Dissertations / Theses on the topic 'Tracker video analysis'

Submitted by Larissa Vitoria Cardoso Cusielo (larissavitoria@id.uff.br) on 2017-05-22T15:59:28Z No. of bitstreams: 3 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Manoel Coelho da Silva Neto - Dissertação Final.compressed.pdf: 2147671 bytes, checksum: c046094e9eb88ea2c91f4ebc1857ab0e (MD5) Manoel Coelho da Silva Neto - Produto Final.pdf: 4043748 bytes, checksum: ed0f262e5d26eb90ede963337eadcabc (MD5)<br>Rejected by Biblioteca do Aterrado BAVR (bavr@ndc.uff.br), reason: oi on 2017-05-22T16:23:42Z (GMT)<br>Submitted by Larissa Vitoria Cardoso Cusielo (larissavitoria@id.uff.br) on 2017-05-22T17:10:03Z No. of bitstreams: 3 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Manoel Coelho da Silva Neto - Dissertação Final.compressed.pdf: 2147671 bytes, checksum: c046094e9eb88ea2c91f4ebc1857ab0e (MD5) Manoel Coelho da Silva Neto - Produto Final.pdf: 4043748 bytes, checksum: ed0f262e5d26eb90ede963337eadcabc (MD5)<br>Approved for entry into archive by Biblioteca do Aterrado BAVR (bavr@ndc.uff.br) on 2017-08-21T15:45:13Z (GMT) No. of bitstreams: 3 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Manoel Coelho da Silva Neto - Dissertação Final.compressed.pdf: 2147671 bytes, checksum: c046094e9eb88ea2c91f4ebc1857ab0e (MD5) Manoel Coelho da Silva Neto - Produto Final.pdf: 4043748 bytes, checksum: ed0f262e5d26eb90ede963337eadcabc (MD5)<br>Made available in DSpace on 2017-08-21T15:45:13Z (GMT). No. of bitstreams: 3 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Manoel Coelho da Silva Neto - Dissertação Final.compressed.pdf: 2147671 bytes, checksum: c046094e9eb88ea2c91f4ebc1857ab0e (MD5) Manoel Coelho da Silva Neto - Produto Final.pdf: 4043748 bytes, checksum: ed0f262e5d26eb90ede963337eadcabc (MD5)<br>Coordenação de Aperfeiçoamento de Pessoal de Nível Superior<br>Universidade Federal Fluminense. Instituto de Ciências Exatas. Programa de Pós-Graduação em Ensino de Física. Volta Redonda,RJ.<br>Esta dissertação apresenta uma atividade de ensino centrada no aluno para tópicos de cinemática, utilizando Tecnologias de Informação e Comunicação (TICs) e o game Angry Birds como motivador do engajamento do aluno no processo de aprendizagem. Em nosso projeto, conduzido no Colégio Estadual Conde Pereira Carneiro, em Angra dos Reis, RJ, os alunos cumpriram atividades de recuperação escolar em aulas vagas do próprio turno de presença, onde, capturando uma sessão de jogo de Angry Birds em vídeo, posteriormente analisavam os movimentos nele contidos no software Tracker. Com isso, trabalharam-se todos os conceitos fundamentais da cinemática, como posição, deslocamento, velocidade e aceleração, além de tópicos da cinemática, como movimento uniforme, acelerado e de projéteis. Os resultados sugerem que este tipo de atividade é efetiva em promover uma maior aproximação do aluno à disciplina de Física, proporcionando engajamento e estimulando autonomia e independência no aprendizado do estudante, qualidades desejáveis em qualquer metodologia de ensino.<br>This work presents a student-centered teaching activity for teaching kinematics, using Communication and Information Tecnologies, and the game Angry Birds as the motivator for student engagement in the learning process. Our project, conducted at Colégio Estadual Conde Pereira Carneiro, in Angra dos Reis, RJ, consisted of sessions where students captured a playing session of Angry Birds in video, with later analysis of the motion of the birds through the software Tracker. They dealt, thus, with all the fundamental concepts of kinematics, such as position, displacement, velocity and acceleration, as well as with topics specific to kinematics, such as uniform and accelerated motion and projectile motion. The results suggest that this kind of activity promotes a greater closeness to the discipline of Physics, as well as engagement and independence in learning, something highly desirable in teaching and learning.

