Diversos problemas práticos envolvendo sistemas de visão computacional, tais como vigilância automatizada, pesquisas de conteúdo específico em bancos de dados multimídias ou edição de vídeo, requerem a localização e o reconhecimento de objetos dentro de seqüências de imagens ou vídeos digitais. Mais formalmente, denomina-se rastreamento o processo de determinação da posição de certo(s) objeto(s) ao longo do tempo numa seqüência de imagens. Já a tarefa de reconhecimento caracteriza-se pela classificação desses objetos de acordo com algum rótulo pré-estabelecido ou apoiada em conhecimento prévio tipicamente introduzido através de um modelo dos objetos de interesse. No entanto, rastrear e classificar objetos em vídeo digital são tarefas desafiadoras, tanto pelas dificuldades inerentes a esse tipo de elemento pictórico, quanto pelo variável grau de complexidade que os quadros sob análise podem apresentar. Este documento apresenta uma metodologia baseada em modelo para rastrear e reconhecer objetos em vídeo digital através de uma representação por grafos relacionais com atributos (ARGs). Tais estruturas surgiram dentro do paradigma de reconhecimento estrutural de padrões e têm se mostrado bastante flexíveis e poderosas para modelar problemas diversos, pois podem transmitir dados quantitativos, relacionais, estruturais e simbólicos. Como modelo e entrada são descritos através desses grafos, a questão de reconhecimento é interpretada como um problema de casamento inexato entre grafos, que consiste em mapear os vértices do ARG de entrada nos vértices do ARG modelo. Em seguida, é realizado o rastreamento dos objetos de acordo com uma transformação afim derivada de parâmetros obtidos da etapa de reconhecimento. Para validar a metodologia proposta, resultados sobre seqüências de imagens digitais, sintéticas e reais, são apresentados e discutidos. / Several practical problems involving computer vision systems, such as automated surveillance, content-based queries in multimedia databases or video editing require the location and recognition of objects within image sequences or digital video. More formally, the process of determining the position of certain objects in an image sequence throughout time is called tracking, whereas the recognition task is characterized by the classification of such objects according to pre-defined labels or a priori knowledge, typically introduced by means of a model of the target objects. However, tracking and recognition of objects in digital video are not simple tasks, either because of the inherent difficulties of such a pictorial element, or due to the variable level of complexity that the frames under consideration might present. This document presents a model-based methodology for tracking and recognizing objects represented by attributed relational graphs (ARGs) in digital video. These structures have arisen from the paradigm of structural pattern recognition and have proven to be very flexible and powerful for modeling various problems, as they can hold many sorts of data (e.g: quantitative, relational, structural and symbolic). Since both model and input data are described through these graphs, the recognition matter may be interpreted as an inexact graph matching problem, which consists in finding a correspondence between the set of vertices of the input ARG and that of the model ARG. In the next step, object tracking is performed according to an affine transform derived from parameters extracted from the recognition phase. To validate the proposed methodology, results obtained from real and synthetic digital image sequences are presented and discussed.

The goal of this thesis is to design and create an automatic system for video anonymization. This system makes use of various object detectors on an image to ensure functionality, as well as active tracking of objects detected in this manner. Adjustments are later applied to these detected objects which ensure sufficient level of anonymization. The main asset of this system is speeding up the anonymization process of videos that can be published after.

This thesis deals with methods for the detection of people and tracking objects in video sequences. An application for detection and tracking of players in video recordings of sport activities, e.g. hockey or basketball matches, is proposed and implemented. The designed application uses the combination of histograms of oriented gradients and classification based on SVM (Support Vector Machines) for detecting players in the picture. Moreover, a particle filter is used for tracking detected players. The whole system was fully tested and the results are shown in the graphs and tables with verbal descriptions.

The aim of this diploma thesis is to obtain information on the motion of people in a scene from the record of the stationary camera. The procedure to detect exceptional events in the scene was designed. Exceptional events can be fast-moving persons, or persons moving in di erent places than everyone else in the scene. To trace the motion of persons, two algorithms were applied and tested - Optical flow and CAMSHIFT. The analysis of the resulting motions is performed by monitoring the progress of motion, and its comparison with the other motions in the scene. The analysis result is represented by detected exceptional motions that can be found in the video. The areas where the motion occurs in the scene, and where the motion is the most common are also described together with the motion direction analysis. The exceptional motion parts extracted from the video represent the main result of the work.

This master's thesis describes principles of the most widely used object tracking systems in video and then mainly focuses on characterization and on implementation of an interactive offline tracking system for generic color objects. The algorithm quality consists in high accuracy evaluation of object trajectory. The system creates the output trajectory from input data specified by user which may be interactively modified and added to improve the system accuracy. The algorithm is based on a detector which uses a color bin features and on the temporal coherence of object motion to generate multiple candidate object trajectories. Optimal output trajectory is then calculated by dynamic programming whose parameters are also interactively modified by user. The system achieves 15-70 fps on a 480x360 video. The thesis describes implementation of an application which purpose is to optimally evaluate the tracker accuracy. The final results are also discussed.

The master's thesis deals with detecting and tracking people in the video. To get optimal recognition was used convolution neural network, which extracts vector features from the enclosed frame the face. The extracted vector is further classified. Recognition process must take place in a real time and also with respect are selected optimal methods. There is a new dataset faces, which was obtained from a video record at the faculty area. Videos and dataset were used for experiments to verify the accuracy of the created system. The recognition accuracy is about 85% . The proposed system can be used, for example, to register people, counting passages or to report the occurrence of an unknown person in a building.

