Dissertations / Theses on the topic 'Analysis of human drowsiness'
To see the other types of publications on this topic, follow the link: Analysis of human drowsiness.
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 'Analysis of human drowsiness.'
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
Padmanabhan, Sivasankar. "Drowsiness detection using HRV analysis." Thesis, California State University, Long Beach, 2015. http://pqdtopen.proquest.com/#viewpdf?dispub=1596988.
Full textAbstract:
The field of drowsiness detection is gaining more attention these days. An estimate by National Highway Traffic Safety Administration states that the total number of people falling asleep on the wheel is increasing day by day. If there is an effective way to monitor this condition and alert the drivers, many fatal accidents can be prevented. This thesis work elaborates on one such simple, yet effective drowsiness detection algorithm, the HRV - Heart Rate Variability analysis. Many psychological researchers have found out that when a person becomes drowsy, there is a variation in their heart signal. Monitoring this physiological variation would be more efficient than monitoring their facial movements such as blinking, eye brow contraction, and yawning, which are said to happen after much longer time when compared to the immediate changes in the heart rate. Hence, an algorithm that detects drowsiness based on HRV analysis is developed and implemented by analyzing heart signals. Simple hardware setups were used to collect the ECG data, and digital filters were used to remove noise and extract the desired information for further analysis. The developed algorithm was implemented successfully and the results obtained were more precise and satisfactory. This approach of monitoring drowsiness is more reliable and accurate and when implemented with its necessary features, it can monitor drowsiness more effectively and save hundreds of lives every day.
2
Yonkers, Shonee L. Kenyon. "An analysis of ANAM Readiness Evaluation System (ARES) as a predictor of performance degradation induced by sleep deprication in Officer Indoctrination School (OIS) students." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 2004. http://library.nps.navy.mil/uhtbin/hyperion/04Jun%5FYonkers.pdf.
Full text
3
Altmüller, Tobias [Verfasser]. "Driver Monitoring and Drowsiness Detection by Steering Signal Analysis / Tobias Altmüller." Aachen : Shaker, 2007. http://d-nb.info/1164338684/34.
Full text
4
Jin, Ning. "Human motion analysis." Thesis, University of Surrey, 2007. http://epubs.surrey.ac.uk/804406/.
Full text
5
Sridharan, Kousik Sarathy. "Real-time acquisition and analysis ofElectro-oculography signals." Thesis, Linköpings universitet, Biomedicinsk instrumentteknik, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-76734.
Full textAbstract:
Electro-oculography signals are corneo-retinal potentials that carry informationpertaining to eye movements. This information can be used to estimate drowsinesslevel of the subject which could provide interesting insights into research of acci-dent prevention. Of all features present, blink duration has been proved to be aneffective measure of drowsiness. The aim of this thesis work is to build a portablesystem to acquire and analyze electro-oculographic (EOG) signals in real-time.The system contains two sub-systems; a hardware sub-system that consists of thefilters, amplifiers, data acquisition card and isolation and the software sub-systemthat contains the program to acquire and analyze the signal and present the resultsto the observer. The filters were designed starting with simulation, implementa-tion on the prototype board, culminating in the design of a printed circuit board(PCB) and packaging. The complete software was written in PythonTMusing sev-eral relevant libraries for data processing. A text-based user interface was createdto enable easy user interaction. The results are graphically displayed in real-time. Ex-situ tests were done with two volunteers while in-situ test was done onone subject. The data from the in-situ tests showed "good signal quality" in a"noisy" environment concurring with the design specifications. To motivate theimportance of calibration, two calibration paradigms were used during ex-situtests, where one paradigm records only normal blinks while the other records longblinks and the results showed differences in detection and error rates. The obser-vations made from performance tests at various levels gave "satisfactory results"and proved the usefulness of the system for experimental purposes in-situ.
6
Taylor-Wiedeman, Jean. "Analysis of human cytomegalovirus in the healthy human carrier." Thesis, Open University, 1992. http://oro.open.ac.uk/57400/.
Full textAbstract:
Much circumstantial evidence has pointed to peripheral blood leukocytes as one site of persistence of Human Cytomegalovirus (HCMV) in healthy carriers. However, the exact population of peripheral blood cells that carry HCMV and to what extent they express HCMV gene products in not known. I have examined the sites of HCMV persistence in the peripheral blood of healthy carriers. Analysis of pure cell populations by the use of the polymerase chain reaction (PCR), sensitive to between 1 and 10 copies of the HCMV genome, showed that the predominant site of persistence was the monocyte. In addition, analysis of healthy seronegative subjects revealed that a significant number (30%) also harbored HCMV. Finally, study of granulocytes demonstrated no evidence of persistent HCMV. Expression of HCMV during persistence was also analyzed, by using reverse transcription PCR (RT-PCR) with a sensitivity of between 1 and 100 infected fibroblasts. RNA from monocytes showed no evidence of polyadenylated immediate early (IE) or late transcripts. In contrast, in vitro differentiated monocyte-derived macrophages (MDM) did show evidence of HCMV gene expression with the class of HCMV genes expressed dependent on the method of differentiation. MDM treated with hydrocortisone (HC) and phorbol 12-myristate 13-acetate, expressed only lEI, but not IE2, glycoprotein B (gB) or phosphoprotein 28 (pp28) transcripts. Whereas, MDM treated with granulocyte-macrophage colony stimulating factor and HC expressed lEI, IE2 and gB, but not pp28 transcripts. In both cases, cocultivation experiments did not show plaques. Therefore, in the healthy carrier, persistence of HCMV in monocytes is independent of HCMV lytic gene expression, but in vitro differentiation of monocytes to MDM induced endogenous HCMV transcription consistent with the known permissivity of in vivo differentiated macrophages to HCMV infection.
7
Sekiguchi, Kazumasa. "Analysis of human mitochondrial DNA heteroplasmy for human identification." Kyoto University, 2004. http://hdl.handle.net/2433/148349.
Full text
8
Kühnle, Tim. "Quantitative Analysis of Human Chronotypes." Diss., lmu, 2006. http://nbn-resolving.de/urn:nbn:de:bvb:19-51686.
Full text
9
Denis, Emmanuelle. "Analysis of chimeric human hexosaminidases." Thesis, McGill University, 2000. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=30814.
