blood donation (n = 43) in human volunteers were selected as experimental models of mild to moderate blood loss. From the tilt study, a novel method for automatically detecting left ventricular ejection time (LVET) from the finger PPG waveform has been developed and verified by comparison with the LVET measured from aortic flow velocity. PPG waveform derived LVET (LVETp) and pulse transit time (PTT) were strongly correlated with aortic LVET and pre-ejection period respectively (median r = 0.954 and 0.964) and with the decrease in central blood volume indicated by the sine of the tilt angle (median r = -0.985 and 0.938), outperforming R-R interval (RRI) and BP in detecting mild central hypovolaemia. In the blood donation study, progressive blood loss was characterised by falling LVETp and rising PTT (p < 0.01). A new way of identifying haemorrhagic phases by monitoring changes and trends in LVETp, PTT and RRI has been proposed based on the results from the two studies. The utility of frequency spectrum analysis of PPG waveform variability (PPGV) in characterising blood loss has also been examined. A new technique of PPGV analysis by computing the coherence-weighted cross-spectrum has been proposed. It has been shown that the spectral measures of finger PPGV exhibited significant changes (p < 0.01) with blood donation and were mildly correlated with systemic vascular resistance in intensive care unit patients (r from 0.53 to 0.59, p < 0.0001), therefore may be useful for identification of different haemorrhagic phases. In conclusion, this thesis has established finger PPG waveform as a potentially useful noninvasive tool for early detection of blood loss.
5
Dohnálek, Tomáš. "Liveness Detection on Fingers Using Vein Pattern." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2015. http://www.nusl.cz/ntk/nusl-234901.
Full textAbstract:
Tato práce se zabývá rozšířením snímače otisků prstů Touchless Biometric Systems 3D-Enroll o jednotku detekce živosti prstu na základě žil. Bylo navrhnuto a zkonstruováno hardwarové řešení s využitím infračervených diod. Navržené softwarové řešení pracuje ve dvou různých režimech: detekce živosti na základě texturních příznaků a verifikace uživatelů na základě porovnávání žilních vzorů. Datový soubor obsahující přes 1100 snímků jak živých prstů tak jejich falsifikátů vznikl jako součást této práce a výkonnost obou zmíněných režimů byla vyhodnocena na tomto datovém souboru. Na závěr byly navrhnuty materiály vhodné k výrobě falsifikátů otisků prstů umožňující oklamání detekce živosti pomocí žilních vzorů.
6
Kini, Anu. "Using Zinc Finger Proteins as a Diagnostic Tool for the Detection of a Cancer Biomarker." TopSCHOLAR®, 2016. http://digitalcommons.wku.edu/theses/1637.
Full textAbstract:
RASSF1A is a tumor suppressor gene which loses its function due to methylation of CpG islands on its promoter region. Detection of methylation leads to early diagnosis of cancer.
Zinc finger proteins are capable of detecting a specific DNA sequence and Methyl binding domain can bind to the methyl group on the CpG, using this idea mCpG SEER- Lac system makes use of a split protein, β-lactamase. Lac A attached to the ZFP and Lac B attached to the MBD protein. On binding to the DNA, the Lac A and Lac B come in close proximity with each other causing a reassembly and activation of the enzyme. In the presence of a substrate, the activated β-lactamse enzyme hydrolyzes the β-lactam bond in the substrate and shows a color change from yellow to red in the presence of a methylated cognate DNA.
The study suggests that a solution based assay was not as specific in differentiating signal intensities between methylated and non-methylated DNA. It was also not sensitive in measuring dose dependent signals. Zinc finger array could successfully show relatively low signals for non-methylated DNA. The findings of the study show that MBD2 shows higher preference for mCpG than MBD1 in the mCpG SEER-Lac system and oligonucleotides with a 2 bp spacing between methylation and ZF target site shows higher signals than the 3 bp spacing. Due to it’s specificity and sensitivity, it serves as a potential diagnostic tool to detect cancer.
7
Ha, Dat Thinh. "Developing a New Sensing Technology for Double-Stranded DNA Detection Utilizing Engineered Zinc Finger Proteins and Nanomaterials." TopSCHOLAR®, 2018. https://digitalcommons.wku.edu/theses/3079.
Full textAbstract:
A specific double-stranded DNA sensing system is of great interest for diagnostic and other biomedical applications. Zinc finger domains, which recognize double-stranded DNA, can be engineered to form custom DNA-binding proteins for recognition of specific DNA sequences. As a proof of concept, a sequence-enabled reassembly of TEM-1 β- lactamase system (SEER-LAC) was previously demonstrated to develop zinc finger protein (ZFP) arrays for the detection of a double-stranded bacterial DNA sequence. Here, we implemented the SEER-LAC system to demonstrate the direct detection of pathogenspecific DNA sequences present in E. coli O157:H7 on the lab-on-a chip. ZFPs customdesigned to detect shiga toxin in E. coli O157:H7 were immobilized on the cyclic olefin copolymer (COC) chip, which can function as a non-PCR based molecular diagnostic. Pathogen-specific double-stranded DNA was directly detected by engineered ZFPs immobilized on the COC chip, providing a detection limit of 10 fmole of target DNA in colorimetric assay. Therefore, in this study, we demonstrated a great potential of ZFP arrays on the COC chip for further development of a simple and novel lab-on-a chip technology for detection of pathogens.
Antibiotic resistance is a serious, and rapidly growing global threat. Here, we designed a novel screening method to detect antibiotic resistance genes (ARGs) in bacteria using a graphene oxide-based biosensor utilizing engineered ZFPs. Two-dimensional
graphene oxide (GO) sheet possesses unique electronic, thermal, and mechanical properties. The quenching ability of GO can create novel methods for detection of biomolecules. Our approach utilizes quenching of fluorescence signal by GO in the absence of target ARGs, but restoring the signal in the presence of target ARGs. Quantum dot (QD)- labeled ZFP can bind to GO via stacking interactions of aromatic and hydrophobic residues in conjunction with hydrogen bonding interaction between hydroxyl or carboxyl groups of GO and hydroxyl or amine groups of the protein. Due to fluorescence resonance energy transfer (FRET) between QD and GO when they are in close proximity, fluorescence signal of QD-labeled ZFP is expected to be quenched. In the presence of target DNA, the bound DNA-protein complex is released from GO, restoring the fluorescence signal.
8
Maguire, Gabriel. "Remote Smoker Monitoring System Incorporating Preemptive Smoking Detection." Case Western Reserve University School of Graduate Studies / OhioLINK, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=case1623268732185854.
Full text
9
Yanenko, M., and A. Popov. "ECoG Eigenvalues Analysis for Motor Activity Detection." Thesis, Sumy State University, 2016. http://essuir.sumdu.edu.ua/handle/123456789/47108.
Full textAbstract:
In this publication the results of Principal Component Analysis (PCA) of finger movements electrocorticography (ECoG) are presented. Eigenvalues configuration was analyzed for ECoG with and without any motor activity. PCA components of ECoG can be separated into motor activity and background parts, enabling spatial localization of motor activity areas in future.
10
Lodrová, Dana. "Bezpečnost biometrických systémů." Doctoral thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2013. http://www.nusl.cz/ntk/nusl-261226.
Full textAbstract:
Hlavním přínosem této práce jsou dva nové přístupy pro zvýšení bezpečnosti biometrických systémů založených na rozpoznávání podle otisků prstů. První přístup je z oblasti testování živosti a znemožňuje použití různých typů falešných otisků prstů a jiných metod oklamání senzoru v průběhu procesu snímání otisků. Tento patentovaný přístup je založen na změně barvy a šířky papilárních linií vlivem přitlačení prstu na skleněný podklad. Výsledná jednotka pro testování živosti může být integrována do optických senzorů. Druhý přístup je z oblasti standardizace a zvyšuje bezpečnost a interoperabilitu procesů extrakce markantů a porovnání. Pro tyto účely jsem vytvořila metodologii, která stanovuje míry sémantické shody pro extraktory markantů otisků prstů. Markanty nalezené testovanými extraktory jsou porovnávány oproti Ground-Truth markantům získaným pomocí shlukování dat poskytnutých daktyloskopickými experty. Tato navrhovaná metodologie je zahrnuta v navrhovaném dodatku k normě ISO/IEC 29109-2 (Amd. 2 WD4).
11
Yegingil, Hakki Orhan Shih Wei-Heng Shih Wan Y. "Breast cancer detection and differentiation using piezoelectric fingers /." Philadelphia, Pa. : Drexel University, 2009. http://hdl.handle.net/1860/2969.
Full text
12
Finne, Patrik. "Development and validation of methods for detection of prostate cancer." Helsinki : University of Helsinki, 2000. http://ethesis.helsinki.fi/julkaisut/laa/kliin/vk/finne/.
Full text
13
Ferreira, Eduardo Rodolfo Teixeira. "Goal detection using laser range finder for goalkeeper and striker from CAMBADA team." Master's thesis, Universidade de Aveiro, 2015. http://hdl.handle.net/10773/15939.