With the advancement of computer technology, demand for more accurate and intelligent monitoring systems has also risen. The use of computer vision and video analysis range from industrial inspection to surveillance. Object detection and segmentation are the first and fundamental task in the analysis of dynamic scenes. Traditionally, this detection and segmentation are typically done through temporal differencing or statistical modelling methods. One of the most widely used background modeling and segmentation algorithms is the Mixture of Gaussians method developed by Stauffer and Grimson (1999). During the past decade many such algorithms have been developed ranging from parametric to non-parametric algorithms. Many of them utilise pixel intensities to model the background, but some use texture properties such as Local Binary Patterns. These algorithms function quite well under normal environmental conditions and each has its own set of advantages and short comings. However, there are two drawbacks in common. The first is that of the stationary object problem; when moving objects become stationary, they get merged into the background. The second problem is that of light changes; when rapid illumination changes occur in the environment, these background modelling algorithms produce large areas of false positives.These algorithms are capable of adapting to the change, however, the quality of the segmentation is very poor during the adaptation phase. In this thesis, a framework to suppress these false positives is introduced. Image properties such as edges and textures are utilised to reduce the amount of false positives during adaptation phase. The framework is built on the idea of sequential pattern recognition. In any background modelling algorithm, the importance of multiple image features as well as different spatial scales cannot be overlooked. Failure to focus attention on these two factors will result in difficulty to detect and reduce false alarms caused by rapid light change and other conditions. The use of edge features in false alarm suppression is also explored. Edges are somewhat more resistant to environmental changes in video scenes. The assumption here is that regardless of environmental changes, such as that of illumination change, the edges of the objects should remain the same. The edge based approach is tested on several videos containing rapid light changes and shows promising results. Texture is then used to analyse video images and remove false alarm regions. Texture gradient approach and Laws Texture Energy Measures are used to find and remove false positives. It is found that Laws Texture Energy Measure performs better than the gradient approach. The results of using edges, texture and different combination of the two in false positive suppression are also presented in this work. This false positive suppression framework is applied to a smart house senario that uses cameras to model ”virtual sensors” to detect interactions of occupants with devices. Results show the accuracy of virtual sensors compared with the ground truth is improved.

With the advancement of computer technology, demand for more accurate and intelligent monitoring systems has also risen. The use of computer vision and video analysis range from industrial inspection to surveillance. Object detection and segmentation are the first and fundamental task in the analysis of dynamic scenes. Traditionally, this detection and segmentation are typically done through temporal differencing or statistical modelling methods. One of the most widely used background modeling and segmentation algorithms is the Mixture of Gaussians method developed by Stauffer and Grimson (1999). During the past decade many such algorithms have been developed ranging from parametric to non-parametric algorithms. Many of them utilise pixel intensities to model the background, but some use texture properties such as Local Binary Patterns. These algorithms function quite well under normal environmental conditions and each has its own set of advantages and short comings. However, there are two drawbacks in common. The first is that of the stationary object problem; when moving objects become stationary, they get merged into the background. The second problem is that of light changes; when rapid illumination changes occur in the environment, these background modelling algorithms produce large areas of false positives.<br>These algorithms are capable of adapting to the change, however, the quality of the segmentation is very poor during the adaptation phase. In this thesis, a framework to suppress these false positives is introduced. Image properties such as edges and textures are utilised to reduce the amount of false positives during adaptation phase. The framework is built on the idea of sequential pattern recognition. In any background modelling algorithm, the importance of multiple image features as well as different spatial scales cannot be overlooked. Failure to focus attention on these two factors will result in difficulty to detect and reduce false alarms caused by rapid light change and other conditions. The use of edge features in false alarm suppression is also explored. Edges are somewhat more resistant to environmental changes in video scenes. The assumption here is that regardless of environmental changes, such as that of illumination change, the edges of the objects should remain the same. The edge based approach is tested on several videos containing rapid light changes and shows promising results. Texture is then used to analyse video images and remove false alarm regions. Texture gradient approach and Laws Texture Energy Measures are used to find and remove false positives. It is found that Laws Texture Energy Measure performs better than the gradient approach. The results of using edges, texture and different combination of the two in false positive suppression are also presented in this work. This false positive suppression framework is applied to a smart house senario that uses cameras to model ”virtual sensors” to detect interactions of occupants with devices. Results show the accuracy of virtual sensors compared with the ground truth is improved.