Full textAbstract:
The major beta-hexosaminidase isozymes in humans are Hex A (deficient in Tay-Sachs disease, TSD), an alphabeta heterodimer and Hex B (deficient in Sandhoff disease) a betabeta homodimer. Hex S, the alphaalpha homodimer is physiologically unstable. Mature alpha and beta subunits share 60% sequence identity. The beta subunit active site hydrolyzes neutral substrates. The alpha subunit active site hydrolyzes neutral (4MUG) and charged substrates (4MUGS, GM2 ganglioside). Only Hex A hydrolyzes the natural substrate, GM2 ganglioside, in the presence of the GM2 activator protein (AP).We investigated regions of the alpha and beta subunits involved in AP binding, subunit dimerization, and substrate specificity. We constructed four chimeric cDNAs: alpha1--259beta292--544 , alpha1--118beta152--544, beta 1--418alpha387--529, and beta1--151 alpha119--259beta292--544 (subscripts refer to amino acid residues). Chimeric cDNAs were expressed in a TSD neuroglial cell line, which produces no endogenous alpha subunits. The chimeric isozymes were chromatofocused and assayed for hydrolysis of (a) 4MUG, (b) 4MUGS and (c) GM2 ganglioside.
Transfection of the cDNA constructs lead to expression of homodimeric and heterodimeric chimeric proteins, albeit at lower yields than transfection of wild alpha-cDNA. All of the chimeric proteins hydrolyzed 4MUG but none were active towards 4MUGS or GM2 ganglioside. These results suggest that (a) all constructs contained sufficient information to form both heterodimeric and homodimeric chimeric proteins, (b) the chimeras lacked the alpha-subunit sequence necessary for the hydrolysis of charged substrates.
10
Dankers, Lea Marie. "Physical analysis of human hair." Diss., Rolla, Mo. : University of Missouri-Rolla, 2007. http://scholarsmine.mst.edu/thesis/pdf/Dankers1_09007dcc8054f11e.pdf.
Full textAbstract:
Thesis (M.S.)--University of Missouri--Rolla, 2007.Vita. The entire thesis text is included in file. Title from title screen of thesis/dissertation PDF file (viewed August 5, 2008) Includes bibliographical references (p. 83-85).
11
Chan, Chee Seng. "Fuzzy qualitative human motion analysis." Thesis, University of Portsmouth, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.494009.
Full textAbstract:
Human motion analysis is a very important task for computer vision with a spectrum of potential applications. This thesis presents a novel approach to the problem of human motion understanding. The main contribution of the thesis is that fuzzy qualitative description has been developed for studying human motion from image sequences.
12
Hong, Jie. "Human gait identification and analysis." Thesis, Brunel University, 2012. http://bura.brunel.ac.uk/handle/2438/7115.
Full textAbstract:
Human gait identification has become an active area of research due to increased security requirements. Human gait identification is a potential new tool for identifying individuals beyond traditional methods. The emergence of motion capture techniques provided a chance of high accuracy in identification because completely recorded gait information can be recorded compared with security cameras. The aim of this research was to build a practical method of gait identification and investigate the individual characteristics of gait. For this purpose, a gait identification approach was proposed, identification results were compared by different methods, and several studies about the individual characteristics of gait were performed. This research included the following: (1) a novel, effective set of gait features were proposed; (2) gait signatures were extracted by three different methods: statistical method, principal component analysis, and Fourier expansion method; (3) gait identification results were compared by these different methods; (4) two indicators were proposed to evaluate gait features for identification; (5) novel and clear definitions of gait phases and gait cycle were proposed; (6) gait features were investigated by gait phases; (7) principal component analysis and the fixing root method were used to elucidate which features were used to represent gait and why; (8) gait similarity was investigated; (9) gait attractiveness was investigated. This research proposed an efficient framework for identifying individuals from gait via a novel feature set based on 3D motion capture data. A novel evaluating method of gait signatures for identification was proposed. Three different gait signature extraction methods were applied and compared. The average identification rate was over 93%, with the best result close to 100%. This research also proposed a novel dividing method of gait phases, and the different appearances of gait features in eight gait phases were investigated. This research identified the similarities and asymmetric appearances between left body movement and right body movement in gait based on the proposed gait phase dividing method. This research also initiated an analysing method for gait features extraction by the fixing root method. A prediction model of gait attractiveness was built with reasonable accuracy by principal component analysis and linear regression of natural logarithm of parameters. A systematic relationship was observed between the motions of individual markers and the attractiveness ratings. The lower legs and feet were extracted as features of attractiveness by the fixing root method. As an extension of gait research, human seated motion was also investigated.
13
Gezgin, Erkin Alizade Rasim. "Biokinematic analysis of human arm." [s.l.]: [s.n.], 2006. http://library.iyte.edu.tr/tezler/master/makinamuh/T000547.pdf.
Full textAbstract:
Thesis (Master)--İzmir Institute of Technology, İzmir, 2006.Keywords: Biokinematic analysis, quaternionlar, structural groups, mechanism theory,robot manipulators. Includes bibliographical references (leaves 78-85).
14
Everding, Vanessa Quigley. "Stability Analysis of Human Walking." Case Western Reserve University School of Graduate Studies / OhioLINK, 2009. http://rave.ohiolink.edu/etdc/view?acc_num=case1232680311.
Full text
15
Meglan, Dwight Alan. "Enhanced analysis of human locomotion." The Ohio State University, 1991. http://rave.ohiolink.edu/etdc/view?acc_num=osu1239984087.
Full text
16
Krulíková, Dagmar. "Human Resources Information System Analysis." Master's thesis, Vysoká škola ekonomická v Praze, 2007. http://www.nusl.cz/ntk/nusl-3859.
Full textAbstract:
One of the biggest and prolonged capital assets of society is investment in staff. If they are managed in the right way, these investments can be the source of innovation and growth, competitive advantage and previsions of leading position in the market. Viz.[7] This Diploma thesis is aimed on the analyses of the human resources management, structure and demands on the personal information system, which solves this area as a whole. Described systems and solutions are generalization of the author's theoretical and practical experiences with particular human resources information system. There are defined the demands on common concept of HR IS. In this diploma thesis you can find the description
17
Outten, Alan Gerard. "Analysis of human muscle activity." Thesis, Imperial College London, 1997. http://hdl.handle.net/10044/1/7958.
Full text
18
Wong, Zilla Yin Har. "Molecular analysis of human minisatellites." Thesis, University of Leicester, 1990. http://hdl.handle.net/2381/34372.
