The frequently studied lobula giant movement detector (LGMD) system of the locust responds most strongly to approaching objects. This thesis describes simulations which were designed with the ultimate aim of constructing a comprehensive model of the neural circuitry showing the effects of individual neurons on the overall responses of the system. The Rind and Bramwell neural network model of the LGMD was studied using new stimuli which revealed that the responses of the model are dependent on the shape of the stimulus. A modification of the model removes this dependence and allows the model to respond to more complex stimuli. Two models of a locust photoreceptor were developed with the aim of producing a detailed model of a light-adapting photoreceptor which could be used to study the responses of the LGMD to natural scenes. The first model, an electrical model of the cell membrane which describes the principal ionic conductances, was found to be overly complex for use in large scale simulations. However, the model was used to calculate from the photoreceptor's impulse response the average conductance change produced by individual photons. The second photoreceptor model, which is suitable for large scale simulations, uses two leaky integrators to mimic the effects of light adaptation on the photoreceptor's response. An electrical model of the lamina region of the optic lobe allowed the proposal that inhibition in the lamina is produced by electrical presynaptic inhibition to be studied, along with the possible effects of this inhibition on the visual input to the LGMD. The responses of the model correspond well with those measured from the LMCs of locusts and other insects, and their implications for the LGMD system are discussed.

In this thesis report, some of the most promising techniques, in the field of intelligent vehicles and mobile robotics, for detection and tracking of moving objects in an indoor environment are investigated. Kalman filter (KF), extended Kalman filter (EKF), and particle filters (PF) based techniques for the tracking of people are implemented and evaluated. A heuristic method is then proposed to improve the performance of the EKF based tracking in situations where moving objects are hidden by obstacles. The proposed method is based on points of maximum uncertainty (PMU) in occlusion situations and its complexity and accuracy is compared with PF method. The EKF, PF and PMU based methods are examined and compared using experimental data which are extracted by a laser range finder in an indoor environment with predefined hinders and people as the moving objects.

Um sistema que realiza a detecção de movimento procura, numa seqüência de imagens, sinais que confirmem a existência de movimentação no ambiente monitorado. Uma vez realizada a detecção do movimento, pode-se realizar o rastreamento (tracking) do objeto na cena em questão. A detecção e o rastreamento de objetos, em tempo real, são técnicas que estão despertando grande interesse por parte de pesquisadores e empresas pois, estas técnicas, podem ser utilizadas em diversas áreas que se estendem desde a engenharia e computação até áreas como a geologia e medicina. Sendo assim, seguindo-se a idéia básica de detecção e rastreamento, encontram-se diversas aplicações para estas técnicas como: sistemas de vigilância, análise de movimentos humanos, sistemas de detecção e rastreamento de pedestres ou veículos, dentre outras. Neste trabalho é mostrado um sistema que foi desenvolvido para armazenamento de imagens em tons de cinza de uma seqüência de vídeo e um posterior processamento dessas imagens para detecção de características que indiquem movimento. O processamento se resume em integrar o sinal de vídeo, que está armazenado nas memórias, nas direções horizontal e vertical gerando os histogramas de intensidade horizontal e vertical. Comparando os histogramas de quadros diferentes da seqüência de vídeo será possível detectar a presença de movimento e a região da imagem onde este ocorreu. Devido à necessidade de um processamento rápido das imagens e no interesse de produzir um sistema dedicado com hardware reduzido, utilizou-se de dispositivos de lógica programável complexa (CPLDs). / A system that performs movement detection in a sequence of images looks for signs that confirm the occurrence of the movement in the controlled environment. Once the movement of the object is detected it is possible to perform the tracking of the object. Real time object detection and tracking techniques are of great interests to researchers and industries because these techniques can be used in several areas going from engineering and computing to geology and medicine. There is a wide field of applications of detection and tracking techniques, such as: surveillance systems, human movement analysis, pedestrians or vehicle detection. This work presents an implementation able to store a gray level image from a video sequence and from these images detect in real time a object movement in the scene. The detection will be performed integrating an image from the video sequence in the horizontal and vertical directions in order to obtain the intensities histograms in these directions. Comparing the histograms with those of a different frame of the video sequence it will be possible to detect the presence of movement and locate where in the image the movement occurs. Due to real time digital image processing requirements and in order to produce a reduce dedicated hardware, complex programmable logic devices (CPLDs) were used.