While there has always been a tremendous demand for streaming video over Wireless networks, the nature of the application still presents some challenging issues. These applications that transmit coded video sequence data over best-effort networks like the Internet, the application must cope with the changing network behaviour; especially, the source encoder rate should be controlled based on feedback from a channel estimator that explores the network intermittently. The arrival of powerful video compression techniques such as H.264, which advance in networking and telecommunications, opened up a whole new frontier for multimedia communications. The aim of this research is to transmit the H.264 coded video frames in the wireless network with maximum reliability and in a very efficient manner. When the H.264 encoded video sequences are to be transmitted through wireless network, it faces major difficulties in reaching the destination. The characteristics of H.264 video coded sequences are studied fully and their capability of transmitting in wireless networks are examined and a new approach called Optimal Packet Fragmentation (OPF) is framed and the H.264 coded sequences are tested in the wireless simulated environment. This research has three major studies involved in it. First part of the research has the study about Long Range Dependence (LRD) and the ways by which the self-similarity can be estimated. For estimating the LRD a few studies are carried out and Wavelet-based estimator is selected for the research because Wavelets incarcerate both time and frequency features in the data and regularly provides a more affluent picture than the classical Fourier analysis. The Wavelet used to estimate the self-similarity by using the variable called Hurst Parameter. Hurst Parameter tells the researcher about how a data can behave inside the transmitted network. This Hurst Parameter should be calculated for a more reliable transmission in the wireless network. The second part of the research deals with MPEG-4 and H.264 encoder. The study is carried out to prove which encoder is superior to the other. We need to know which encoder can provide excellent Quality of Service (QoS) and reliability. This study proves with the help of Hurst parameter that H.264 is superior to MPEG-4. The third part of the study is the vital part in this research; it deals with the H.264 video coded frames that are segmented into optimal packet size in the MAC Layer for an efficient and more reliable transfer in the wireless network. Finally the H.264 encoded video frames incorporated with the Optimal Packet Fragmentation are tested in the NS-2 wireless simulated network. The research proves the superiority of H.264 video encoder and OPF's master class.

Track stiffness is the one of the most critical parameters of the track structure. Its evaluation is important to assess track quality, component performance, localised faults and optimise maintenance periods and activities. Keeping the track stiffness within acceptable range of values is connected with keeping the railway network in a satisfactorily performing condition, allowing thereby upgrade of its capacity (speed, load, intensity). Current railway standards are changing to define loading and stiffness requirements for improved ballasted and ballastless performance under high speed train traffic. In recent years various techniques have been used to measure track deflection which have been also used to validate numerical models to assess various problems within the railway network. Based on recent introduction of the Video Gauge for its application in the civil engineering industry this project provides the proof of effective applicability of this DIC (Digital image correlation) tool for the accurate assessment of track deflection and the calculation of track stiffness through its effective applicability in various track conditions for assessing the stiffness of various track forms including track irregularities where abrupt change in track stiffness occur such as transition zones and rail joints. Attention is given in validation of numerical modelling of the response of insulated rail joints under the passage of wheel load within the goal to improve track performance adjacent to rail joints and contribute to the sponsoring company s product offering. This project shows a means of improving the rail joint behaviour by using external structural reinforcement, and this is presented through numerical modelling validated by laboratory and field measurements. The structural response of insulated rail joints (IRJs) under the wheel vertical load passage is presented to enhance industry understanding of the effect of critical factors of IRJ response for various IRJ types that was served as a parametric FE model template for commercial studies for product optimisation.