Full textAbstract:
Tandem-repetitive hypervariable minisatellites detected in a DNA fingerprint provide highly informative genetic markers. To identify and localize specific loci represented in a DNA fingerprint, it is necessary to clone individual minisatellites. This thesis is concerned with the characterization of single locus minisatellite probes cloned from DNA fingerprints. Seven single locus human minisatellite probes have been cloned by screening ? libraries with DNA fingerprint probes 33.6 and 33.15. Each locus consists of a minisatellite, with repeat units ranging in length from 9 to 47 base pairs depending on the locus. These autosomal loci are amongst the most variable loci characterized to date. The heterozygosity values of D1S7, D1S8, D5S43, D7S21, D7S22 and D12S11 range from 85% to >99%. Clustering of minisatellites was initially detected at the D12S11 locus. This observation led to the subsequent discovery of minisatellites showing close physical linkage as well as a tendency for minisatellites to be localized in proterminal chromosomal regions. An association of a minisatellite with a dispersed repetitive element was identified when studying the organization of cloned D7S22. This phenomenon was later found to be common amongst minisatellites. Pedigree analysis revealed a high level of instability of the locus detected by D1S7. This manifestation of detectable mutant alleles demonstrated the feasibility of direct estimation of mutation rates at minisatellite loci. The hypervariability of loci detected by minisatellites and their sensitivity in blot hybridizations make minisatellites a powerful tool in genetic analysis. These probes have already proved instrumental in many genetic and clinical studies. The high degree of individual specificity and the relatively simple banding pattern generated make these probes invaluable in forensic medicine. D1S7 and D7S21 were used in the first example of DNA-based identification in a rape and murder enquiry. One minisatellite probe was found to detect two loci, DNF21S1 and DNF21S2, on chromosomes 6 and 16 respectively. The 39 base pair repeat unit of this minisatellite is itself repetitive. The heterozygosity values of DNF21S1 and DNF21S2 are 61% and 16% respectively. Genomic mapping and sequence analyses revealed close similarity between these loci. Human population and pedigree studies showed that some individuals carry two alleles at DNF21S2, some carry one allele, some carry a duplicated allele while some are devoid of this locus. A model of duplication of a large proterminal segment of chromosome 6 DNA containing a minisatellite and transposition into an interstitial region of chromosome 16 in some human individuals is suggested. This is, to my knowledge, the first report of a human DNA polymorphism arising via transposition of DNA. The duplication unit on chromosome 16 is large (>15 kb) and has inserted into a member of a target site family present in 5-10 copies per genome. This sequence family represents a novel class of human repetitive DNA.
19
Belz, Steven Mark. "An On-Road Investigation of Commercial Motor Vehicle Operators and Self-Rating of Alertness and Temporal Separation as Indicators of Driver Fatigue." Diss., Virginia Tech, 2000. http://hdl.handle.net/10919/29589.
Full textAbstract:
This on-road field investigation employed, for the first time, a completely automated, trigger-based data collection system capable of evaluating driver performance in an extended duration real-world commercial motor vehicle environment. The complexities associated with the development of the system, both technological and logistical and the necessary modifications to the plan of research are presented herein
This study, performed in conjunction with an on-going three year contract with the Federal Highway Administration, examined the use of self-rating of alertness and temporal separation (minimum time-to-collision, minimum headway, and mean headway) as indicators of driver fatigue. Without exception, the regression analyses for both the self-rating of alertness and temporal separation yielded models low in predictive ability; neither metric was found to be a valid indicator of driver fatigue. Various reasons for the failure of self-rating of fatigue as a valid measure are discussed. Dispersion in the data, likely due to extraneous (non-fatigue related) factors (e.g., other drivers) are credited with reducing the sensitivity of the temporal separation indicators.
Overall fatigue levels for all temporal separation incidents (those with a time-to-collision equal to or less than four seconds) were found to be significantly higher than for those randomly triggered incidents. On this basis, it is surmised that temporal separation may be a sensitive indicator for time-to-collision values greater than the 4-second criterion employed in this study.
Two unexpected relationships in the data are also discussed. A "wall" effect was found to exist for minimum time-to-collision values at 1.9 seconds. That is, none of the participants who participated in this research effort exhibited following behaviors with less than a 1.9-second time-to-collision criterion. In addition, based upon the data collected for this research, anecdotal evidence suggests that commercial motor vehicle operators do not appear to follow the standard progression of events associated with the onset of fatigue.Ph. D.
20
El-Ladan, Sulaim. "Human entropy (HENT) - a new approach to human reliability analysis." Thesis, University of Strathclyde, 2013. http://oleg.lib.strath.ac.uk:80/R/?func=dbin-jump-full&object_id=18990.
Full text
21
Keet, Andre. "Human rights education or human rights in education a conceptual analysis /." Pretoria : [s.n.], 2006. http://upetd.up.ac.za/thesis/available/etd-06192007-130614/.
Full text
22
Huan, Mengyuan. "Can Human Capital be Tracked? An Analysis of Human Resource Disclosures." Thesis, Université d'Ottawa / University of Ottawa, 2016. http://hdl.handle.net/10393/35532.
Full textAbstract:
This thesis presents a new methodology for measuring and reporting the value of human capital (HC). Building on prior research in strategic HC management and related fields, a disclosure-based HC index, which contains both HC proxies and disclosures scores, is built based on information collected from the annual reports and other stakeholder reports of “the best companies to work for” survey (“Universum” 2010).
This thesis examines the importance of the degree of HC disclosure and its correlation with company “Universum” ranks and tests whether higher employee benefits and welfare are positively related to HC information disclosed in the issued reports. Furthermore, it investigates whether higher levels of financial and non-financial HC information disclosure are associated with better firm performance and tests whether the positive relationship between human capital proxies and firm performance (concluded by resource-based theory and strategic HRM) is still valid during the crisis years (2008-2010). Regression results indicate that human capital information disclosed in previous years has a weak effect on company’s Universum rank and no influence on firm performance. Moreover, the commonly used employee incentive-based management methods may no longer be effective during the economic crisis years. Investing in training during the financial crisis period is critical for better firm performance. More research is needed in the future to examine the role of human capital in firm performance and how it should be measured, managed and governed in modern corporations.
23
Hazell, Laurence Paul. "Rule analysis and social analysis." Thesis, Durham University, 1986. http://etheses.dur.ac.uk/6883/.
Full textAbstract:
This thesis investigates the use of rules in the analysis of language mastery and human action, which are both viewed as social phenomena. The investigation is conducted through an examination of two analyses of the use of language in everyday social life and documents how each formulates a different understanding of rule-following in explaining linguistic and social action. The analyses in question are ‘Speech Act Theory' and 'Ethnomethodology'. The principal idea of speech act theory is that social action is rule-governed, and the theory attempts to explain the possibility of meaningful social interaction on that basis. The rigidities imposed by the notion of rule-governance frustrate that aim. The thesis then turns to an examination of ethnomethodology and conversation analysis and contrasts the notion of rule-orientation developed by that perspective. From that examination it becomes clear that what is on offer is not just a greater flexibility in the use of rules, but a restructuring of the concept of analysis itself. It is argued that re-structuring amounts to a reflexive conception of analysis. Its meaning and implications are enlarged upon through a close scrutiny of the later philosophy of Wittgenstein, particularly his concern with the nature of rule-following in his ‘Philosophical Investigations'. The thesis argues that his concern with rules was motivated by his insight that their use as ‘explanations’ of action said as much about the formulater of the rule as the activities the rules were held to formulate. The thesis concludes by outlining the meaning of this analytic reflexivity for social scientific findings.
24
Kepenekci, Burcu. "Human Activity Recognition By Gait Analysis." Phd thesis, METU, 2011. http://etd.lib.metu.edu.tr/upload/12613089/index.pdf.
