O trabalho apresentado por essa dissertação busca contribuir com a atenuação do problema da correspondência em visão estéreo a partir de uma abordagem local de soluções. São usadas duas estratégias como solução às ambigüidades e às oclusões da cena: a análise multi-resolução das imagens empregando a estrutura piramidal, e a força de agrupamento perceptual, conhecida como Gestalt theory na psicologia. Inspirado no sistema visual humano, a visão estéreo é uma área de grande interesse em visão computacional, e está relacionada à recuperação de informações tridimensionais de uma cena a partir de imagens da mesma. Para isso, as imagens são capturadas em posições diferentes para o futuro relacionamento das várias projeções de um mesmo ponto 3D. Apesar de ser estudada há quase quatro décadas, ela ainda apresenta problemas de difícil solução devido às dificuldades relacionadas às distorções produzidas pela mudança da perspectiva de visualização. Dentre esses problemas destacam-se os relacionados à oclusão de pontos e também à ambigüidade gerada pela repetição ou ausência de textura nas imagens. Esses por sua vez compõem a base do problema estéreo, chamado de problema da correspondência. Os resultados obtidos são equivalentes aos obtidos por técnicas globais, com a vantagem de requerer menor complexidade computacional. O uso da teoria de agrupamento perceptual faz desse trabalho um método moderno de estimação de disparidades, visto que essa técnica é alvo de atenção especial em recentes estudos na área de visão computacional. / This work aims to give a contribution to the correspondence problem using a local approach. Two strategies are used as solution to ambiguities and occlusions: the multi-resolution analysis with irnages pyramids and the other is the perceptual grouping weight, called Gestalt theory in the psychology. Inspired by human vision system, the stereo vision is an very important area in computer vision. It is related with the 3D information recovery from a pair of images. The images are captured frorn different positions to hereafter association of the 3D point projections. Although it has being studied for quite a long time, stereo vision presents some difficult problems, related to the change of visualisation perspective. Among the different problems originated from point of view changes, occlusions and ambiguities have special attention and compose the foundation of stereo problem, named correspondence problem. The results obtained were closer to the ones generated by global techniques, with the advantage of requiring less computational complexity. The use of Gestalt theory makes this a modern disparity estimation method, as this theory has been received special attention in computer vision researchs.

Sistemas de teleconferência e telepresença são ferramentas de comunicação cada vez mais comuns. Partindo da existência de um canal de comunicação de alta capacidade, busca-se permitir visualização tridimensional realista, sensível ao ponto de vista do usuário e que mantenha a estrutura física da cena sem conhecimento prévio de sua estrutura, por meio de câmeras estéreo. A partir de pares de imagens temporalmente coerentes são sintetizadas visões intermediárias da cena alvo, de modo que um usuário rastreado tenha a ilusão de estar vendo a cena real através de uma janela. O sistema implementado baseia-se em dispositivos que provejam melhor qualidade visual no componente de geração de imagens intermediárias e procura maximizar a facilidade de uso na parte de visualização, empregando dispositivos domésticos e dispensando procedimentos complexos de calibração. / Teleconference and telepresence systems are increasingly common. Based on the existence of a high capacity communication channel, it is aimed to provide user\'s point of view sensible realistic 3D visualization without physical distortion or any prior knowledge about the structure of the scene, using stereo cameras. Pairs of temporally coherent images are used to generate intermediary view of the target scene so that a tracked user will have the illusion of posing in front so the real scene. The implemented system is based on high visual quality components on the side of views generation and tries to maximize ease of use in the visualization part by using commodity components and being free so complex calibration procedures.