Full textAbstract:
Mestrado em Engenharia Eletrónica e Telecomunicações<br>For a robot be autonomous and mobile, it requires being attached with a
set of sensors that helps it to have a better perception of the surrounding
world, to manage to localize itself and the surrounding objects.
CAMBADA is the robotic soccer team of the IRIS research group, from
IEETA, University of Aveiro, that competes in the Middle-Size League of
RoboCup.
In competition, in order to win, the main objective of the game it's to score
more goals than the conceded, so not conceding goals, and score as much
as possible it's desirable, thus, this thesis focus on adapt an agent with a
better localization capacity in defensive and offensive moments.
It was introduced a laser range finder to the CAMBADA robots, making
them capable of detecting their own and the opponent goal, and to detect
the opponents in specific game situations.
With the new information and adapting the Goalie and Penalty behaviors,
the CAMBADA goalkeeper is now able to detect and track its own goal and
the CAMBADA striker has a better performance in a penalty situation.
The developed work was incorporated within the competition software of
the robots, which allows the presentation, in this thesis, of the experimental
results obtained with physical robots on the laboratory field.<br>Para que um robô seja autónomo e móvel, necessita estar equipado com
vários sensores que o ajudem a ter uma percepção do mundo que o rodeia,
de forma a obter a sua própria localização e a detecção de objectos.
CAMBADA é a equipa de futebol robótico do grupo de investigação IRIS,
da unidade de investigação IEETA, da Universidade de Aveiro que participa
na Liga de Robôs Médios da RoboCup.
Em competição, para ganhar, o principal objetivo de uma equipa durante
um jogo é não sofrer golos e marcar o maior número possível, desta forma,
esta tese foca-se em dotar um agente de uma melhor capacidade de localização em situações defensivas e ofensivas de jogo.
Foi introduzido um laser range finder aos robôs da equipa CAMBADA,
tornando-os aptos a detetar a sua própria baliza e a do adversário, e a detetar
oponentes em situações especificas do jogo.
Com a nova informação adquirida e adaptando os behaviors Goalie e
Penalty, agora o guarda-redes da equipa CAMBADA está apto a detetar
e rastrear a sua própria baliza e o avançado da equipa CAMBADA tem
uma melhor performance em situações de penalty.
O trabalho desenvolvido foi incorporado no software de competição dos
robôs, o que permite nesta tese apresentar resultados experimentais de
testes efectuados nos robôs em laboratório.
14
Purewal, Victoria Jane. "Novel detection and removal of hazardous biocide residues historically applied to herbaria." Thesis, University of Lincoln, 2012. http://eprints.lincoln.ac.uk/13573/.
Full textAbstract:
This research is concerned with the detection and removal of hazardous biocide residues from historic applications to herbarium collections. There are two main aims: • To develop a rapid, cost-effective and non-destructive screening method for identifying toxic residues on herbarium sheets; and • To establish the most suitable decontamination method for the removal of naphthalene from herbarium collections, maintaining the integrity of the specimen. The research outlines how the presence of fluorescent marks on specimen sheets throughout the herbarium, at Amgueddfa Cymru- National Museum Wales (AC-NMW), is indicative of mercury(II) chloride contamination. Compelling evidence is given to support the hypothesis that the observed fluorescence is due to the reduction of Hg(II) to Hg(I) during the oxidative degradation of cellulose, occurring as part of the natural ageing process. The rate of fluorescence development is shown to be increased by the presence of naphthalene, and is estimated to take at least 30 years to develop. From the results obtained, it is evident that a hand-held UV-A lamp can provide a rapid and effective method of identifying samples within a collection that are contaminated with mercury, thus providing a rapid and economical means to prioritise which collections require immediate re-mounting. Furthermore, this method will enforce the implementation of safe, standard procedures to protect personnel and visitors when handling the collections, plus enable the removal of a large amount of hazardous chemical from the herbarium environment. It is also demonstrated, through decontamination tests, that the air-drying of contaminated specimen sheets is a more efficient method of removing naphthalene, than either freeze-drying or oven-drying. It is also the most cost-effective, and the least damaging to the specimen. It is shown that the efficacy of the decontamination is dependent upon the paper type. Thin, unfinished, papers are more efficient at losing naphthalene than the heavier, finished and coated papers, as their porous structure allows the naphthalene to remain more mobile. These results provide important information about which specimen sheets are more likely to be successfully decontaminated by the air-drying procedure and can inform the selection and prioritisation process.
15
Wälivaara, Marcus. "General Object Detection Using Superpixel Preprocessing." Thesis, Linköpings universitet, Datorseende, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-140874.
Full textAbstract:
The objective of this master’s thesis work is to evaluate the potential benefit of a superpixel preprocessing step for general object detection in a traffic environment. The various effects of different superpixel parameters on object detection performance, as well as the benefit of including depth information when generating the superpixels are investigated. In this work, three superpixel algorithms are implemented and compared, including a proposal for an improved version of the popular Spectral Linear Iterative Clustering superpixel algorithm (SLIC). The proposed improved algorithm utilises a coarse-to-fine approach which outperforms the original SLIC for high-resolution images. An object detection algorithm is also implemented and evaluated. The algorithm makes use of depth information obtained by a stereo camera to extract superpixels corresponding to foreground objects in the image. Hierarchical clustering is then applied, with the segments formed by the clustered superpixels indicating potential objects in the input image. The object detection algorithm managed to detect on average 58% of the objects present in the chosen dataset. It performed especially well for detecting pedestrians or other objects close to the car. Altering the density distribution of the superpixels in the image yielded an increase in detection rate, and could be achieved both with or without utilising depth information. It was also shown that the use of superpixels greatly reduces the amount of computations needed for the algorithm, indicating that a real-time implementation is feasible.
16
Hu, Kun. "Fine-grained Human Action Recognition for Freezing of Gait Detection." Thesis, The University of Sydney, 2021. https://hdl.handle.net/2123/27286.
Full textAbstract:
Freezing of gait (FoG) presents as a sudden and brief episode of movement cessation despite the intention to continue walking. As a common symptom of Parkinson's Disease, early detection and quantification of FoG are of great importance in clinical practice. Therefore, this thesis focuses on vision-based and pressure-based FoG detection methods, which were seldom investigated in the past. The task can be treated as a human action recognition problem. Although various deep architectures have achieved encouraging performance for general action recognition, FoG events contain fine-grained patterns, which requires novel deep architectures to learn the domain knowledge. Hence, fine-grained deep architectures are studied, and the major contributions of this thesis are as follows:
1. A graph-based neural network is proposed for vision-based FoG detection by representing a temporal video segment as a directed graph where FoG related candidate regions are the vertices. A weakly-supervised learning strategy is studied to eliminate the resource expensive annotations.
2. A graph sequence recurrent neural network is proposed to formulate long-term graph temporal patterns, which takes graph sequences of dynamic structures as inputs and characterizes FoG patterns by graph recurrent cells.
3. An adversarial spatio-temporal network is proposed to learn FoG patterns across multiple levels using footstep pressure sequences. The adversarial training scheme aims to obtain subject-independent representations to alleviate the issue of high inter-subject variance.
4. A graph fusion neural network is introduced for multimodal learning using footstep pressure maps, video recordings and their associated optical flows. Multimodal graphs are introduced by treating the encoded features of each modality as vertex-level inputs.
Comprehensive experiments demonstrate the effectiveness of the proposed methods.
17
Fang, Yong. "Road scene perception based on fisheye camera, LIDAR and GPS data combination." Thesis, Belfort-Montbéliard, 2015. http://www.theses.fr/2015BELF0265/document.