Full textAbstract:
This thesis analyzes the human action recognition problem. Human actions are modeled as a time evolving temporal texture. Gabor filters, which are proved to be a robust 2D texture representation tool by detecting spatial points with high variation, is extended to 3D domain to capture motion texture features. A well known filtering algorithm and a recent unsupervised clustering algorithm, the Genetic Chromodynamics, are combined to select salient spatio-temporal features of the temporal texture and to segment the activity sequence into temporal texture primitives. Each activity sequence is represented as a composition of temporal texture primitives with its salient spatio-temporal features, which are also the symbols of our codebook. To overcome temporal variation between different performances of the same action, a Profile Hidden Markov Model is applied with Viterbi Path Counting (ensemble training). Not only parameters and structure but also codebook is learned during training.
25
Dubé, Marie-Pierre. "New approaches in human genetic analysis." Thesis, McGill University, 1999. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=36581.
Full textAbstract:
The present thesis covers two aspects of statistical analysis applied to the genetics of human diseases. First, the significance of LOD-score results for the confirmation of linkage is addressed, with special emphasis on small pedigrees. A new analytical approach is presented for the linkage analysis of heterogenetic traits, using hereditary spastic paraplegia as a model, a disease well suited for the analyses. The critical significance values for confirmation of linkage are evaluated using Bayesian statistics, and empirical P-values for LOD score results are calculated using computer simulation methods. The presented analytical approach resulted in conclusive linkage analyses on small to medium-size families, under the restrictions of genetic heterogeneity.The second part addresses linkage-disequilibrium based fine mapping in the French Canadian population. The performance of five linkage-disequilibrium based fine-mapping methods is evaluated using French Canadian chromosomes with one of three diseases found in this population: oculopharyngeal muscular dystrophy (OPMD), hidrotic ectodermal dysplasia (HED), and sensorimotor polyneuropathy with or without agenesis of the corpus callosum (ACCPN). The gene for OPMD was recently mapped and cloned, allowing us to evaluate the performance of the methods with the OPMD results, and to make predictions about the ACCPN and HED putative gene positions. In addition, a new approach to linkage-disequilibrium based fine mapping is presented using FrenchCanadian ascending genealogies. The method involves two steps. First, the likely founding couple of a mutation-bearing chromosome is identified using a computerised randomisation statistic. Then, using a delete-d jackknife resampling scheme, the distribution of gene mapping estimates is calculated from the count of ancestral recombinants and ancestral meioses joining the identified founding couple to the disease gene carriers. Gene mapping estimates are calculated from each marker individually, and confidence intervals of the estimates are derived from the jackknife distributions. The method, when applied to French Canadian families with OPMD, successfully confirmed the localisation of PABP2 responsible for OPMD and performed better than other linkage disequilibrium-based mapping models.
26
Cordeiro, Paulo. "Human hexosaminidases : databases and modelling analysis." Thesis, McGill University, 2000. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=31211.
Full textAbstract:
The GM2 gangliosidoses are a group of recessive disorders, which lead to the accumulation of GM2 ganglioside in neuronal cells. The genes responsible for these disorders are HEXA (Tay-Sachs disease and variants), HEXB (Sandhoff disease and variants) and GM2A (AB variant of GM2 gangliosidosis). We have established three relational locus-specific databases recording allelic variation at the HEXA, HEXB and GM2A genes, and these can be accessed through the G M2 Gangliosidoses home page (http://data.mch.mcgill.ca/gm2-gangliosidoses/). The purpose of these databases is to collect and distribute information on mutations in the genes responsible for GM2 gangliosidosis. These databases are available online for users to search and retrieve information about specific mutations either by mutation, phenotype or author(s). In addition, submission forms are available for the addition of new mutations to the databases.In order to provide information concerning the effects of mutations on the manifestations of disease, we proceeded to model on the theoretical model of the alpha subunit a few missense mutations. (Abstract shortened by UMI.)
27
López, Méndez Adolfo. "Articulated models for human motion analysis." Doctoral thesis, Universitat Politècnica de Catalunya, 2012. http://hdl.handle.net/10803/112124.
Full textAbstract:
Human motion analysis is as a broad area of computer vision that has strongly attracted the interest of researchers in the last decades. Motion analysis covers topics such as human motion tracking and estimation, action and behavior recognition or segmentation of human motion. All these fields are challenging due to different reasons, but mostly because of viewing perspectives, clutter and the imprecise semantics of actions and human motion.
The computer vision community has addressed human motion analysis from several perspectives. Earlier approaches often relied on articulated human body models represented in the three-dimensional world. However, due to the traditionally high difficulty and cost of estimating such an articulated structure from video, research has focus on the development of human motion analysis approaches relying on low-level features. Although obtaining impressive results in several tasks, low-level features are typically conditioned by appearance and viewpoint, thus making difficult their application on different scenarios. Nonetheless, the increase in computational power, the massive availability of data and the irruption of consumer-depth cameras is changing the scenario, and with that change human motion analysis through articulated models can be reconsidered.