Rail track asset sighting distance must be checked regularly to ensure the continued and safe operation of rolling stock. Methods currently used to check asset line-of-sight involve manual labour or laser systems. Video cameras and computer vision techniques provide one possible route for cheaper, automated systems. Three categories of computer vision method are identified for possible application: two-dimensional object recognition, two-dimensional object tracking and three-dimensional scene recovery. However, presented experimentation shows recognition and tracking methods produce less accurate asset line-of-sight results for increasing asset-camera distance. Regarding three-dimensional scene recovery, evidence is presented suggesting a relationship between image feature and recovered scene information. A novel framework which learns these relationships is proposed. Learnt relationships from recovered image features probabilistically limit the search space of future features, improving efficiency. This framework is applied to several scene recovery methods and is shown (on average) to decrease computation by two-thirds for a possible, small decrease in accuracy of recovered scenes. Asset line-of-sight results computed from recovered three-dimensional terrain data are shown to be more accurate than two-dimensional methods, not effected by increasing asset-camera distance. Finally, the analysis of terrain in terms of effect on asset line-of-sight is considered. Terrain elements, segmented using semantic information, are ranked with a metric combining a minimum line-of-sight blocking distance and the growth required to achieve this minimum distance. Since this ranking measure is relative, it is shown how an approximation of the terrain data can be applied, decreasing computation time. Further efficiency increases are found by decomposing the problem into a set of two-dimensional problems and applying binary search techniques. The combination of the research elements presented in this thesis provide efficient methods for automatically analysing asset line-of-sight and the impact of the surrounding terrain, from captured monocular video.

Motion segmentation is an important process for separating moving objects from the background. Common methods usually assume fixed camera, other approaches exist as well, but they are usually very computational intensive. This work presents an approach for scene segmentation to regions with coherent motion, which works faster than similar methods and it is capable of online processing with no prior knowledge of objects or camera. The main assumption is that the points belonging to a single objects are moving together and this applies as well in the opposite direction. The proposed method is based on tracking of feature points and searching for groups with similar motion by using RANSAC-based algorithm. Short-range repair of broken tracks is applied to increase the overall robustness of tracking. Found clusters are subsequently processed to represent separate moving objects.

Este trabalho propõe introduzir conteúdos de Física, de modo a torná-los atrativos para alunos de 8ª série, através do estudo de situações divertidas, como os movimentos presentes em atividades esportivas e de lazer do seu cotidiano. Os movimentos foram filmados pelos alunos utilizando uma câmera fotográfica digital e, após, foi usado um programa de análise de imagens (Tracker). A escolha dos temas a serem filmados e analisados partiu de sugestões dos próprios alunos em sala de aula, orientados pela professora de Ciências e pelo autor dessa proposta de trabalho. As filmagens foram realizadas pelos alunos no pátio e no salão esportivo da escola; a análise dos movimentos filmados e sua descrição foram realizadas no laboratório de informática. A proposta foi aplicada no Colégio São José, de Caxias do Sul, RS, com cinco turmas de oitava série na disciplina de Ciências, durante os meses de setembro a novembro de 2008, inserindo as atividades paralelamente à apresentação dos conteúdos. Todo material desenvolvido e utilizado nesta proposta foi disponibilizado, gradualmente, no decorrer de sua aplicação na página Web do Colégio. O planejamento e a execução desta proposta foram embasados na teoria interacionista de Lev Vygotsky. Essa escolha se deu, principalmente, pelos objetivos pretendidos neste trabalho que previam que os alunos trabalhassem em grupo com a mediação dos professores, proporcionando e estimulando o gosto por aprender. A avaliação da proposta foi feita pelos alunos no final de sua aplicação através de um questionário de opinião. Segundo as respostas dos alunos, na medida em que atividades e tecnologias do seu cotidiano são utilizadas nas aulas de Física, faz com que essas se tornem mais motivadoras e interessantes. O material instrucional produzido, acompanhado de um guia de informações e orientações será publicado na série “Hipermídias de Apoio ao Professor de Física”, onde serão descritos os objetivos, a justificativa e a metodologia utilizados, com o intuito de que possam ser aplicados por outros professores associados à disciplina de Ciências da 8ª série.<br>This work proposes an alternative introduction of 8th grade Physics school contents through the study of Kinematics concepts present, e.g., in the students' daily sporting and leisure activities, in order to make these concepts more attractive and motivating to them. The situations have been registered in the schoolyard and gymnasium by the students themselves using a digital camera. The videoclips were then analyzed using an image analysis software (Tracker) in the school's computer laboratory. The subjects on the videoclips were selected among students' suggestions and assisted by the Science class teacher together with the author. The proposal has been carried out in Colégio São José, of Caxias do Sul, RS, with five different groups of 8th graders during Science classes, from September to November of 2008, these activities being alternated with regular classes. All material developed and used in the proposal was made available, during its application, on the School's Webpage. The planning and execution of this proposal are oriented along the social interaction theory of Lev Vygotsky. This choice is mainly motivated by the goal of promoting collaborative students work, intermediated by the teachers, providing and stimulating the taste for learning. The students evaluated the work by its conclusion through an opinion questionnaire. According to the students' answers to the questionnaire, when their daily activities were introduced in the Physics classes making use of available technology through electronic and computer devices, the Physics learning was rendered more interesting and motivating. The instructional material produced during the project application together with an information guide orienting other 8th grade Science teachers on its application will be published in the series “Hipermídias de Apoio ao Professor de Física”, where aims and methodology will also be described.