Full textAbstract:
La perception de scènes routières est un domaine de recherche très actif. Cette thèse se focalise sur la détection et le suivi d’objets par fusion de données d’un système multi-capteurs composé d’un télémètre laser, une caméra fisheye et un système de positionnement global (GPS). Plusieurs étapes de la chaîne de perception sont ´ étudiées : le calibrage extrinsèque du couple caméra fisheye / télémètre laser, la détection de la route et enfin la détection et le suivi d’obstacles sur la route.Afin de traiter les informations géométriques du télémètre laser et de la caméra fisheye dans un repère commun, une nouvelle approche de calibrage extrinsèque entre les deux capteurs est proposée. La caméra fisheye est d’abord calibrée intrinsèquement. Pour cela, trois modèles de la littérature sont étudiés et comparés. Ensuite, pour le calibrage extrinsèque entre les capteurs,la normale au plan du télémètre laser est estimée par une approche de RANSAC couplée `a une régression linéaire `a partir de points connus dans le repère des deux capteurs. Enfin une méthode des moindres carres basée sur des contraintes géométriques entre les points connus, la normale au plan et les données du télémètre laser permet de calculer les paramètres extrinsèques. La méthode proposée est testée et évaluée en simulation et sur des données réelles.On s’intéresse ensuite `a la détection de la route à partir des données issues de la caméra fisheye et du télémètre laser. La détection de la route est initialisée `a partir du calcul de l’image invariante aux conditions d’illumination basée sur l’espace log-chromatique. Un seuillage sur l’histogramme normalisé est appliqué pour classifier les pixels de la route. Ensuite, la cohérence de la détection de la route est vérifiée en utilisant les mesures du télémètre laser. La segmentation de la route est enfin affinée en exploitant deux détections de la route successives. Pour cela, une carte de distance est calculée dans l’espace couleur HSI (Hue,Saturation, Intensity). La méthode est expérimentée sur des données réelles. Une méthode de détection d’obstacles basée sur les données de la caméra fisheye, du télémètre laser, d’un GPS et d’une cartographie routière est ensuite proposée. On s’intéresse notamment aux objets mobiles apparaissant flous dans l’image fisheye. Les régions d’intérêts de l’image sont extraites `a partir de la méthode de détection de la route proposée précédemment. Puis, la détection dans l’image du marquage de la ligne centrale de la route est mise en correspondance avec un modelé de route reconstruit `a partir des données GPS et cartographiques. Pour cela, la transformation IPM (Inverse Perspective Mapping) est appliquée à l’image. Les régions contenant potentiellement des obstacles sont alors extraites puis confirmées à l’aide du télémètre laser.L’approche est testée sur des données réelles et comparée `a deux méthodes de la littérature. Enfin, la dernière problématique étudiée est le suivi temporel des obstacles détectés `a l’aide de l’utilisation conjointe des données de la caméra fisheye et du télémètre laser. Pour cela, les resultats de détection d’obstacles précédemment obtenus sont exploit ´es ainsi qu’une approche de croissance de région. La méthode proposée est également testée sur des données réelles<br>Road scene understanding is one of key research topics of intelligent vehicles. This thesis focuses on detection and tracking of obstacles by multisensors data fusion and analysis. The considered system is composed of a lidar, a fisheye camera and aglobal positioning system (GPS). Several steps of the perception scheme are studied: extrinsic calibration between fisheye camera and lidar, road detection and obstacles detection and tracking. Firstly, a new method for extinsic calibration between fisheye camera and lidar is proposed. For intrinsic modeling of the fisheye camera, three models of the literatureare studied and compared. For extrinsic calibration between the two sensors, the normal to the lidar plane is firstly estimated based on the determination of ń known ż points. The extrinsic parameters are then computed using a least square approachbased on geometrical constraints, the lidar plane normal and the lidar measurements. The second part of this thesis is dedicated to road detection exploiting both fisheye camera and lidar data. The road is firstly coarse detected considering the illumination invariant image. Then the normalised histogram based classification is validated using the lidar data. The road segmentation is finally refined exploiting two successive roaddetection results and distance map computed in HSI color space. The third step focuses on obstacles detection, especially in case of motion blur. The proposed method combines previously detected road, map, GPS and lidar information.Regions of interest are extracted from previously road detection. Then road central lines are extracted from the image and matched with road shape model extracted from 2DŋSIG map. Lidar measurements are used to validated the results.The final step is object tracking still using fisheye camera and lidar. The proposed method is based on previously detected obstacles and a region growth approach. All the methods proposed in this thesis are tested, evaluated and compared to stateŋofŋtheŋart approaches using real data acquired with the IRTESŋSET laboratory experimental platform
18
Swaro, James E. "A Heuristic-Based Approach to Real-Time TCP State and Retransmission Analysis." Ohio University / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1448030769.
Full text
19
Zheng, Michael. "Deriving activity from RFID detection records in an assisted living context a dissertation submitted to Auckland University of Technology in partial fufilment of the requirements for the degree of Master of Computer and Information Sciences (MCIS), 2008 /." Click here to access this resource online, 2008. http://hdl.handle.net/10292/538.
Full textAbstract:
Thesis (MCIS - Computer and Information Sciences) -- AUT University, 2007.<br>Includes bibliographical references. Also held in print (xii, 126 leaves : ill. ; 30 cm.) in the Archive at the City Campus (T 621.384191 ZHE)
20
Holmberg, Per. "Sensor Fusion with Coordinated Mobile Robots." Thesis, Linköping University, Department of Electrical Engineering, 2003. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-1717.
Full textAbstract:
<p>Robust localization is a prerequisite for mobile robot autonomy. In many situations the GPS signal is not available and thus an additional localization system is required. A simple approach is to apply localization based on dead reckoning by use of wheel encoders but it results in large estimation errors. With exteroceptive sensors such as a laser range finder natural landmarks in the environment of the robot can be extracted from raw range data. Landmarks are extracted with the Hough transform and a recursive line segment algorithm. By applying data association and Kalman filtering along with process models the landmarks can be used in combination with wheel encoders for estimating the global position of the robot. If several robots can cooperate better position estimates are to be expected because robots can be seen as mobile landmarks and one robot can supervise the movement of another. The centralized Kalman filter presented in this master thesis systematically treats robots and extracted landmarks such that benefits from several robots are utilized. Experiments in different indoor environments with two different robots show that long distances can be traveled while the positional uncertainty is kept low. The benefit from cooperating robots in the sense of reduced positional uncertainty is also shown in an experiment. </p><p>Except for localization algorithms a typical autonomous robot task in the form of change detection is solved. The change detection method, which requires robust localization, is aimed to be used for surveillance. The implemented algorithm accounts for measurement- and positional uncertainty when determining whether something in the environment has changed. Consecutive true changes as well as sporadic false changes are detected in an illustrative experiment.</p>
21
Murabito, Francesca. "Deeply Incorporating Human Capabilities into Machine Learning Models for Fine-Grained Visual Categorization." Doctoral thesis, Università di Catania, 2019. http://hdl.handle.net/10761/4144.
Full textAbstract:
Artificial intelligence and machine learning have long attempted to emulate human visual system.
With the recent advances in deep neural networks, which take inspiration from the architecture of the primate visual hierarchy, human-level visual abilities are now coming within reach of artificial systems. However, the existing computational models are designed with engineering goals, loosely emulating computations and connections of biological neurons, especially in terms of intermediate visual representations.
In this thesis we aim at investigating how human skills can be integrated into computational models in order to perform fine-grained image categorization, a task which requires the application of specific perceptive and cognitive abilities to be solved. In particular, our goal is to develop systems which, either implicitly or explicitly, combine human reasoning processes with deep classification models. Our claims is that by the emulation of the process carried out by humans while performing a recognition task it is possible to yield improved classification performance.
To this end, we first attempt to replicate human visual attention by modeling a saliency detection system able to emulate the integration of the top-down (task-controlled, classification-driven) and bottom-up (sensory information) processes; thus, the generated saliency maps are able to represent implicitly the way humans perceive and focus their attention while performing recognition, and, therefore, a useful supervision for the automatic classification system. We then investigate if and to what extent the learned saliency maps can support visual classification in nontrivial cases. To achieve this, we propose SalClassNet, a CNN framework consisting of two networks jointly trained: a) the first one computing top-down saliency maps from input images, and b) the second one exploiting the computed saliency maps for visual classification.
Gaze shifts change in relation to a task is not the only process when performing classification in specific domains, but humans also leverage a-priori specialized knowledge to perform recognition. For example, distinguishing between different dog breeds or fruit varieties requires skills that not all human possess but only domain experts. Of course, one may argue that the typical learning-by-example approach can be applied by asking domain experts to collect enough annotations from which machine learning methods can derive the features necessary for the classification. Nevertheless, this is a really costly process and often infeasible. Thus, the second part of this thesis aim at explicitly modeling and exploiting domain-specific knowledge to perform recognition.
To this end, we introduce and demonstrate that computational ontologies can explicitly encode human knowledge and that it can be used to support multiple tasks from data annotation to classification. In particular, we propose an ontology-based annotation tool, able to reduce significantly the efforts to collect highly-specialized labels and demonstrate its effectiveness building the VegImage dataset, a collection of about 4,000 images belonging to 24 fruit varieties, annotated with over 65,000 bounding boxes and enriched with a large knowledge base consisting of more than 1,000,000 OWL triples.
We then exploit this ontology-structured knowledge by combining a semantic-classifier, which performs inference based on the information encoded in the domain ontology, with a visual convolutional neural network, showing that the integration of semantics into automatic classification models can represents the key to solve a complex task such as the fine-grained recognition of fruit varieties, a task which requires the contribution of domain expert to be completely solved.
Performance evaluation of the proposed approaches provides a basis to assess the validity of our claim along with the scientific soundness of developed models.
22
Frémy, Guillaume. "Synthèse de sondes luminescentes pour la détection séquence spécifique d'ADN double brin." Thesis, Université Grenoble Alpes (ComUE), 2019. http://www.theses.fr/2019GREAV073.