Analyzing and understanding of human motion through 3-dimensional information is still a crucial issue in order to obtain richer models of dynamics and behavior. In that sense, articulated models of the human body offer a compact and view-invariant representation of motion that can be used to leverage motion analysis. In this dissertation, we present several approaches for motion analysis. In particular, we address the problem of pose inference, action recognition and temporal clustering of human motion. Articulated models are the leitmotiv in all the presented approaches. Firstly, we address pose inference by formulating a layered analysis-by-synthesis framework where models are used to generate hypothesis that are matched against video. Based on the same articulated representation upon which models are built, we propose an action recognition framework. Actions are seen as time-series observed through the articulated model and generated by underlying dynamical systems that we hypothesize that are generating the time-series. Such an hypothesis is used in order to develop recognition methods based on time-delay embeddings, which are analysis tools that do not make assumptions on the form of the form of the underlying dynamical system. Finally, we propose a method to cluster human motion sequences into distinct behaviors, without a priori knowledge of the number of actions in the sequence. Our approach relies on the articulated model representation in order to learn a distance metric from pose data. This metric aims at capturing semantics from labeled data in order to cluster unseen motion sequences into meaningful behaviors. The proposed approaches are evaluated using publicly available datasets in order to objectively measure our contributions.L’anàlisi del moviment humà es una area de visió per computador que, en les últimes dècades, ha atret l'interès de la comunitat científica. L’anàlisi de moviment inclou temes com el seguiment del cos humà, el reconeixement d'accions i patrons de comportament, o la segmentació del moviment humà. Tots aquests camps suposen un repte a causa de diferents raons, però especialment a la perspectiva de captura de les escenes a analitzar i també a l’absència d'una semàntica precisa associada a les accions i el moviment humà. La comunitat de visió per computador ha abordat l’anàlisi del moviment humà des de diverses perspectives. Els primers enfocaments es basen en models articulats del cos humà. Aquests models representen el cos com una estructura esqueletal tridimensional. No obstant, a causa de la dificultat i el cost computacional de l’estimació d'aquesta estructura articulada a partir de vídeo, la investigació s'ha anat enfocant, en els últims anys, cap a l’anàlisi de moviment humà basat en característiques de baix nivell. Malgrat obtenir resultats impressionants en diverses tasques, les característiques de baix nivell estan normalment condicionades per l’aparença i punt de vista, cosa que fa difícil la seva aplicació en diferents escenaris. Avui dia, l'augment de la potència de càlcul, la disponibilitat massiva de dades i la irrupció de les càmares de profunditat de baix cost han proporcionat un escenari que permet reconsiderar l’anàlisi de moviment humà a través de models articulats. L'anàlisi i comprensió del moviment humà a través de la informació tridimensional segueix sent un enfocament crucial per obtenir millors models dinàmics al voltant del moviment del cos humà. Per això, els models articulats del cos humà, que ofereixen una representació compacta i invariant al punt de vista de la captura, són una eina per potenciar l'anàlisi de moviment. En aquesta tesi, es presenten diversos enfocaments per a l'anàlisi de moviment. En particular, s'aborda el problema de l'estimació de pose, el reconeixement d'accions i el clustering temporal del moviment humà. Els models articulats són el leitmotiv en tots els plantejaments presentats. En primer lloc, plantegem l’estimació de pose mitjançant la formulació d'un mètode jeràrquic d'anàlisi per síntesi en que els models s'utilitzen per generar hipòtesis que es contrasten amb vídeo. Fent servir la mateixa representació articulada del cos humà, es proposa una formulació del moviment humà per al reconeixement d'accions. La nostra hipòtesi és que les accions formen un conjunt de sistemes dinàmics subjacents que generen observacions en forma de sèries temporals. Aquestes sèries temporals són observades a través del model articulat. Aquesta hipòtesi s'utilitza amb la finalitat de desenvolupar mètodes de reconeixement basats en time-delay embeddings, una eina d’anàlisi de sèries temporals que no fa suposicions sobre la forma del sistema dinàmic subjacent. Finalment, es proposa un mètode per segmentar seqüències de moviment del cos humà en diferents comportaments o accions, sense necessitar un coneixement a priori del nombre d'accions en la seqüència. El nostre enfocament utilitza els models articulats del cos humà per aprendre una distància mètrica. Aquesta mètrica té com a objectiu capturar la semàntica implícita de les anotacions que es puguin trobar en altres bases de dades que continguin seqüències de moviment. Amb la finalitat de mesurar objectivament les nostres contribucions, els mètodes proposats són avaluats utilitzant bases de dades publiques.
28
Suau, Cuadros Xavier. "Human body analysis using depth data." Doctoral thesis, Universitat Politècnica de Catalunya, 2013. http://hdl.handle.net/10803/134801.
Full textAbstract:
Human body analysis is one of the broadest areas within the computer vision field. Researchers have put a strong effort in the human body analysis area, specially over the last decade, due to the technological improvements in both video cameras and processing power. Human body analysis covers topics such as person detection and segmentation, human motion tracking or action and behavior recognition. Even if human beings perform all these tasks naturally, they build-up a challenging problem from a computer vision point of view. Adverse situations such as viewing perspective, clutter and occlusions, lighting conditions or variability of behavior amongst persons may turn human body analysis into an arduous task.
In the computer vision field, the evolution of research works is usually tightly related to the technological progress of camera sensors and computer processing power. Traditional human body analysis methods are based on color cameras. Thus, the information is extracted from the raw color data, strongly limiting the proposals. An interesting quality leap was achieved by introducing the multiview concept. That is to say, having multiple color cameras recording a single scene at the same time. With multiview approaches, 3D information is available by means of stereo matching algorithms. The fact of having 3D information is a key aspect in human motion analysis, since the human body moves in a three-dimensional space. Thus, problems such as occlusion and clutter may be overcome with 3D information.
The appearance of commercial depth cameras has supposed a second leap in the human body analysis field. While traditional multiview approaches required a cumbersome and expensive setup, as well as a fine camera calibration; novel depth cameras directly provide 3D information with a single camera sensor. Furthermore, depth cameras may be rapidly installed in a wide range of situations, enlarging the range of applications with respect to multiview approaches. Moreover, since depth cameras are based on infra-red light, they do not suffer from illumination variations.
In this thesis, we focus on the study of depth data applied to the human body analysis problem. We propose novel ways of describing depth data through specific descriptors, so that they emphasize helpful characteristics of the scene for further body analysis. These descriptors exploit the special 3D structure of depth data to outperform generalist 3D descriptors or color based ones. We also study the problem of person detection, proposing a highly robust and fast method to detect heads. Such method is extended to a hand tracker, which is used throughout the thesis as a helpful tool to enable further research. In the remainder of this dissertation, we focus on the hand analysis problem as a subarea of human body analysis. Given the recent appearance of depth cameras, there is a lack of public datasets. We contribute with a dataset for hand gesture recognition and fingertip localization using depth data. This dataset acts as a starting point of two proposals for hand gesture recognition and fingertip localization based on classification techniques. In these methods, we also exploit the above mentioned descriptor proposals to finely adapt to the nature of depth data.%, and enhance the results in front of traditional color-based methods.L’anàlisi del cos humà és una de les àrees més àmplies del camp de la visió per computador. Els investigadors han posat un gran esforç en el camp de l’anàlisi del cos humà, sobretot durant la darrera dècada, degut als grans avenços tecnològics, tant pel que fa a les càmeres com a la potencia de càlcul. L’anàlisi del cos humà engloba varis temes com la detecció i segmentació de persones, el seguiment del moviment del cos, o el reconeixement d'accions. Tot i que els essers humans duen a terme aquestes tasques d'una manera natural, es converteixen en un difícil problema quan s'ataca des de l’òptica de la visió per computador. Situacions adverses, com poden ser la perspectiva del punt de vista, les oclusions, les condicions d’il•luminació o la variabilitat de comportament entre persones, converteixen l’anàlisi del cos humà en una tasca complicada. En el camp de la visió per computador, l’evolució de la recerca va sovint lligada al progrés tecnològic, tant dels sensors com de la potencia de càlcul dels ordinadors. Els mètodes tradicionals d’anàlisi del cos humà estan basats en càmeres de color. Això limita molt els enfocaments, ja que la informació disponible prové únicament de les dades de color. El concepte multivista va suposar salt de qualitat important. En els enfocaments multivista es tenen múltiples càmeres gravant una mateixa escena simultàniament, permetent utilitzar informació 3D gràcies a algorismes de combinació estèreo. El fet de disposar d’informació 3D es un punt clau, ja que el cos humà es mou en un espai tri-dimensional. Això doncs, problemes com les oclusions es poden apaivagar si es disposa de informació 3D. L’aparició de les càmeres de profunditat comercials ha suposat un segon salt en el camp de l’anàlisi del cos humà. Mentre els mètodes multivista tradicionals requereixen un muntatge pesat i car, i una celebració precisa de totes les càmeres; les noves càmeres de profunditat ofereixen informació 3D de forma directa amb un sol sensor. Aquestes càmeres es poden instal•lar ràpidament en una gran varietat d'entorns, ampliant enormement l'espectre d'aplicacions, que era molt reduït amb enfocaments multivista. A més a més, com que les càmeres de profunditat estan basades en llum infraroja, no pateixen problemes relacionats amb canvis d’il•luminació. En aquesta tesi, ens centrem en l'estudi de la informació que ofereixen les càmeres de profunditat, i la seva aplicació al problema d’anàlisi del cos humà. Proposem noves vies per descriure les dades de profunditat mitjançant descriptors específics, capaços d'emfatitzar característiques de l'escena que seran útils de cara a una posterior anàlisi del cos humà. Aquests descriptors exploten l'estructura 3D de les dades de profunditat per superar descriptors 3D generalistes o basats en color. També estudiem el problema de detecció de persones, proposant un mètode per detectar caps robust i ràpid. Ampliem aquest mètode per obtenir un algorisme de seguiment de mans que ha estat utilitzat al llarg de la tesi. En la part final del document, ens centrem en l’anàlisi de les mans com a subàrea de l’anàlisi del cos humà. Degut a la recent aparició de les càmeres de profunditat, hi ha una manca de bases de dades públiques. Contribuïm amb una base de dades pensada per la localització de dits i el reconeixement de gestos utilitzant dades de profunditat. Aquesta base de dades és el punt de partida de dues contribucions sobre localització de dits i reconeixement de gestos basades en tècniques de classificació. En aquests mètodes, també explotem les ja mencionades propostes de descriptors per millor adaptar-nos a la naturalesa de les dades de profunditat.