Qu'est-ce qui prédispose le Portugal, le Brésil, le Québec, et l'Indiana aux USA, à mettre en place des sites institutionnels des récits de vie comme les musées de la personne, contrairement en France, où des initiatives de ce genre relèvent de la vie privée ? Nous nous interrogeons sur la force que peuvent revêtir ces récits de vie vidéos et sur le choix de ces pays de les podcaster : s’agit-il de redonner la parole à toutes les générations, les rendre plus visibles ou audibles, dans le but de transmettre, de laisser des traces pour la postérité ? Quelle est la teneur des ces traces, et qu’est-ce qui s’opère dans l’interaction entre générations ? Nous recherchons à podcaster et étudier les traces sémiotiques, sémantiques, sémiologiques des récits de vie issus de ce réseau de sites « Musée de la personne » de ces 4 pays. Nous considérons que les traces de la mémoire vivante des récits présents sur des supports numériques ou audiovisuels, constituent un édifice aussi matériel qu’un musée dans un espace donné. Le récit de vie traduirait une immémorialité, « un mouvement permanent entre temps présent et temps passé, des informations ou des événements passés et présents marquent le dialogue présent ». Nous sommes en présence de normes nouvelles, mais surtout en présence de paradigmes successifs ou de mouvements paradoxaux de recontextualisation et de reconfiguration symbolique, au fur et à mesure que ces récits de vie se transmettent d’un citoyen à un autre. Ces récits et « ces pratiques mémorielles sont très vivants chez les Anglais et les Australiens ». Il nous semble que les récits de vie peuvent participer à la formation du lien social entre générations, entre citoyens nationaux et non nationaux. Ce lien social doit s’inscrire dans l'attention et la responsabilité portée et partagée entre ascendants et descendants. Ce programme d'attention aux générations s'appelle la « neguentropie ». Il s'agirait d'un programme éthique et responsable de l'attention portée à autrui, basé sur la générosité.Tous ces dispositifs d'attention, ces récits de vie doivent s’inscrire dans une « noopolitique » de la santé publique aussi bien physique que mentale. Il s'agit de prendre garde « aux déficits attentionnels et aux troubles intergénérationnels ». Un « psychopouvoir » devrait être mis en place par nos gouvernements au service « d'une politique industrielle des technologies de l'esprit »<br>What predisposes Portugal, Brazil, Quebec, and Indiana in the USA, to set up institutional sites of “life stories” on supports (media) videos (like virtual museums), unlike in France, where such initiative remains private life? We will try to focus on the strength of life stories, and we will try to understand why countries chose to podcast them. Actually, do they use life stories in order to hand over to the rising generation, and to make them more visible and audible, so that life stories are passing on and leave prints forever (to let posterity)? Besides, what is the content of these prints, and what do they occur to the generations? Also, what about the interaction between them? In fact, we will try to podcast and study semiotic, semantic and semiological prints of life stories that we can find on the following websites, called “Museum of the person" which is suitable for the four countries that we have previously mentioned. It seems that life stories prints found in digital and audiovisual media, are like a material building, as real as a museum in a given and real place. Moreover, we have to say that a life story is like a "permanent movement between the past and the present” that influences the present dialogue. We are facing with such new standards, especially with successive paradigms or paradoxical movements of recontextualization and symbolic reconfiguration, every time that a life story is told from a citizen to another. Life stories and memory passing down generation to generation, are very common to English and Australian people. It truly seems that life stories prints are part of a social link between all the generations, and also between national and non-national citizens. This important social link takes part of aspecific care/ attention to memories and their responsibility that are shared between ascendants and descendants. This care program is called "neguentropy". It is an ethical and responsible program based of the attention to others, and generosity. All this plan of actions, relying on the attention of life stories, should be part of a”physical and mental public noopolitic health program”. The aim is to face attention deficit disorder and intergenerational discord. Finally, a "psychopower" should be set up by our governments in order to serve an “industrial policy of spirit mind technology”