Full textAbstract:
L’ADN est le support de l’information de tout être vivant. La possibilité de pouvoir cibler et visualiser in vivo une séquence spécifique d’ADN et plus particulièrement un gène est un enjeu de taille pour le suivi médical aussi bien que pour la compréhension du vivant. Pour y parvenir, la détection par luminescence est particulièrement attrayante de par sa facilité de visualisation avec des outils simples.L’objet de cette thèse était d’apporter la preuve de concept de sondes luminescentes pour la détection séquence spécifique d’ADN double brin, basées d’une part sur les propriétés de luminescence des lanthanides, particulièrement intéressantes pour la détection en milieu biologique, et d’autre part sur les propriétés de reconnaissance de l’ADN par les protéines à doigts de zinc. Nous nous sommes intéressé au ciblage d’un duplex d’ADN palindromique de 12 paires de bases par un couple de protéines à doigts de zinc intégrant un système FRET, où un complexe de lanthanide(III) sur une protéine joue le rôle de donneur et un fluorophore organique sur l’autre protéine joue celui d’accepteur.Pour cela, une nouvelle famille de complexes de lanthanide(III) bioconjugables a été élaborée et des protéines à doigts de zinc fonctionnalisée par différents chromophores ont été synthétisés chimiquement par synthèse peptidique supportée sur résine et assemblage par ligation chimique native de trois fragments. Les caractérisations spectroscopiques des systèmes développés ont permis de mettre en évidence l’interaction des sondes avec la séquence d’ADN palindromique et de valider la preuve de concept d’une détection de cette séquence par un FRET basé sur des lanthanides<br>DNA is the carrier of genetic information in living organisms. Targeting and visualizing in vivo a specific DNA sequence is of particular interest for medical diagnosis and biological research. In this purpose, luminescent detection is very attractive because it can be easily observed with simple tools.The aim of this work was to establish the proof of concept of luminescent probes for the sequence-specific detection of double stranded DNA based on lanthanide luminescence, which is attractive for biological applications, and on zinc finger proteins for their DNA binding properties. We focused on the detection of a 12-base pair palindromic DNA using a pair of zinc finger proteins, one bearing a lanthanide(III) complex as a the FRET donor and the other an organic fluorophore as an acceptor.In this purpose, a new family of bioconjugatable lanthanide(III) complexes was developed and zinc finger proteins with various chromophores were synthesized chemically, by combination of solid phase peptide synthesis and assembly of peptidic segments by native chemical ligation. The spectroscopic characterizations of these systems have evidenced the interaction of the probes with the palindromic DNA, thereby validating the proof of concept of luminescence detection of this DNA sequence by a lanthanide-based FRET system
23
Meinhardt, Llopis Enric. "Morphological and statistical techniques for the analysis of 3D images." Doctoral thesis, Universitat Pompeu Fabra, 2011. http://hdl.handle.net/10803/22719.
Full textAbstract:
Aquesta tesi proposa una estructura de dades per
emmagatzemar imatges tridimensionals. L'estructura da dades té
forma d'arbre i codifica les components connexes dels conjunts de
nivell de la imatge. Aquesta estructura és la eina bàsica per
moltes aplicacions proposades: operadors morfològics
tridimensionals, visualització d'imatges mèdiques, anàlisi
d'histogrames de color, seguiment d'objectes en vídeo i detecció
de vores. Motivada pel problema de la completació de vores, la
tesi conté un estudi de com l'eliminació de soroll mitjançant variació
total anisòtropa es pot fer servir per calcular conjunts de
Cheeger en mètriques anisòtropes. Aquests conjunts de Cheeger
anisòtrops es poden utilitzar per trobar òptims globals d'alguns
funcionals per completar vores. També estan relacionats amb
certs invariants afins que s'utilitzen en reconeixement
d'objectes, i en la tesi s'explicita aquesta relació.<br>This thesis proposes a tree data structure to encode the connected
components of level sets of 3D images. This data structure is applied
as a main tool in several proposed applications: 3D morphological
operators, medical image visualization, analysis of color histograms,
object tracking in videos and edge detection. Motivated by the
problem of edge linking, the thesis contains also an study of
anisotropic total variation denoising as a tool for computing
anisotropic Cheeger sets. These anisotropic Cheeger sets can be used
to find global optima of a class of edge linking functionals. They
are also related to some affine invariant descriptors which are used
in object recognition, and this relationship is laid out explicitly.
24
Guieu, Julien. "Esthétiques de l'indice dans le cinéma américain des années 2000." Thesis, Paris 3, 2012. http://www.theses.fr/2012PA030141.
Full textAbstract:
Plusieurs films américains des années 2000 (Mulholland Drive et INLAND EMPIRE de David Lynch, The Virgin Suicides de Sofia Coppola, Memento de Christopher Nolan, The Pledge de Sean Penn, Broken Flowers de Jim Jarmusch et Zodiac de David Fincher) opèrent une remise en question de la fonction, du fonctionnement et de la représentation des indices sur lesquels s’appuient tant la littérature que le cinéma policiers. Ces films, qui reprennent certains codes du genre sans être tous à proprement parler des « films policiers », ont pour point commun de mettre en scène une enquête qui n’aboutit pas et qui se retourne contre l’enquêteur jusqu’à ébranler son identité. Ils font ainsi écho aux récits de détection dits métaphysiques (The Crying of Lot 49 de Thomas Pynchon, City of Glass de Paul Auster...) : l’indice, loin de permettre la clôture du récit, devient le moyen de son ouverture. À sa juste interprétation succède le foisonnement des lectures et des histoires possibles. Autrefois transparent, il se fait opaque ; de fluide, sa circulation devient accidentée – ce à quoi correspondent de nouvelles manières de le filmer. Les codes du genre policier visant à marquer l’indice tout en favorisant sa lisibilité et l’identification avec l’enquêteur (insert en gros plan, raccord-regard, faible profondeur de champ…) sont détournés selon diverses stratégies : inversion, exagération, etc. Celles-ci ont pour effet de déjouer les attentes des spectateurs et de les rendre inquiets en rétablissant l’incertitude fondamentale de la littérature policière, que le cinéma policier tend à minorer, tout en la mettant au service de projets esthétiques par ailleurs très différents les uns des autres<br>A few American films released between 2000 and 2007 (David Lynch’s Mulholland Drive and INLAND EMPIRE, Sofia Coppola’s The Virgin Suicides, Christopher Nolan’s Memento, Sean Penn’s The Pledge, Jim Jarmusch’s Broken Flowers and David Fincher’s Zodiac) question the function, inner workings and representation of the clues on which detective fiction and film rely. These movies, which take up certain tropes of the genre without necessarily being detective films per se, all revolve around an investigation which is left incomplete and eventually turns against the investigator, to the point of shattering his or her sense of identity. They thus follow in the footsteps of metaphysical detective fiction (novels such as Thomas Pynchon’s The Crying of Lot 49 and Paul Auster’s City of Glass), in that the clue, instead of bringing about the closure of the narrative, becomes the instrument of its open-endedness. Its one correct interpretation is replaced by a proliferation of possible readings and stories. Once transparent, it turns opaque; once fluid, its circulation becomes problematic – which leads to new ways of filming it. The codes that detective films use to point out the clue, increase its legibility and foster identification with the investigator (close-up insert, eyeline match, shallow focus…) are subverted through a number of strategies such as inversion and exaggeration. These aim to deceive the spectator’s expectations and to unsettle him or her by reinstating the fundamental uncertainty of detective fiction, which detective films normally tend to repress, and which is here incorporated into aesthetic projects that otherwise differ widely
25
Adiaviakoye, Ladji. "Observatoire de trajectoire de piétons à l'aide d'un réseau de télémètre laser à balayage : application à l'intérieur des bâtiments." Thesis, Angers, 2015. http://www.theses.fr/2015ANGE0086.
Full textAbstract:
Dans la vie de tous les jours, nous assistons à des chorégraphies surprenantes dans les déplacements de foules de piétons. Les mécanismes qui sont à la base de la dynamique des foules humaines restent peu connus. Un des modes d’observation des piétons consiste à réaliser des mesures en conditions réelles (exemple : aéroport, gare, etc.). La trajectoire empruntée, la vitesse et l’accélération sont les données de base pour une telle analyse. C’est dans ce contexte que se placent nos travaux qui combinent étroitement observations en milieu naturel et expérimentations contrôlées. Nous avons proposé un système pour le suivi de plusieurs piétons dans un environnement fermé, à l’aide d’un réseau de télémètres lasers à balayage. Nous avons fait avancer l’état de l’art sur quatre plans.Premièrement, nous avons introduit une méthode de fusion automatique des données, permettant de discriminer les objets statiques (murs, poteaux, etc.) et aussi d’augmenter le taux de détection.Deuxièmement, nous avons proposé une méthode de détection non paramétrique basée sur la modélisation de la marche. L’algorithme estime la position du piéton, que celui-ci soit immobile ou en mouvement.Finalement, notre suivi repose sur la méthode Rao-Blackwell Monte Carlo Association de Données, avec la particularité de suivre un nombre variable de piétons.L’algorithme a été évalué quantitativement par des expériences de comportement social à différents niveaux de densité. Ces expériences ont eu lieu dans une école, près de 300 piétons ont été suivis dont une trentaine simultanément<br>In everyday life, we witness surprising choreographies in the movements of crowds of pedestrians. The mechanisms that underlie the dynamics of human crowd dynamics remain poorly understood. One of the ways of observing pedestrians consists in taking measurements in real conditions (e. g. airport, station, etc.). The trajectory, speed and acceleration are the basic data for such an analysis. It is in this context that our work is placed, which closely combines observations in the natural environment with controlled experiments. We proposed a system for tracking multiple pedestrians in a closed environment using a network of scanning laser rangefinders. We have advanced the state of the art on four levels: first, we have introduced an automatic data fusion method to discriminate static objects (walls, poles, etc.) and also to increase the detection rate; second, we have proposed a non-parametric detection method based on walking modeling. The algorithm estimates the position of the pedestrian, whether stationary or moving, and finally, our monitoring is based on the Rao-Blackwell Monte Carlo Association Data Method, with the particularity of tracking a variable number of pedestrians, which was quantitatively evaluated by experiments in social behaviour at different levels of density. These experiments took place in a school, nearly 300 pedestrians were followed, about thirty of them simultaneously
26
Vožda, Ondřej. "Řízení invalidního vozíku." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2013. http://www.nusl.cz/ntk/nusl-220145.