29
Dubé, Marie-Pierre. "New approaches in human genetic analysis." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape2/PQDD_0030/NQ64551.pdf.
Full text
30
Holmberg, Björn. "Towards markerless analysis of human motion /." Uppsala : Department of Information Technology, Uppsala University, 2005. http://www.it.uu.se/research/publications/lic/2005-011/.
Full text
31
Nemeth, Andrea Hilary. "Molecular analysis of human proximal Xp." Thesis, University of Oxford, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.282128.
Full text
32
Waddington, Jonathan. "Human optokinetic nystagmus : a stochastic analysis." Thesis, University of Plymouth, 2012. http://hdl.handle.net/10026.1/1040.
Full textAbstract:
Optokinetic nystagmus (OKN) is a fundamental gaze-stabilising response in which eye movements attempt to compensate for the retinal slip caused by self-motion. The OKN response consists of a slow following movement made in the direction of stimulus motion interrupted by fast eye movements that are primarily made in the opposite direction. The timing and amplitude of these slow phases and quick phases are notably variable, but this variability is poorly understood. In this study I performed principal component analysis on OKN parameters in order to investigate how the eigenvectors and eigenvalues of the underlying components contribute to the correlation between OKN parameters over time. I found three categories of principal components that could explain the variance within each cycle of OKN, and only parameters from within a single cycle contributed highly to any given component. Differences found in the correlation matrices of OKN parameters appear to reflect changes in the eigenvalues of components, while eigenvectors remain predominantly similar across participants, and trials. I have developed a linear and stochastic model of OKN based on these results and demonstrated that OKN can be described as a 1st order Markov process, with three sources of noise affecting SP velocity, QP triggering, and QP amplitude. I have used this model to make some important predictions about the optokinetic reflex: the transient response of SP velocity, the existence of signal dependent noise in the system, the target position of QPs, and the threshold at which QPs are generated. Finally, I investigate whether the significant variability within OKN may represent adaptive control of explicit and implicit parameters. iii
33
Khan, Amir Ali. "Proteomics analysis of human stem cells." Thesis, University of Leeds, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.493771.
Full textAbstract:
Stem cells have two characteristics that make them unique from any other cell: they can renew themselves indefmitely and they can be differentiated into other cell types. The aim of this investigation was to employ proteomic techniques (2D-PAGE/mass spectrometry) to compare protein expression profiles between two embryonic cell lines (HI and Hues1) and between Huesl and a multipotent cell line (MSC).
34
Pleat, Jonathon Michael. "A proteomic analysis of human scarring." Thesis, University of Oxford, 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.534204.
Full text
35
Robinson, R. A. "Genetic analysis of human absence epilepsy." Thesis, University College London (University of London), 2010. http://discovery.ucl.ac.uk/20469/.
Full textAbstract:
Idiopathic Mendelian epilepsies have been typically identified as channelopathies. Evidence suggests that mutations in genes encoding GABAA receptors, GABAB receptors or voltage-dependent calcium channels (VDCCs) may underlie childhood absence epilepsy (CAE), an idiopathic generalised epilepsy with complex inheritance. The aims of this project were: i) Ascertainment of a patient resource ii) Investigation of candidate genes by linkage analysis iii) Mutation analysis by direct sequencing iv) Construction of single nucleotide polymorphism (SNP) based haplotypes in candidate genes v) Intra-familial association analysis using SNP based haplotypes DNA and clinical data were obtained from: 53 nuclear CAE pedigrees; 29 families including individuals with CAE and a broader „absence‟ epilepsy phenotype; 217 parent-child trios; a North American family in which absence epilepsy segregates with episodic ataxia type 2 (EA2) Sixteen calcium channel genes and seven GABAA and two GABAB receptor subunit genes were excluded by linkage analysis. Significant linkage was demonstrated for CACNG3 on chromosome 16p12-p13.1 for both CAE and the broader absence phenotype. Positive linkage was also obtained at the GABRA5, GABRB3, GABRG3 cluster on chromosome 15q11-q13. Non-parametric linkage analysis was significant at both the 16p and 15q loci. Two-locus analysis supported a digenic effect from these two loci. Sequencing of CACNG3 revealed 34 sequence variants, none clearly causal, although bioinformatic analysis provided supportive functional evidence. Association analysis showed significant transmission disequilibrium both for individual single nucleotide polymorphisms (SNPs) and SNP based haplotypes spanning CACNG3. This work has provided genetic evidence that CACNG3 and at least one of the three GABAA receptor genes are susceptibility loci for absence epilepsy. Linkage analysis performed in the family with absence epilepsy and EA2 was suggestive that the VDCC CACNA1A was the causative gene. This was subsequently confirmed by sequence analysis in collaboration with the Institute of Neurology, UCL. This is the first reported family in which a CACNA1A mutation that impairs calcium channel function cosegregates with typical absence seizures and 3Hz spike-wave discharges on EEG.