Detecção de pedestres é uma importante área em visão computacional com o potencial de salvar vidas quando aplicada em veículos. Porém, essa aplicação exige detecções em tempo real, com alta acurácia e menor quantidade de falsos positivos possível. Durante os últimos anos, diversas ideias foram exploradas e os métodos mais recentes que utilizam arquiteturas profundas de redes neurais possibilitaram um grande avanço nesta área, melhorando significativamente o desempenho das detecções. Apesar desse progresso, a detecção de pedestres que estão distantes do veículo continua sendo um grande desafio devido às suas pequenas escalas na imagem, sendo necessária a avaliação da eficácia dos métodos atuais em evitar ou atenuar a gravidade dos acidentes de trânsito que envolvam pedestres. Dessa forma, como primeira proposta deste trabalho, foi realizado um estudo para avaliar a aplicabilidade dos métodos estado-da-arte para evitar colisões em cenários urbanos. Para isso, a velocidade e dinâmica do veículo, o tempo de reação e desempenho dos métodos de detecção foram considerados. Através do estudo, observou-se que em ambientes de tráfego rápido ainda não é possível utilizar métodos visuais de detecção de pedestres para assistir o motorista, pois nenhum deles é capaz de detectar pedestres que estão distantes do veículo e, ao mesmo tempo, operar em tempo real. Mas, ao considerar apenas pedestres em maiores escalas, os métodos tradicionais baseados em janelas deslizantes já conseguem atingir um bom desempenho e rápida execução. Dessa forma, com a finalidade de restringir a operação dos detectores apenas para pedestres em maiores escalas e assim, possibilitar a aplicação de métodos visuais em veículos, foi proposta uma configuração de câmeras que possibilitou obter imagens para um maior intervalo de distância à frente do veículo com pedestres em resolução quase duas vezes maior em comparação à uma câmera comercial. Resultados experimentais mostraram considerável melhora no desempenho das detecções, possibilitando superar a dificuldade causada pelas pequenas escalas dos pedestres nas imagens. / Pedestrian detection is an important area in computer vision with the potential to save lives when applied on vehicles. This application requires accurate detections and real-time operation, keeping the number of false positives as minimal as possible. Over the past few years, several ideas were explored, including approaches with deep network architectures, which have reached considerably better performances. However, detecting pedestrians far from the camera is still challenging due to their small sizes on images, making it necessary to evaluate the effectiveness of existing approaches on avoiding or reducing traffic accidents that involves pedestrians. Thus, as the first proposal of this work, a study was done to verify the state-of-the-art methods applicability for collision avoidance in urban scenarios. For this, the speed and dynamics of the vehicle, the reaction time and performance of the detection methods were considered. The results from this study show that it is still not possible to use a vision-based pedestrian detector for driver assistance on urban roads with fast moving traffic, since none of them is able to handle real-time pedestrian detection. However, for large-scale pedestrians on images, methods based on sliding window approach can already perform reliably well with fast inference time. Thus, in order to restrict the operation of detectors only for pedestrians in larger scales and enable the application of vision-based methods in vehicles, it was proposed a camera setup that provided to get images for a larger range of distances in front of the vehicle with pedestrians resolution almost twice as large compared to a commercial camera. Experimental results reveal a considerable enhancement on detection performance, overcoming the difficulty caused by the reduced scales that far pedestrians have on images.

Towing-tank experiments are performed for a surface combatant as it undergoes static and dynamic planar motion mechanism maneuvers in calm water. The data includes global forces/moment/motions and phase-averaged local flow-fields, and uncertainty assessment. The geometry is DTMB model 5512, which is a 1/46.6 scale geosym of DTMB model 5415, with L = 3.048 m. The experiments are performed in a 3.048 × 3.048 × 100 m towing tank. The measurement system features a custom designed planar motion mechanism, a towed stereoscopic particle image velocimetry system, a Krypton contactless motion tracker, and a 6-component loadcell. The forces/moment and UA are conducted in collaboration with two international facilities (FORCE and INSEAN), including test matrix and overlapping tests using the same model geometry but with different scales. Quality of the data is assessed by monitoring the statistical convergence, including tests for randomness, stationarity, and normality. Uncertainty is assessed following the ASME Standards (1998 and 2005). Hydrodynamic derivatives are determined from the forces/moment data by using the Abkowitz (1966) mathematical model, with two different 'Multiple-Run (MR)' and 'Single-Run (SR)' methods. The results for reconstructions of the forces/moment indicate that usually the MR method is more accurate than the SR. Comparisons are made of the hydrodynamic derivatives across different facilities. The scale effect is small for sway derivatives, whereas considerable for yaw derivatives. Heave, pitch, and roll motions exhibit cross-coupling between the motions and forces and moment data, as expect based on ship motions theory. Hydrodynamic derivatives are compared between different mount conditions. Linear derivatives values are less sensitive to the mounting conditions, whereas the non-linear derivatives are considerably different. Phase-averaged flowfield results indicate maneuvering-induced vortices and their interactions with the turbulent boundary layer. The tests are sufficiently documented and detailed so as to be useful as benchmark EFD data for CFD validation.

Flight is a vital component of butterfly natural history, and flight-associated morphology is thought to be under strong selection for the performance of critical behaviors such as patrolling, courtship and oviposition. However, while different behaviors require different proportions of flapping versus gliding flight, few studies actually quantify butterfly flight behavior. Moreover, as butterfly flight is anteromotoric, no prior study has measured the role of hind wing allometry in flight. Using high-speed videography, this study compares the flight of two species of Haeterini (Nymphalidae) that regularly employ gliding flight. We also employ stereo videography and experimental hind wing area reduction to measure the effects of hind wing allometry on flight. Results suggest that although the forewings are reliable predictors of flight in these two species, relative hind wing area can significantly affect gliding flight performance, and should be considered as a factor in future investigations on flight-associated morphology in butterflies.