Full textAbstract:
This thesis describes development of control algorithm for a wheelchair. Wheelchair should be capable of tracking and following a wall or a similar flat surface. Thesis is supposed to be an extension of the previous concept, whose purpose was to allow remote telepresence control of this wheelchair. SRF08 ultrasonic range finders are used to measure distance from the wall. Furthermore, image processing for mark detection is discussed. Purpose of these marks is to increase precision during final phase of the parking.
27
Wåhlin, Peter. "Enhanching the Human-Team Awareness of a Robot." Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-16371.
Full textAbstract:
The use of autonomous robots in our society is increasing every day and a robot is no longer seen as a tool but as a team member. The robots are now working side by side with us and provide assistance during dangerous operations where humans otherwise are at risk. This development has in turn increased the need of robots with more human-awareness. Therefore, this master thesis aims at contributing to the enhancement of human-aware robotics. Specifically, we are investigating the possibilities of equipping autonomous robots with the capability of assessing and detecting activities in human teams. This capability could, for instance, be used in the robot's reasoning and planning components to create better plans that ultimately would result in improved human-robot teamwork performance. we propose to improve existing teamwork activity recognizers by adding intangible features, such as stress, motivation and focus, originating from human behavior models. Hidden markov models have earlier been proven very efficient for activity recognition and have therefore been utilized in this work as a method for classification of behaviors. In order for a robot to provide effective assistance to a human team it must not only consider spatio-temporal parameters for team members but also the psychological.To assess psychological parameters this master thesis suggests to use the body signals of team members. Body signals such as heart rate and skin conductance. Combined with the body signals we investigate the possibility of using System Dynamics models to interpret the current psychological states of the human team members, thus enhancing the human-awareness of a robot.<br>Användningen av autonoma robotar i vårt samhälle ökar varje dag och en robot ses inte längre som ett verktyg utan som en gruppmedlem. Robotarna arbetar nu sida vid sida med oss och ger oss stöd under farliga arbeten där människor annars är utsatta för risker. Denna utveckling har i sin tur ökat behovet av robotar med mer människo-medvetenhet. Därför är målet med detta examensarbete att bidra till en stärkt människo-medvetenhet hos robotar. Specifikt undersöker vi möjligheterna att utrusta autonoma robotar med förmågan att bedöma och upptäcka olika beteenden hos mänskliga lag. Denna förmåga skulle till exempel kunna användas i robotens resonemang och planering för att ta beslut och i sin tur förbättra samarbetet mellan människa och robot. Vi föreslår att förbättra befintliga aktivitetsidentifierare genom att tillföra förmågan att tolka immateriella beteenden hos människan, såsom stress, motivation och fokus. Att kunna urskilja lagaktiviteter inom ett mänskligt lag är grundläggande för en robot som ska vara till stöd för laget. Dolda markovmodeller har tidigare visat sig vara mycket effektiva för just aktivitetsidentifiering och har därför använts i detta arbete. För att en robot ska kunna ha möjlighet att ge ett effektivt stöd till ett mänskligtlag måste den inte bara ta hänsyn till rumsliga parametrar hos lagmedlemmarna utan även de psykologiska. För att tyda psykologiska parametrar hos människor förespråkar denna masteravhandling utnyttjandet av mänskliga kroppssignaler. Signaler så som hjärtfrekvens och hudkonduktans. Kombinerat med kroppenssignalerar påvisar vi möjligheten att använda systemdynamiksmodeller för att tolka immateriella beteenden, vilket i sin tur kan stärka människo-medvetenheten hos en robot.<br><p>The thesis work was conducted in Stockholm, Kista at the department of Informatics and Aero System at Swedish Defence Research Agency.</p>
28
FAMOURI, SINA. "Machine learning methods for the analysis and interpretation of images and other multi-dimensional data." Doctoral thesis, Politecnico di Torino, 2022. https://hdl.handle.net/11583/2972835.
Full text
29
Manet, Anthony. "Etude de défauts non francs sur des câbles en vue du diagnostic." Thesis, Paris Est, 2016. http://www.theses.fr/2016PESC1054/document.
Full textAbstract:
La détection des défauts non francs est un passage obligé dans la gestion de la maintenance des câbles (Wire Health Monitoring) et permet d’anticiper l’apparition de défauts francs engendrés par l'aggravation de défauts non francs. Ces travaux de thèse visent à étudier la problématique de défauts non francs dans les câbles électriques. L'étude proposée consiste à étudier le problème direct : modélisation électromagnétique et compréhension des phénomènes physiques liés à la présence des défauts non francs, et impact des défauts sur leurs signatures obtenues par réflectométrie. Il est proposé dans ce travail de caractériser des défauts non francs représentatifs de situations réelles, ce qui peut servir ultérieurement dans la résolution du problème inverse : déterminer la localisation et la sévérité des défauts à partir du réflectogramme en vue du diagnostic. L'approche proposée se fait en deux temps. Dans un premier temps, une caractérisation électromagnétique d’une zone localisée d’un câble présentant un défaut non franc est réalisée grâce à une modélisation électromagnétique prenant en compte la géométrie tridimensionnelle du défaut. Deux méthodes numériques ont été exploitées : une méthode de différences finies dans le domaine temporel (FDTD) et une méthode de Galerkin discontinu. Les résultats des simulations permettent d'exprimer les perturbations engendrées par le défaut et de déduire leur influence sur la propagation des signaux dans le câble. Des validations expérimentales menées dans le domaine temporel et le domaine fréquentiel permettent de confronter les mesures aux prédictions numériques. Dans un deuxième temps, des modèles électriques de défauts sont exprimés sous forme de paramètres localisés R, L, C, et G qui peuvent être utilisés dans un modèle de ligne de transmission. Une telle analyse des défauts non francs permet de relier une faible variation locale des caractéristiques physiques et électriques de la ligne à une variation des signaux de réflectométrie et des paramètres électriques de la ligne. L’approche permet de fournir des informations utiles pour caractériser des défauts et peut ainsi contribuer à améliorer les performances des systèmes de détection<br>The soft fault detection feature is certainly a very important aspect of wire health monitoring and an important process required in electrical wiring system operation. It has a great influence on the security and quality of supply. In transmission line networks, this feature is needed to provide a timely identification of the faulted line thus anticipating the appearance of severe faults that are initially caused by soft fault degradation. This work focuses on soft fault problems in electrical fault diagnosis and their weak impact on coaxial transmission lines. The objective of this work is to carry out a soft fault forward model: electromagnetic modeling and investigating the behavior of the line after soft damages and then to analyze its effects on their signatures obtained by reflectometry. It is proposed in this work to characterize the representative soft damages in real situations, which could be used later in solving the inverse problem: determining the position and severity of defects from the reflectometry response for the diagnosis. The proposed approach is based on the following steps: first, an electromagnetic characterization of a faulty region of a cable is carried out by electromagnetic modeling, by taking into account the three-dimensional geometry of defect. For this purpose, two numerical methods have been used: Finite Difference Time Domain (FDTD) and a Discontinuous Galerkin. The simulation results allow to study the disruption initiated by the fault and to infer their influence on the signal propagation along the cable. The experimental validation provided in frequency- and time-domain allows to confront experimental measurements with simulation predictions. In a second step, electrical fault models are expressed in terms of lumped parameters R, L, C, and G, which can be used in a transmission line model. Such analysis of soft faults allows to relate low local variation of the physical and electrical characteristics of the line to a reflectometry signals variation and electrical parameters changes. The approach can provide useful information to characterize defects and can thus contribute to improve the performance of detection systems
30
Floyd, Beatrice K. "Vision-Based Techniques for Cognitive and Motor Skill Assessments." Case Western Reserve University School of Graduate Studies / OhioLINK, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=case1338824242.