Accurate motion capture of deformable objects from monocular video sequences is a challenging Computer Vision problem with immense applicability to domains ranging from virtual reality, animation to image guided surgery. Existing dense motion capture methods rely on expensive setups with multiple calibrated cameras,structured light, active markers or prior scene knowledge learned from a large 3D dataset. In this thesis, we propose an end-to-end pipeline for 3D reconstruction of deformable scenes from a monocular video sequence. Our method relies on a two step pipeline in which temporally consistent video registration is followed by a dense non-rigid structure from motion approach. We present a data-driven method to reconstruct non-rigid smooth surfaces densely, using only a single video as input, without the need for any prior models or shape templates. We focus on the well explored low-rank prior for deformable shape reconstruction and propose its convex relaxation to introduce the first variational energy minimisation approach to non-rigid structure from motion. To achieve realistic dense reconstruction of sparsely textured surfaces, we incorporate an edge preserving spatial smoothness prior into the low-rank factorisation framework and design a single variational energy to address the non-rigid structure from motion problem. We also discuss the importance of long-term 2D trajectories for several vision problems and explain how subspace constraints can be used to exploit the redundancy present in the motion of real scenes for dense video registration. To that end, we adopt a variational optimisation approach to design a robust multi-frame video registration algorithm that combines a robust subspace prior with a total variation spatial regulariser. Throughout this thesis, we advocate the use of GPU-portable and scalable energy minimisation algorithms to progress towards practical dense non-rigid 3D motion capture from a single video in the presence of occlusions and illumination changes.

Um sistema que realiza a detecção de movimento procura, numa seqüência de imagens, sinais que confirmem a existência de movimentação no ambiente monitorado. Uma vez realizada a detecção do movimento, pode-se realizar o rastreamento (tracking) do objeto na cena em questão. A detecção e o rastreamento de objetos, em tempo real, são técnicas que estão despertando grande interesse por parte de pesquisadores e empresas pois, estas técnicas, podem ser utilizadas em diversas áreas que se estendem desde a engenharia e computação até áreas como a geologia e medicina. Sendo assim, seguindo-se a idéia básica de detecção e rastreamento, encontram-se diversas aplicações para estas técnicas como: sistemas de vigilância, análise de movimentos humanos, sistemas de detecção e rastreamento de pedestres ou veículos, dentre outras. Neste trabalho é mostrado um sistema que foi desenvolvido para armazenamento de imagens em tons de cinza de uma seqüência de vídeo e um posterior processamento dessas imagens para detecção de características que indiquem movimento. O processamento se resume em integrar o sinal de vídeo, que está armazenado nas memórias, nas direções horizontal e vertical gerando os histogramas de intensidade horizontal e vertical. Comparando os histogramas de quadros diferentes da seqüência de vídeo será possível detectar a presença de movimento e a região da imagem onde este ocorreu. Devido à necessidade de um processamento rápido das imagens e no interesse de produzir um sistema dedicado com hardware reduzido, utilizou-se de dispositivos de lógica programável complexa (CPLDs). / A system that performs movement detection in a sequence of images looks for signs that confirm the occurrence of the movement in the controlled environment. Once the movement of the object is detected it is possible to perform the tracking of the object. Real time object detection and tracking techniques are of great interests to researchers and industries because these techniques can be used in several areas going from engineering and computing to geology and medicine. There is a wide field of applications of detection and tracking techniques, such as: surveillance systems, human movement analysis, pedestrians or vehicle detection. This work presents an implementation able to store a gray level image from a video sequence and from these images detect in real time a object movement in the scene. The detection will be performed integrating an image from the video sequence in the horizontal and vertical directions in order to obtain the intensities histograms in these directions. Comparing the histograms with those of a different frame of the video sequence it will be possible to detect the presence of movement and locate where in the image the movement occurs. Due to real time digital image processing requirements and in order to produce a reduce dedicated hardware, complex programmable logic devices (CPLDs) were used.

Orientadores: João Mauricio Rosario, Francisco Carlos Parquet Bizarria. / Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecanica / Made available in DSpace on 2018-08-12T03:58:51Z (GMT). No. of bitstreams: 1 Barbosa_SilvanaAparecida_D.pdf: 3254271 bytes, checksum: dfd0e2d57b3560c893dad3675337cfe9 (MD5) Previous issue date: 2008 / Resumo: A tarefa contínua de detecção de mudança de cenários em determinado ambiente pode ocasionar estresse físico e mental para o supervisor. Com o uso da visão computacional associada à automação é possível oferecer recursos para que essa tarefa seja executada de forma automatizada. Neste contexto, este trabalho apresenta uma proposta de arquitetura para um sistema detectar mudanças de cenários por meio da comparação sucessiva de imagens. Esse sistema de visão deverá possibilitar por meio da implementação de um algoritmo, utilizando recursos matemáticos específicos para a aplicação, a detecção de mudança no cenário e o registro das imagens relativas a essa situação. Para validar a referida proposta, com o enfoque na aplicação aeroespacial, é apresentado nesta tese o estudo de caso para aplicação de técnicas de Visão Artificial na Detecção de Mudança de Cenários em Plataforma de Integração de Veículos Espaciais. Esse estudo visa supervisionar áreas destinadas principalmente à integração e aos testes desse veículo espacial. A implementação desse algoritmo utiliza técnicas de processamento de imagens baseada em filtros espaciais, em especial convolução por filtro da média. Os resultados satisfatórios, obtidos nos ensaios práticos realizados em protótipo da Torre Móvel de Integração, indicam que o sistema é adequado para aplicação a qual se destina. / Abstract: The continuous task of detecting changes in scenarios can cause a mental and physical stress on supervisor. The associated use of computational vision and automation provides resources to execute this task in an automated way. This thesis presents an architectural proposal for a system to detect changes in the imaged scenes by comparing images successively. Through the development of algorithm using specific mathematical tools, this vision system detects and record changes in the imaged scenes. Focusing aerospace area to validate this proposal, Artificial Vision Applied in Detection of Change of Scenes, a Study of Case in Platform for Integration of Space Vehicles is presented in this thesis. The purpose of this research is supervising the designed areas for integration and tests of the space vehicle. Image processing techniques based on spatial filters, in particular convolution, are used for algorithm development. The results obtained through practical tests executed on a prototype of an Integration Mobile Tower, show the system is appropriate to this application. / Doutorado / Mecanica dos Sólidos e Projeto Mecanico / Doutor em Engenharia Mecânica

No description available.