36
Burns, Thomas Ray. "Acquisition and analysis of human brainwaves." Honors in the Major Thesis, University of Central Florida, 1994. http://digital.library.ucf.edu/cdm/ref/collection/ETH/id/125.
Full textAbstract:
This item is only available in print in the UCF Libraries. If this is your Honors Thesis, you can help us make it available online for use by researchers around the world by following the instructions on the distribution consent form at http://library.ucf.edu/Systems/DigitalInitiatives/DigitalCollections/InternetDistributionConsentAgreementForm.pdf You may also contact the project coordinator, Kerri Bottorff, at kerri.bottorff@ucf.edu for more information.Bachelors
Engineering
Electrical Engineering
37
Irvine, Alan David. "Mutation analysis in human keratin diseases." Thesis, Queen's University Belfast, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.268237.
Full text
38
McSharry, Brian. "Analysis of human cytomegalovirus gene function." Thesis, Cardiff University, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.400342.
Full text
39
Brookes, Anthony Joseph. "Molecular analysis of human collagen genes." Thesis, University College London (University of London), 1988. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.267102.
Full text
40
Tran, Cam Thanh Lucy. "Molecular analysis of human DDAH genes." Thesis, University College London (University of London), 2003. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.408021.
Full text
41
Miguel, Angela Ruth. "Human error analysis for collaborative work." Thesis, University of York, 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.441020.
Full text
42
Chee, Mark. "Analysis of the human cytomegalovirus genome." Thesis, University of Cambridge, 1990. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.357727.
Full text
43
Saw, Wee Hee. "Human thermal experimentation, analysis & control /." free to MU campus, to others for purchase, 2003. http://wwwlib.umi.com/cr/mo/fullcit?p1420926.
Full textAbstract:
Thesis (M.S.)--University of Missouri-Columbia, 2003.Accompany CD-ROM contains complete dissertation in Microsoft Word documents. Typescript. Vita. Includes bibliographical references. Also available on the Internet.
44
Laxminarayan, Parameshvyas. "Exploratory analysis of human sleep data." Worcester, Mass. : Worcester Polytechnic Institute, 2004. http://www.wpi.edu/Pubs/ETD/Available/etd-0119104-120134/.
Full textAbstract:
Thesis (M.S.)--Worcester Polytechnic Institute.Keywords: association rule mining; logistic regression; statistical significance of rules; window-based association rule mining; data mining; sleep data. Includes bibliographical references (leaves 166-167).
45
Neverova, Natalia. "Deep learning for human motion analysis." Thesis, Lyon, 2016. http://www.theses.fr/2016LYSEI029/document.
Full textAbstract:
L'objectif de ce travail est de développer des méthodes avancées d'apprentissage pour l’analyse et l'interprétation automatique du mouvement humain à partir de sources d'information diverses, telles que les images, les vidéos, les cartes de profondeur, les données de type “MoCap” (capture de mouvement), les signaux audio et les données issues de capteurs inertiels. A cet effet, nous proposons plusieurs modèles neuronaux et des algorithmes d’entrainement associés pour l’apprentissage supervisé et semi-supervisé de caractéristiques. Nous proposons des approches de modélisation des dépendances temporelles, et nous montrons leur efficacité sur un ensemble de tâches fondamentales, comprenant la détection, la classification, l’estimation de paramètres et la vérification des utilisateurs (la biométrie). En explorant différentes stratégies de fusion, nous montrons que la fusion des modalités à plusieurs échelles spatiales et temporelles conduit à une augmentation significative des taux de reconnaissance, ce qui permet au modèle de compenser les erreurs des classifieurs individuels et le bruit dans les différents canaux. En outre, la technique proposée assure la robustesse du classifieur face à la perte éventuelle d’un ou de plusieurs canaux. Dans un deuxième temps nous abordons le problème de l’estimation de la posture de la main en présentant une nouvelle méthode de régression à partir d’images de profondeur. Dernièrement, dans le cadre d’un projet séparé (mais lié thématiquement), nous explorons des modèles temporels pour l'authentification automatique des utilisateurs de smartphones à partir de leurs habitudes de tenir, de bouger et de déplacer leurs téléphones. Dans ce contexte, les données sont acquises par des capteurs inertiels embraqués dans les appareils mobilesThe research goal of this work is to develop learning methods advancing automatic analysis and interpreting of human motion from different perspectives and based on various sources of information, such as images, video, depth, mocap data, audio and inertial sensors. For this purpose, we propose a several deep neural models and associated training algorithms for supervised classification and semi-supervised feature learning, as well as modelling of temporal dependencies, and show their efficiency on a set of fundamental tasks, including detection, classification, parameter estimation and user verification. First, we present a method for human action and gesture spotting and classification based on multi-scale and multi-modal deep learning from visual signals (such as video, depth and mocap data). Key to our technique is a training strategy which exploits, first, careful initialization of individual modalities and, second, gradual fusion involving random dropping of separate channels (dubbed ModDrop) for learning cross-modality correlations while preserving uniqueness of each modality-specific representation. Moving forward, from 1 to N mapping to continuous evaluation of gesture parameters, we address the problem of hand pose estimation and present a new method for regression on depth images, based on semi-supervised learning using convolutional deep neural networks, where raw depth data is fused with an intermediate representation in the form of a segmentation of the hand into parts. In separate but related work, we explore convolutional temporal models for human authentication based on their motion patterns. In this project, the data is captured by inertial sensors (such as accelerometers and gyroscopes) built in mobile devices. We propose an optimized shift-invariant dense convolutional mechanism and incorporate the discriminatively-trained dynamic features in a probabilistic generative framework taking into account temporal characteristics. Our results demonstrate, that human kinematics convey important information about user identity and can serve as a valuable component of multi-modal authentication systems
46
Holmes, Andrew Keith. "Systems analysis of human phenylalanine metabolism." Thesis, Imperial College London, 1986. http://hdl.handle.net/10044/1/38037.
Full text
47
Elbayoudi, Abubaker. "Trend analysis for human activities recognition." Thesis, Nottingham Trent University, 2018. http://irep.ntu.ac.uk/id/eprint/33844/.