Full text
31
Chander, Bhan Chander Bhan. "Photonics-based environmental sensors for automotive air quality monitoring." Electronic Thesis or Diss., Lyon, INSA, 2024. http://www.theses.fr/2024ISAL0120.
Full textAbstract:
Cette thèse explore les dispositifs de circuits photoniques intégrés (PIC) basés sur une plateforme en nitrure de silicium (SiN), en mettant l'accent sur leur potentiel pour la détection de particules dans l'air, un élément clé des capteurs de l'indice de qualité de l'air (AQI). La haute sensibilité volumique des résonateurs à anneaux (MRR) dans ces dispositifs permet la détection de faibles concentrations de particules, tandis que les forces optiques permettent le piégeage spécifique à la taille des particules. Pour relever les défis liés au piégeage de particules diélectriques de moins de 100 nm, cette recherche explore diverses structures photoniques, y compris des guides d'onde diélectriques, des résonateurs en mode d'ordre supérieur (HOM) et des guides d'onde plasmoniques hybrides. cette étude comprend leur conception, leur fabrication et leur compatibilité avec des plateformes industrielles telles que DAPHNE de STMicroelectronics. L'analyse des forces optiques, réalisée à l'aide de méthodes telles que le tenseur de contrainte de Maxwell (MST) et l'approximation de dipôle discret (DDA), fournit un cadre rigoureux pour optimiser la conception et évaluer différentes structures. Les résultats soulignent le potentiel des guides d'ondes HOM et des guides d'ondes plasmoniques hybrides pour le piégeage optique avancé et la détection de l'IQA, ouvrant ainsi la voie à des approches innovantes pour les applications de surveillance de l'environnement<br>This thesis explores photonic integrated circuit (PIC) devices based on a silicon nitride (SiN) platform, focusing on their potential for airborne particle detection, a key component of air quality index (AQI) sensors. The bulk sensitivity of the ring resonators (MRR) in these devices enables detection of low particle concentrations, while the optical forces enable size-specific trapping of particles. To address the challenges of trapping dielectric particles smaller than 100 nm, this research explores various photonic structures, including dielectric waveguides, higher-order mode (HOM) resonators and hybrid plasmonic waveguides. The study includes their design, fabrication and compatibility with industrial platforms such as STMicroelectronics' DAPHNE. Optical force analysis, using methods such as Maxwell's stress tensor (MST) and discrete dipole approximation (DDA), provides a rigorous framework for optimizing the design and evaluating different structures.The findings underscore the potential of HOM waveguides and hybrid plasmonic waveguides for advanced optical trapping and AQI sensing, paving the way for innovative approaches to environmental monitoring applications
32
Debroux, Noémie. "Mathematical modelling of image processing problems : theoretical studies and applications to joint registration and segmentation." Thesis, Normandie, 2018. http://www.theses.fr/2018NORMIR02/document.
Full textAbstract:
Dans cette thèse, nous nous proposons d'étudier et de traiter conjointement plusieurs problèmes phares en traitement d'images incluant le recalage d'images qui vise à apparier deux images via une transformation, la segmentation d'images dont le but est de délimiter les contours des objets présents au sein d'une image, et la décomposition d'images intimement liée au débruitage, partitionnant une image en une version plus régulière de celle-ci et sa partie complémentaire oscillante appelée texture, par des approches variationnelles locales et non locales. Les relations étroites existant entre ces différents problèmes motivent l'introduction de modèles conjoints dans lesquels chaque tâche aide les autres, surmontant ainsi certaines difficultés inhérentes au problème isolé. Le premier modèle proposé aborde la problématique de recalage d'images guidé par des résultats intermédiaires de segmentation préservant la topologie, dans un cadre variationnel. Un second modèle de segmentation et de recalage conjoint est introduit, étudié théoriquement et numériquement puis mis à l'épreuve à travers plusieurs simulations numériques. Le dernier modèle présenté tente de répondre à un besoin précis du CEREMA (Centre d'Études et d'Expertise sur les Risques, l'Environnement, la Mobilité et l'Aménagement) à savoir la détection automatique de fissures sur des images d'enrobés bitumineux. De part la complexité des images à traiter, une méthode conjointe de décomposition et de segmentation de structures fines est mise en place, puis justifiée théoriquement et numériquement, et enfin validée sur les images fournies<br>In this thesis, we study and jointly address several important image processing problems including registration that aims at aligning images through a deformation, image segmentation whose goal consists in finding the edges delineating the objects inside an image, and image decomposition closely related to image denoising, and attempting to partition an image into a smoother version of it named cartoon and its complementary oscillatory part called texture, with both local and nonlocal variational approaches. The first proposed model addresses the topology-preserving segmentation-guided registration problem in a variational framework. A second joint segmentation and registration model is introduced, theoretically and numerically studied, then tested on various numerical simulations. The last model presented in this work tries to answer a more specific need expressed by the CEREMA (Centre of analysis and expertise on risks, environment, mobility and planning), namely automatic crack recovery detection on bituminous surface images. Due to the image complexity, a joint fine structure decomposition and segmentation model is proposed to deal with this problem. It is then theoretically and numerically justified and validated on the provided images
33
Hsiao, Chao-Yueh, and 蕭朝岳. "Study Finger Detection Techniques Using Physical Feature." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/68189641290444567747.
Full textAbstract:
碩士<br>國立勤益科技大學<br>電子工程系<br>102<br>With the advancement of technology, human-computer interaction interface has been the subject of many people’s researches, from the early keyboard and mouse to the current cameras and microphones and other tablet products. In recent years, the sold somatosensory games such as Nintendo Wii, Xbox and Kinect can allow users to manipulate the game by using the human body rather than the remote control or the handle to operate the game.
Through the color detection and image subtraction technique, this study found the hand image, and the histogram analysis was then used to find the palm and wrist arm junction points. After obtaining the palm image, to the convex hull algorithm was used to analyze the characteristics of the palm to identify the portion of fingertips. Finally, by the midpoint of the fingertips and the wrist, the possible gestures of wrists were calculated. The experimental results show that this method can effectively remove background and keep the hand image, so the palm image is segmented out to find exactly the fingertip position and identify a variety of gestures.
34
Chuang, Yi-Fan. "Vision-based Finger Detection and Its Applications." 2007. http://www.cetd.com.tw/ec/thesisdetail.aspx?etdun=U0001-3006200701504500.
Full text
35
Chuang, Yi-Fan, and 莊怡凡. "Vision-based Finger Detection and Its Applications." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/33510051014997799611.
Full textAbstract:
碩士<br>臺灣大學<br>資訊網路與多媒體研究所<br>95<br>In this paper, we developed a real-time fingertip detection
technique. The proposed technique works on images captured by infrared cameras. The cameras are settled on one side of the interactive surface, capturing human gestures taken place on the other side. The novelties of our technique are: firstly, the technique works with an infrared camera coupled with an infrared illuminator, which is easy to deploy and cost effective. Secondly, the proposed technique is designed to be robust for a non-uniform illuminated surface. We have deployed the technique on two applications: i-m-Top and Magic Crystal Ball (MaC Ball). i-m-Top is a rear-projection multi-resolution tabletop which provides several basic functions of browsing and modifying documents on the tabletop. With the characteristics of the projection diffuser, we can separate finger touching from palm hovering events when the user interacts with the diffuser. A video retrieval system working with finger touching and palm hovering interactions is presented on i-m-Top to show its intuitive operations. MaC Ball is an interactive display system that is suitable in museums, galleries, and exhibitions to demonstrate 3D treasures. For the interactions of MaC Ball, we integrate the fingertip finding technique and optic-flow motion detection to provide the users with natural interactions to experience the virtual exhibition.
36
Liu, Yung-Chun, and 劉勇均. "EEG Signal Analysis System for Finger Movement Detection." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/23412415412673544100.
Full textAbstract:
碩士<br>國立成功大學<br>資訊工程學系碩博士班<br>92<br>Many neurological diseases, such as stroke and spinal cord injury, disrupt the connections between brain cortex and muscles. Besides, some other diseases may destruct the muscle and make it functionless. All these diseases interfere with the voluntary movements of the subjects and influence their ability to accomplish the attempted task. Brain-computer interface (BCI), which defines an artificial alternative output from the brain cortex to make communication with their surrounding targets, can improve above deficits.
The most common way of BCI is to give control signals based on the analysis of Electroencephalogram (EEG) signals. And the recognition of finger movements has been one of the most important issues in this field. In the previous researches, the length of EEG trials for analysis were usually between 4 to 10 seconds, therefore it would have difficulties in real-time applications. For this reason, we study the technique of analyzing the EEG signals which have the length of one second, and construct a real-time EEG recognition system based on it for detecting finger movements. We adopt the strategy, named Active Time Segment Selection, to pick the most appropriate time segment of the EEG trial for the recognition of finger movements. And the classifier is trained with the information of this segment in all trials. The integrated processes with the above-mentioned functions form a two-staged recognition system to classify the finger motions in real-time. Besides, we propose an automatic approach to provide statistical analysis on the results of recognition in each stage.