Dans ce document, je décris mes activités professionnelles, pour la période allant de 1998 à 2005. <br />La plus grande partie de ce document (parties II à VI) <br />est rédigée en anglais. Elle contient la description des résultats<br />scientifiques que j'ai obtenus durant cette période. Un résumé en français en est donné dans la première<br />partie du manuscrit. Il est précédé d'une description de mes activités d'animation <br />de la recherche (organisations de colloques, participations à des comités de programme, <br />responsabilités scientifiques, participations à des<br />projets, communications invitées, etc.) <br />et des tâches administratives et d'enseignement dont j'ai eu la charge.<br />Ce document est accompagné par une sélection des articles les plus<br />représentatifs de mes activités de recherche pour la période concernée.

<p>En modern grafikprocessor är oerhört kraftfull och har en prestanda som potentiellt sett är många gånger högre än för en modern mikroprocessor. I takt med att grafikprocessorn blivit alltmer programmerbar har det blivit möjligt att använda den för beräkningstunga tillämpningar utanför dess normala användningsområde. Inom det här arbetet utreds vilka möjligheter och begränsningar som uppstår vid användandet av grafikprocessorer för generell programmering. Arbetet inriktas främst mot signal- och bildbehandlingstillämpningar men mycket av principerna är tillämpliga även inom andra områden.</p><p>Ett ramverk för bildbehandling implementeras och några algoritmer inom bildanalys realiseras och utvärderas, bland annat stereoseende och beräkning av optiskt flöde. Resultaten visar på att vissa tillämpningar kan uppvisa en avsevärd prestandaökning i en grafikprocessor jämfört med i en mikroprocessor men att andra tillämpningar kan vara ineffektiva eller mycket svåra att implementera.</p> / <p>The modern graphical processing unit, GPU, is an extremely powerful unit, potentially many times more powerful than a modern microprocessor. Due to its increasing programmability it has recently become possible to use it in computation intensive applications outside its normal usage. This work investigates the possibilities and limitations of general purpose programming on GPUs. The work mainly concentrates on signal and image processing although much of the principles are applicable to other areas as well.</p><p>A framework for image processing on GPUs is implemented and a few computer vision algorithms are implemented and evaluated, among them stereo vision and optical flow. The results show that some applications can gain a substantial speedup when implemented correctly in the GPU but others can be inefficent or extremly hard to implement.</p>

<p>The purpose of this master’s thesis was to study the possibility to use computer vision methods to detect and classify objects in the front passenger seat in a car. This work presents different approaches to solve this problem and evaluates the usefulness of each technique. The classification information should later be used to modulate the speed and the force of the airbag, to be able to provide each occupant with optimal protection and safety.</p><p>This work shows that computer vision has a great potential in order to provide data, which may be used to perform reliable occupant classification. Future choice of method to use depends on many factors, for example costs and requirements on the system from laws and car manufacturers. Further, evaluation and tests of the methods in this thesis, other methods, the ABE approach and post-processing of the results should also be made before a reliable classification algorithm may be written.</p>

<p>Robotic manipulators have been introduced in industry as a form of increasing productivity. Today, there exist an interest to enlarge the application of these manipulators to outdoor environments. Forestry cranes used in the forestry industry are a clear example. A long term goal in this industry is the development of autonomous systems to increase the logging efficiency. In this thesis, we consider how to control the rotator of these cranes, which is an electro-hydraulically actuated motor, and is used to control the end ffector tool. Control system design for the rotator is a challenging task since the sensing is not available to full extent. The main reason is the harsh environment that these machines are exposed to and sensors such as encoders are very fragile and cannot be used. In this thesis we use alternative sensing devices, such as a magnetic sensor and a stereo camera. In the case of the camera we face a problem with big delay. A prediction method has been used to compute desired values. Due to various reasons certain measuring devices can not be used in the industry. We consider four cases for control system design where dfferent combinations of available sensors have been used. Initially angular position of the rotator is controlled using only the magnetic sensor. A cascade control setup is used where pressure and position are measurable, first using the magnetic sensor and later using the camera. When only pressure measurements are available identified models have replaced sensors for position feedback. All tests and experiments have been done using a scaled version of a real forestry crane. The available crane has similar configuration and dynamics as the real one and is therefor useful for experimental purposes.</p>

<p>The objective of this thesis is to investigate if it is possible to use stereo vision to find and track the players and the ball during a football game.</p><p>The thesis shows that it is possible to detect all players that isn’t too occluded by another player. Situations when a player is occluded by another player is solved by tracking the players from frame to frame.</p><p>The ball is also detected in most frames by looking for ball-like features. As with the players the ball is tracked from frame to frame so that when the ball is occluded, the positions is estimated by the tracker.</p>