L'anévrisme cérébral est une région fragile de la paroi d'un vaisseau sanguin dans le cerveau, qui peut se rompre et provoquer des saignements importants et des accidents vasculaires cérébraux. La segmentation de l'anévrisme cérébral est une étape primordiale pour l'aide au diagnostic, le traitement et la planification chirurgicale. Malheureusement, la segmentation manuelle prend encore une part importante dans l'angiographie clinique et elle est devenue couteuse en temps de traitement étant donné la gigantesque quantité de données générées par les systèmes d'imagerie médicale. Les méthodes de segmentation automatique d'image constituent un moyen essentiel pour faciliter et accélérer l'examen clinique et pour réduire l'interaction manuelle et la variabilité inter-opérateurs. L'objectif principal de ce travail de thèse est de développer des méthodes automatiques pour la segmentation et la mesure des anévrismes. Le présent travail de thèse est constitué de trois parties principales. La première partie concerne la segmentation des anévrismes géants qui contiennent à la fois la lumière et le thrombus. La méthode consiste d'abord à extraire la lumière et le thrombus en utilisant une procédure en deux étapes, puis à affiner la forme du thrombus à l'aide de la méthode des courbes de niveaux. Dans cette partie, la méthode proposée est également comparée à la segmentation manuelle, démontrant sa bonne précision. La deuxième partie concerne une approche LBM pour la segmentation des vaisseaux dans des images 2D+t et de l'anévrisme cérébral dans les images en 3D. La dernière partie étudie un modèle de segmentation 4D en considérant les images 3D+t comme un hypervolume 4D et en utilisant un réseau LBM D4Q81, dans lequel le temps est considéré de la même manière que les trois autres dimensions pour la définition des directions de mouvement des particules dans la LBM, considérant les données 3D+t comme un hypervolume 4D et en utilisant un réseau LBM D4Q81. Des expériences sont réalisées sur des images synthétiques d'hypercube 4D et d'hypersphere 4D. La valeur de Dice sur l'image de l'hypercube avec et sans bruit montre que la méthode proposée est prometteuse pour la segmentation 4D et le débruitage. / Cerebral aneurysm is a fragile area on the wall of a blood vessel in the brain, which can rupture and cause major bleeding and cerebrovascular accident. The segmentation of cerebral aneurysm is a primordial step for diagnosis assistance, treatment and surgery planning. Unfortunately, manual segmentation is still an important part in clinical angiography but has become a burden given the huge amount of data generated by medical imaging systems. Automatic image segmentation techniques provides an essential way to easy and speed up clinical examinations, reduce the amount of manual interaction and lower inter operator variability. The main purpose of this PhD work is to develop automatic methods for cerebral aneurysm segmentation and measurement. The present work consists of three main parts. The first part deals with giant aneurysm segmentation containing lumen and thrombus. The methodology consists of first extracting the lumen and thrombus using a two-step procedure based on the LBM, and then refining the shape of the thrombus using level set technique. In this part the proposed method is also compared with manual segmentation, demonstrating its good segmentation accuracy. The second part concerns a LBM approach to vessel segmentation in 2D+t images and to cerebral aneurysm segmentation in 3D medical images through introducing a LBM D3Q27 model, which allows achieving a good segmentation and high robustness to noise. The last part investigates a true 4D segmentation model by considering the 3D+t data as a 4D hypervolume and using a D4Q81 lattice in LBM where time is considered in the same manner as for other three dimensions for the definition of particle moving directions in the LBM model.

The goal of this master's thesis is to analyze the situation of wearable devices with the Android Wear operating system and recognition capabilities of various movement activities using neural networks. The primary focus is therefore on identifying and describing the most appropriate tool for recognizing dynamic movements using machine learning methods based on data obtained from this type of devices. The practical part of the thesis then comments on the implementation of a stand-alone Android Wear application capable of recording and formatting data from sensors, training the neural network in a designed external desktop tool, and then reusing trained neural network for motion recognition directly on the device.

This master’s thesis is dealing with recognition of an easy static gestures in order to computer controlling. First part of this work is attended to the theoretical review of methods used to hand segmentation from the image. Next methods for hang gesture classification are described. The second part of this work is devoted to choice of suitable method for hand segmentation based on skin color and movement. Methods for hand gesture classification are described in next part. Last part of this work is devoted to description of proposed system.