From the results of the experiment, it has shown that our system can distinguish a finger movement or a non-movement from the input EEG signal sequences, and further recognize the movement as a left or a right one successfully. We expect to use the system in controlling clinical assistive devices in the future, and benefit the subjects with neurological diseases or limb disabilities.
37
Chuang, Su-Ting, and 莊舒婷. "Finger Detection for Multi-Touch Tabletop Display System." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/59765946114343651201.
Full textAbstract:
碩士<br>國立臺灣大學<br>資訊網路與多媒體研究所<br>99<br>Advances in display and input technologies either based on electronic devices or computer vision have led to booming popularity of direct-touch interactive surfaces. Since there is a trend to use larger display, computer vision approach is adopted for direct-touch interaction due to low cost. However it suffered from non-uniform lighting problem. Besides, the computation efficiency is not good enough in existent multi-touch detection systems. Furthermore, determining parameters for detection system includes try-and-error process which is tedious and time-consuming. Therefore, we modified and designed a finger detection system based on previous work to improve drawbacks mentioned above. In this work, we develop a GPU-accelerated multi-touch detection which makes the computational efficiency fast enough to reduce the delay while manipulating tabletop system. In addition, we propose a method to normalize foreground to solve the non-uniform lighting problem. Furthermore, we propose a sampling-based parameter search method to help user determine an appropriate set of parameters for multi-touch detection system.
38
Hsueh, Jing-Lin, and 薛敬霖. "Finger Detection and Gesture Recognition In Tabletop Display System." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/90072916299454162365.
Full textAbstract:
碩士<br>國立臺灣大學<br>資訊工程學研究所<br>99<br>Due to the development of multi-touch technology and the demand for user-friendly interactive operation, there have been a number of successful products. Among them, interactive tabletop system is a remarkable one, and it is still in progress. Based on computer vision approach, it is capable of expanding to large scale with low cost. However, the computational efficiency would be a concern as the image processing loading increases. In order to overcome this issue, we develop a GPU-accelerated multi-touch detection system. In the meantime, we figure out the input images would have uneven brightness due to lighting. So we implement an adaptive threshold algorithm so that the system performance would be more preferable.
As for gesture recognition, we propose a software architecture which can support a variety of multi-touch hardware, provide gesture processing, be cross platform compatible, and allow applications to be developed in the desired programming language. Besides, a prototype is implemented for the purpose of recognize user-defined gestures.
39
GAO, ZHEN-JIE, and 高振傑. "Finger Detection by Renewed FEMD Method using Kinect Depth Camera Image." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/18527072041332052585.
Full textAbstract:
碩士<br>輔仁大學<br>資訊工程學系碩士班<br>104<br>The production cost reduction of depth sensor makes it cheaper and cheaper than ever before. Such a trend also provides many research hints of using different sensing ways for Human-Computer Interface (HCI) applications. Among the integrated sensors sold in the market, the Kinect senor is relatively cheaper than the others. The Kinect sensor consists of RGB camera, depth sensor, and multi-array microphone. It makes a great progress of using the Kinect sensor for human body tracking, face recognition, and human action recognition. For hand gesture recognition, with respect to the whole body recognition, the gesture analysis region is even smaller, more delicate and complex. Therefore, hand gesture is still an open problem and is under the development stage.
In this thesis, we improve the Finger-Earth Mover Distance (FEMD) gesture recognition method used in「Part-Based Hand Gesture Recognition System」. This recognition system uses RGB image as the input image and fixed thresh for the threshing decomposition. The proposed improvements consist of two aspects. Firstly, the hand gesture images are captured with the depth image rather than RGB image, which can effectively reduce the noise on hand image while doing the Background Subtraction and skin color detection failure. Moreover, for the threshing decomposition, we replace the fixed thresh by the relative distance thresh to the circle of the palm. It can immediately compute the corresponding optimal thresh for the recognition of different hand gestures with respect to various types of palms. By our experimental result, our proposed method can increase the recognition rate from 92.9% to 98.2% and the average recognition time is less than 34 ms.
40
Wu, Chen-Hung, and 吳宸泓. "Menu Control for Recalling of Senior Citizens Based on Motion Finger Detection." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/20332029477663704530.
Full textAbstract:
碩士<br>銘傳大學<br>電子工程學系碩士班<br>101<br>This thesis presents and designs a menu control system for memory recalling which is simple and easy-to-use for senior citizens and their life convenience can be improved. This system includes three major parts: (1) Fingertip detection: This can be achieved by skin detection and edge detection to locate the fingertip position. Then the users can intuitively control the system by fingertip clicking；(2) Menu switching: Simple and clear menu pages are designed to let the users understand and switch the menu pages fluently；(3) Recording and playing: By using the video clips to record the process of object placement in the daily life for senior citizens, the users can directly use the control menu to choose the desired video clips to play and the position of the forgotten object can be recalled. Furthermore, this thesis proposes the algorithms for finger and fingertip detection. This can let the users to intuitively click the menu by using the fingertip. By integrating skin detection, edge detection, fingertip detection, and image processing techniques, this thesis has achieved a simple and easy-to-use menu control system.
41
Lisogurski, Dan. "On Line Single Trial Detection of Index Finger Flexions from Spatiotemporal EEG." Thesis, 1998. http://hdl.handle.net/2429/7954.
Full textAbstract:
A Brain Computer Interface (BCI) detects commands directly from the operator's
brain and provides an output which can be easily interpreted by a computer. Much of
the research to date has focused on differentiating between several possible commands
rather than between control signals and the idle state. For most practical applications,
it is essential that the operator is able to rest without issuing unintended commands.
Mason proposes an Asynchronous Signal Detector (ASD) which allows existing
BCI techniques to function outside the laboratory. The ASD continuously monitors
the electroencephalograph (EEG) identifying segments which contain commands and
acts as a switch which selectively relays EEG to a Control Signal Classifier (CSC).
Existing BCI methods may be used for the CSC in order to determine which command
the operator intended to issue. Alternatively, the ASD can function as a stand alone
system capable of recognizing a single control signal.
The goal of this research was to implement an ASD capable of identifying
Voluntary Movement Related Potentials (VMRPs) from a continuous sampling of
surface electrodes spatially distributed over the motor areas of the brain. Features
were extracted from EEG components below 4 Hz as in Mason's Low Frequency
ASD (LF-ASD) and classified using Learning Vector Quantization (LVQ). A revised
version of Mason's ASD was implemented as an on line system. Two able bodied
subjects each participated in three sessions as a preliminary evaluation of the ASD in
detecting right handed index finger flexions. Subject training was also briefly investigated
by providing the participants with feedback one second after movements were detected. Training appeared to take place rapidly with the percentage of detected
movements for both subjects increasing from 24.0% in the first session to 45.3% and
49.3% respectively during the second attempt. During the three sessions for each
subject 90.4% up to 99.2% of the idle E EG collected was correctly classified. Further
research is required to evaluate the ASD as a generic VMRP detector and to test the
method with participants who have little or no motor control.
42
Lin, Chun-Chang, and 林鈞章. "Application of zinc finger protein-conjugated sensor chip for the detection of zinc ions." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/78424933225107361209.
Full textAbstract:
碩士<br>國立清華大學<br>分子與細胞生物研究所<br>95<br>Metal-responsive transcription factor 1 (MTF-1) is a transcription factor which regulates the gene expression of several metal inducible genes. The N-terminus of MTF-1 is consist of six zinc fingers, and the C-terminus contains three domains associated with transcriptional activation. The zinc finger domains of MTF-1 are able to sense the concentration change of Zn(Ⅱ) and bind to the metal response elements (MREs). In this study, we attempt to purify the zinc finger domains of MTF-1, and try to establish a biomolecule-based biosensor system which is specific for Zn(Ⅱ) detection through the combination of zinc finger protein-conjugated sensor chip and surface plasmon resonance technology. We expressed the glutathione-S-transferase and zinc finger protein fusion protein (GST-6ZF) in E. coli. This fusion protein was initially purified with glutathione beads, followed by gel filtration chromatography. The purified GST-6ZF was immobilized onto a carboxy- methylated dextran matrix (CM5 chip). We evaluted the interaction at different pH values between the zinc finger sensor chip and six metal ions, including Zn(Ⅱ), Ca(Ⅱ), Cd(Ⅱ), Ni(Ⅱ), Co(Ⅱ), and Mg(Ⅱ). It is found that the interaction between zinc finger sensor chip and Zn(Ⅱ) is much stronger than other metal ions at pH 4. The sensitivity of the zinc finger sensor chip to Zn(Ⅱ) is also evaluated. The sensor chip detected the zinc concentration is low as 1μM. Our results show the possibility of using MTF-1 to develop the detection system for bioavailable zinc ions.