The thesis is divided into two parts theoretical one and practical one. The theoretical part describes methods of implementation of physical experiments, also there is discussion about curriculum that was used in the created experiments and description of video analysis with used app, at the end of this part there is also several experiments that are made to inspire teachers and to show them video analysis options. For some of the experiments there is also graphical manual. The practical part contains a set of differentiated tasks and worksheets. In this work there is also few worksheets that were filled by students.

abstract: This dissertation presents reflective teaching practices that draw from an object-oriented rhetorical framework. In it, practices are offered that prompt teachers and students to account for the interdependent relationships between objects and writers. These practices aid in re-envisioning writing as materially situated and leads to more thoughtful collaborations between writers and objects. Through these practices, students gain a more sophisticated understanding of their own writing processes, teachers gain a more nuanced understanding of the outcomes of their pedagogical choices, and administrators gain a clearer vision of how the classroom itself affects curriculum design and implementation. This argument is pursued in several chapters, each presenting a different method for inciting reflection through the consideration of human/object interaction. The first chapter reviews the literature of object oriented rhetorical theory and reflective teaching practice. The second chapter adapts a methodology from the field of Organizational Science called Narrative Network Analysis (NNA) and leads students through a process of identifying and describing human/object interaction within narratives and asks students to represent these relationships visually. As students undertake this task they can more objectively examine their own writing processes. In the third chapter, video ethnographic methodologies are used to observe object oriented rhetoric theory in practice through the interactions of humans and objects in the writing classroom. Through three video essays, clips of footage taken of a writing classroom and its writing objects are selected and juxtaposed to highlight the agency and influence of objects. In chapter four, a tool developed using freely available cloud-based web applications is presented which is termed the “Fitness Tracker for Teaching.” This tool is used to regularly collect, store, and analyze data that students self-report through a daily class survey about their work efforts, their work environment, and their feelings of confidence, productivity, and self-efficacy. The data gathered through this tool provides a more complete understanding of student effort and affect than could be provided by the teacher’s and students’ own memories or perceptions. Together these chapters provide a set of reflective practices that reinforce teaching writing as a process that is affective and embodied and acknowledges and accounts for the rhetorical agency of objects.<br>Dissertation/Thesis<br>Chapter 3 Video Presentation<br>Doctoral Dissertation English 2017

碩士<br>國立交通大學<br>多媒體工程研究所<br>100<br>In volleyball games, the analysis of players’ moving and jumping trajectories bring much tactical information. In this paper, we analyze volleyball videos to extract players’ trajectories and to identify the jumping parts of the extracted trajectories. The jumping parts can be determined via (i) vertical component analysis of trajectories and (ii) vanishing point-based collinear analysis of trajectories. Specifically, we first use background subtraction to segment foreground athletes and detect their head positions in an image sequence. The head positions are then transformed to top-view coordinates via homography transformation and form athletes’ trajectories. Finally, the method (i) and (ii) are applied to differentiate the moving and jumping parts of the trajectories. In our experiments, all the jumping parts of the trajectories are detected correctly, with moving trajectories of the athletes being displayed.