Full textAbstract:
Smart environments equipped with appropriate sensory devices are used to measure people's activities. These activities represent Activities of Daily Living (ADL) or Activities of Daily Working (ADW). Measuring progressive changes in activities is a subject of research interest. A number of medical conditions and their treatments are associated with progressive changes such as reduced movement over time. The aim of this research is to determine means of inspecting trends in the ADL/ADW to identify progressive changes and predict behavioural abnormalities. The ADL/ADW pattern will change over time and this is a consequence of the individual's condition. Identifying evolving behavioural patterns will help to predict the trend in the ADL/ADW behavioural pattern before any abnormalities are identifed. The data provided for this investigation are from real environments home and office). Additionally, a simulator is developed to generate simulated data for ADLs. To answer the research question identifed in this research, the initial investigation was conducted and a novel Human Behaviour Momentum Indicator (HBMI) is proposed. The HBMI is introduced to identify changes based on activities recorded from a single sensor. To show the effectiveness of the proposed approach, results are compared with Relative Strength Index (RSI). The results show that trends in ADL or ADW can be detected and the direction of the activity's trend is predicted. To represent a holistic report based on a multiple sensors/activities representing progressive changes in the participant's behaviour, a novel Human Behaviour Indicator (HBI) is also proposed. The proposed HBI indicator is constructed as a composite indicator, which will compute progressive changes in behaviour based on the events that are performed during the entire day. The percentage of changes between events is used to compare events and measure the progressive changes. The proposed technique identifies the user's daily behaviour and distinguishes between normal and abnormal behavioural patterns of the ADLs or ADWs. Analysis of the data indicates that the HBI could clearly differentiate between the normal and the abnormal behaviour and give a warning status with a confidence level. Identifying trends in ADLs or ADWs using trend analysis techniques are investigated to interpret the behavioural changes in a suitable format to be understood by the carers or supervisors.
48
Oikonomopoulos, Antonios. "Spatiotemporal visual analysis of human actions." Thesis, Imperial College London, 2010. http://hdl.handle.net/10044/1/5871.
Full textAbstract:
In this dissertation we propose four methods for the recognition of human activities. In all four of them, the representation of the activities is based on spatiotemporal features that are automatically detected at areas where there is a significant amount of independent motion, that is, motion that is due to ongoing activities in the scene. We propose the use of spatiotemporal salient points as features throughout this dissertation. The algorithms presented, however, can be used with any kind of features, as long as the latter are well localized and have a well-defined area of support in space and time. We introduce the utilized spatiotemporal salient points in the first method presented in this dissertation. By extending previous work on spatial saliency, we measure the variations in the information content of pixel neighborhoods both in space and time, and detect the points at the locations and scales for which this information content is locally maximized. In this way, an activity is represented as a collection of spatiotemporal salient points. We propose an iterative linear space-time warping technique in order to align the representations in space and time and propose to use Relevance Vector Machines (RVM) in order to classify each example into an action category. In the second method proposed in this dissertation we propose to enhance the acquired representations of the first method. More specifically, we propose to track each detected point in time, and create representations based on sets of trajectories, where each trajectory expresses how the information engulfed by each salient point evolves over time. In order to deal with imperfect localization of the detected points, we augment the observation model of the tracker with background information, acquired using a fully automatic background estimation algorithm. In this way, the tracker favors solutions that contain a large number of foreground pixels. In addition, we perform experiments where the tracked templates are localized on specific parts of the body, like the hands and the head, and we further augment the tracker’s observation model using a human skin color model. Finally, we use a variant of the Longest Common Subsequence algorithm (LCSS) in order to acquire a similarity measure between the resulting trajectory representations, and RVMs for classification. In the third method that we propose, we assume that neighboring salient points follow a similar motion. This is in contrast to the previous method, where each salient point was tracked independently of its neighbors. More specifically, we propose to extract a novel set of visual descriptors that are based on geometrical properties of three-dimensional piece-wise polynomials. The latter are fitted on the spatiotemporal locations of salient points that fall within local spatiotemporal neighborhoods, and are assumed to follow a similar motion. The extracted descriptors are invariant in translation and scaling in space-time. Coupling the neighborhood dimensions to the scale at which the corresponding spatiotemporal salient points are detected ensures the latter. The descriptors that are extracted across the whole dataset are subsequently clustered in order to create a codebook, which is used in order to represent the overall motion of the subjects within small temporal windows.Finally,we use boosting in order to select the most discriminative of these windows for each class, and RVMs for classification. The fourth and last method addresses the joint problem of localization and recognition of human activities depicted in unsegmented image sequences. Its main contribution is the use of an implicit representation of the spatiotemporal shape of the activity, which relies on the spatiotemporal localization of characteristic ensembles of spatiotemporal features. The latter are localized around automatically detected salient points. Evidence for the spatiotemporal localization of the activity is accumulated in a probabilistic spatiotemporal voting scheme. During training, we use boosting in order to create codebooks of characteristic feature ensembles for each class. Subsequently, we construct class-specific spatiotemporal models, which encode where in space and time each codeword ensemble appears in the training set. During testing, each activated codeword ensemble casts probabilistic votes concerning the spatiotemporal localization of the activity, according to the information stored during training. We use a Mean Shift Mode estimation algorithm in order to extract the most probable hypotheses from each resulting voting space. Each hypothesis corresponds to a spatiotemporal volume which potentially engulfs the activity, and is verified by performing action category classification with an RVM classifier.
49
Holmberg, Björn. "Towards markerless analysis of human motion." Licentiate thesis, Uppsala universitet, Avdelningen för systemteknik, 2005. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-86359.
Full textAbstract:
The topic for this thesis is the analysis of human movement, or more specifically, markerless analysis of human movement from video material. By markerless analysis is meant that the full image material is used as input in contrast with traditional marker systems that only use the positions of marker centers. The basic idea is to use more of the information in the images to improve the analysis. Starting of with the aim of markerless analysis an application is designed that use, to the subject added texture to estimate the position of the knee joint center in real images. The approach show the plausibility of using subject texture for estimation purposes. Another issue that is addressed is how one can generate synthetic image data. Using basic tools of graphics programming a virtual environment used to synthesize data is created. This environment is also used to evaluate some different camera solutions. One method to make three dimensional reconstruction from multiple images of an object is tested using the synthetic data. The method is based on a "brute force" approach and does not show good performance in terms of computing speed. With appropriate representations of the three dimensional objects, mathematical methods might speed up the analysis.
50
Takano, Kuniko. "analysis of human polymorphonuclear leukocyte function." Kyoto University, 2001. http://hdl.handle.net/2433/151463.
Full textAbstract:
主論文1のタイトル「Rapid and prominent upregulation of high-affinity receptor for IgG(FcγRI) by cross-linking of β2 integrins on polymorphonuclear leukocytes(多形核白血球β2インテグリンのクロスリンクによる高親和性IgGレセプター(FcγRI)の速やかかつ顕著な発現増加)」とあり主論文2のタイトル「Demonstration of functionally distinct human polymorphonuclear leukocyte fractions by simultaneous measurement of phagocytosis and oxygen radical generation(貪食能と活性酸素産生能の同時測定に基づくヒト多形核白血球の異なる機能的分画の証明)」とあり
Kyoto University (京都大学)
0048
新制・論文博士
博士(医学)
乙第10574号
論医博第1731号
新制||医||756(附属図書館)
UT51-2001-A766
(主査)教授 中畑 龍俊, 教授 光山 正雄, 教授 内山 卓
学位規則第4条第2項該当