43
Lu, Wei-Yu, and 呂緯昱. "A Gesture Recognition Method based on the Finger Tips and Angles with Local Skin Color Detection." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/gm82ej.
Full textAbstract:
碩士<br>國立臺北科技大學<br>資訊工程系研究所<br>98<br>Gesture recognition can be applied to various fields. Usually, it is applied to Human-Computer Interface. By using gesture recognition, the system could transform the gesture signals into computational control signal to replace the interaction model of Computer-Human.
In this paper, we use frame difference to detect the changing pixel in the frame. After masking the face region by face detection, the changing pixel will be examined by skin color detection to keep the parts for labeling. The maximum connected component is found out to set as the region of interest. Statistics and analysis will be conducted to examine the colors in the component, and the color probability distribution and location will become the initial target of Camshift.
In the part of hand feature, convex hull of computational geometry is used to describe the hand contour. From the relationships among polygons in the space, the gestures are recognized by the angles of concave parts.
44
Zhong, Yi-Shu, and 鍾宜書. "Cloning of a cDNA Encoding a Potein with PHD Finger and Detection of Its Autoantibody in Autoimmune Disease Patients." Thesis, 1997. http://ndltd.ncl.edu.tw/handle/01921870228166646752.
Full text
45
Chung, Yi-Shu, and 鍾宜書. "Cloning of a cDNA Encoding a Potein with PHD Finger and Detection of Its Autoantibody in Autoimmune Disease Patients." Thesis, 1997. http://ndltd.ncl.edu.tw/handle/71335499644823052161.
Full textAbstract:
碩士<br>國立臺灣大學<br>生化科學研究所<br>85<br>cDNA encoding a PHD Finger protein, Requiem 6, was cloned.
The expression of Requiem 6 mRNA was found in many tissues and
cells .Requiem 6 is associated with a complex containing DNA
-dependent protein kinase catalytic subunit (DNA-PKcs).
Recently, patients have been identified with antibodies to
the DNA-PKcs that appears to be associated with anti-Ku
antibody. Anti-Requiem 6 auto-antibody was found to be
present in patients of systemic lupus erythematosus, Sj"
gren's syndrome , rheumatoid arthritis, asthma,
palindromic syndrome and multiple sclerosis. The
appearance of anti-Requiem 6 and anti-DNA-PKcs auto-antibodies
in patients with autoimmune conditions is strikingly similar.
These results suggest that Requiem 6 and DNA-PKcs exist in the
same complex .
46
Lu, Ming-Kun, and 呂鳴崑. "Multi-Camera Vision-based Finger Detection, Tracking, and Event Identification Techniques for Multi-Touch Sensing and Human Computer Interactive Systems." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/vgss3p.
Full textAbstract:
碩士<br>國立臺北科技大學<br>資訊工程系研究所<br>100<br>Nowadays, multi-touch technology has become a popular issue. Multi-touch has been implemented in several ways including resistive type, capacitive type and so on. However, because of limitations, multi-touch by these implementations cannot support large screens. Therefore, this thesis proposes a multi-camera vision-based finger detection, tracking, and event identification techniques for multi-touch sensing with implementation. The proposed system detects the multi-finger pressing on an acrylic board by capturing the infrared light through four infrared cameras. The captured infrared points, which are equivalent to the multi-finger touched points, can be used for input equipments and supply man-computer interface with convenience. Additionally, the proposed system is a multi-touch sensing with computer vision technology. Compared with the conventional touch technology, multi-touch technology allows users to input complex commands.
The proposed multi-touch point detection algorithm identifies the multi-finger touched points by using the bright object segmentation techniques. The extracted bright objects are then tracked, and the trajectories of objects are recorded. Furthermore, the system will analyze the trajectories of objects and identify the corresponding events pre-defined in the proposed system. For applications, this thesis wants to provide a simple human-computer interface with easy operation. Users can access and input commands by touch and move fingers. Besides, the proposed system is implemented with a table-sized screen, which can support multi-user interaction.
47
Ali, Syed Musharaf. "Fusion of Stationary Monocular and Stereo Camera Technologies for Traffic Parameters Estimation." Doctoral thesis, 2017. https://repositorium.ub.uni-osnabrueck.de/handle/urn:nbn:de:gbv:700-2017030715611.
Full textAbstract:
Modern day intelligent transportation system (ITS) relies on reliable and accurate estimated traffic parameters. Travel speed, traffic flow, and traffic state classification are the main traffic parameters of interest. These parameters can be estimated through efficient vision-based algorithms and appropriate camera sensor technology.
With the advances in camera technologies and increasing computing power, use of monocular vision, stereo vision, and camera sensor fusion technologies have been an active research area in the field of ITS. In this thesis, we investigated stationary monocular and stereo camera technology for traffic parameters estimation. Stationary camera sensors provide large spatial-temporal information of the road section with relatively low installation costs.
Two novel scientific contributions for vehicle detection and recognition are proposed. The first one is the use stationary stereo camera technology, and the second contribution is the fusion of monocular and stereo camera technologies.
A vision-based ITS consists of several hardware and software components. The overall performance of such a system does not only depend on these single modules but also on their interaction. Therefore, a systematic approach considering all essential modules was chosen instead of focusing on one element of the complete system chain. This leads to detailed investigations of several core algorithms, e.g. background subtraction, histogram based fingerprints, and data fusion methods.
From experimental results on standard datasets, we concluded that proposed fusion-based approach, consisting of monocular and stereo camera technologies performs better than each particular technology for vehicle detection and vehicle recognition. Moreover, this research work has a potential to provide a low-cost vision-based solution for online traffic monitoring systems in urban and rural environments.
48
"Multi-Directional Slip Detection Between Artificial Fingers and a Grasped Object." Master's thesis, 2012. http://hdl.handle.net/2286/R.I.14851.
Full textAbstract:
abstract: Effective tactile sensing in prosthetic and robotic hands is crucial for improving the functionality of such hands and enhancing the user's experience. Thus, improving the range of tactile sensing capabilities is essential for developing versatile artificial hands. Multimodal tactile sensors called BioTacs, which include a hydrophone and a force electrode array, were used to understand how grip force, contact angle, object texture, and slip direction may be encoded in the sensor data. Findings show that slip induced under conditions of high contact angles and grip forces resulted in significant changes in both AC and DC pressure magnitude and rate of change in pressure. Slip induced under conditions of low contact angles and grip forces resulted in significant changes in the rate of change in electrode impedance. Slip in the distal direction of a precision grip caused significant changes in pressure magnitude and rate of change in pressure, while slip in the radial direction of the wrist caused significant changes in the rate of change in electrode impedance. A strong relationship was established between slip direction and the rate of change in ratios of electrode impedance for radial and ulnar slip relative to the wrist. Consequently, establishing multiple thresholds or establishing a multivariate model may be a useful method for detecting and characterizing slip. Detecting slip for low contact angles could be done by monitoring electrode data, while detecting slip for high contact angles could be done by monitoring pressure data. Predicting slip in the distal direction could be done by monitoring pressure data, while predicting slip in the radial and ulnar directions could be done by monitoring electrode data.<br>Dissertation/Thesis<br>M.S. Bioengineering 2012
49
Chiang, Yi-Kai, and 蔣亦凱. "An Algorithm For Detecting Bending-Degree of Finger Skeleton Based on Image Depth Information." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/6zq66z.
Full textAbstract:
碩士<br>國立中興大學<br>資訊科學與工程學系所<br>101<br>A non-contact human-computer interaction system provides an alternative way to control devices and it is more convenient and less restrictive than traditional input methods. However, most researches applied finger or hand gestures recognition by only using a 2D camera. A 3D depth image can provide more intuitional data for finger or hand gestures recognition. In this thesis, a cross-platform algorithm is proposed to detect finger gesture information such as finger bending degree, finger joint and palm position. The proposed method takes into account the 3D data no matter where the images are obtained. This algorithm first obtains a complete 3D hand image for initialization. Then the blending information for each finger is considering. Finally we can reconstruct entire finger bending degrees to form a hand skeleton.
In this thesis, we used a Microsoft Kinect to acquire the experimental samples. Only the depth data is used in the proposed method. The experimental results show that the reconstructed hand skeletons match the real hand situation for every participant.
50
Chen, Jian-Liang, and 陳建良. "The Study of Robot Environmental Feature Detection in SLAM for a Laser Range Finder." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/10763871547042451697.
Full textAbstract:
碩士<br>淡江大學<br>機械與機電工程學系碩士班<br>99<br>The localization is the very important problem for a mobile robot in the unknown environment. It is necessary to modify the exact position of the robot by the new map if the robot moves from any start position. So, localization and mapping of a mobile robot are complement each other in the practical application. Sometimes, it is also called chicken/egg problem.
The objective of this thesis is to make a SLAM by the EKF theory. The localization and mapping are discussed separately under the assumption of Markov. The data of a laser range finder are used to develop the feature map. The feature map and the corresponding pre-set way point are applied to calculate the SLAM by the moving robot in the unknown environmen