An autonomous vehicle is a complex system that requires a good perception of the surrounding environment to operate safely. One part of that is multiple object tracking, which is an essential component in camera-based perception whose responsibility is to estimate object motion from a sequence of images. This requires an association problem to be solved where newly estimated object positions are mapped to previously predicted trajectories, for which different solution strategies exist.  In this work, a multiple hypothesis tracking algorithm is implemented. The purpose is to demonstrate that measurement associations are improved compared to less compute-intensive alternatives. It was shown that the implemented algorithm performed 13 percent better than an intersection over union tracker when evaluated using a standard evaluation metric. Furthermore, this work also investigates the usage of abstraction layers to accelerate time-critical parallel operations on the GPU. It was found that the execution time of the tracking algorithm could be reduced by 42 percent by replacing four functions with implementations written in the purely functional array language Futhark. Finally, it was shown that a GPU code abstraction layer can reduce the knowledge barrier required to write efficient CUDA kernels.

La représentation visuelle est un problème fondamental en vision par ordinateur. Le but est de réduire l'information au strict nécessaire pour une tâche désirée. Plusieurs types de représentation existent, comme les caractéristiques de couleur (histogrammes, attributs de couleurs...), de forme (dérivées, points d'intérêt...) ou d'autres, comme les bancs de filtres.Les caractéristiques bas-niveau (locales) sont rapides à calculer. Elles ont un pouvoir de représentation limité, mais leur généricité présente un intérêt pour des systèmes autonomes et multi-tâches, puisque les caractéristiques haut-niveau découlent d'elles.Le but de cette thèse est de construire puis d'étudier l'impact de représentations fondées seulement sur des caractéristiques locales de bas-niveau (couleurs, dérivées spatiales) pour deux tâches : la poursuite d'objets génériques, nécessitant des caractéristiques robustes aux variations d'aspect de l'objet et du contexte au cours du temps; la détection d'objets, où la représentation doit décrire une classe d'objets en tenant compte des variations intra-classe. Plutôt que de construire des descripteurs d'objets globaux dédiés, nous nous appuyons entièrement sur les caractéristiques locales et sur des mécanismes statistiques flexibles visant à estimer leur distribution (histogrammes) et leurs co-occurrences (Transformée de Hough Généralisée). La Transformée de Hough Généralisée (THG), créée pour la détection de formes quelconques, consiste à créer une structure de données représentant un objet, une classe... Cette structure, d'abord indexée par l'orientation du gradient, a été étendue à d'autres caractéristiques. Travaillant sur des caractéristiques locales, nous voulons rester proche de la THG originale.En poursuite d'objets, après avoir présenté nos premiers travaux, combinant la THG avec un filtre particulaire (utilisant un histogramme de couleurs), nous présentons un algorithme plus léger et rapide (100fps), plus précis et robuste. Nous présentons une évaluation qualitative et étudierons l'impact des caractéristiques utilisées (espace de couleur, formulation des dérivées partielles...). En détection, nous avons utilisé l'algorithme de Gall appelé forêts de Hough. Notre but est de réduire l'espace de caractéristiques utilisé par Gall, en supprimant celles de type HOG, pour ne garder que les dérivées partielles et les caractéristiques de couleur. Pour compenser cette réduction, nous avons amélioré deux étapes de l'entraînement : le support des descripteurs locaux (patchs) est partiellement produit selon une mesure géométrique, et l'entraînement des nœuds se fait en générant une carte de probabilité spécifique prenant en compte les patchs utilisés pour cette étape. Avec l'espace de caractéristiques réduit, le détecteur n'est pas plus précis. Avec les mêmes caractéristiques que Gall, sur une même durée d'entraînement, nos travaux ont permis d'avoir des résultats identiques, mais avec une variance plus faible et donc une meilleure répétabilité. / Visual representation is a fundamental problem in computer vision. The aim is to reduce the information to the strict necessary for a query task. Many types of representation exist, like color features (histograms, color attributes...), shape ones (derivatives, keypoints...) or filterbanks.Low-level (and local) features are fast to compute. Their power of representation are limited, but their genericity have an interest for autonomous or multi-task systems, as higher level ones derivate from them. We aim to build, then study impact of low-level and local feature spaces (color and derivatives only) for two tasks: generic object tracking, requiring features robust to object and environment's aspect changes over the time; object detection, for which the representation should describe object class and cope with intra-class variations.Then, rather than using global object descriptors, we use entirely local features and statisticals mecanisms to estimate their distribution (histograms) and their co-occurrences (Generalized Hough Transform).The Generalized Hough Transform (GHT), created for detection of any shape, consists in building a codebook, originally indexed by gradient orientation, then to diverse features, modeling an object, a class. As we work on local features, we aim to remain close to the original GHT.In tracking, after presenting preliminary works combining the GHT with a particle filter (using color histograms), we present a lighter and fast (100 fps) tracker, more accurate and robust.We present a qualitative evaluation and study the impact of used features (color space, spatial derivative formulation).In detection, we used Gall's Hough Forest. We aim to reduce Gall's feature space and discard HOG features, to keep only derivatives and color ones.To compensate the reduction, we enhanced two steps: the support of local descriptors (patches) are partially chosen using a geometrical measure, and node training is done by using a specific probability map based on patches used at this step.With reduced feature space, the detector is less accurate than with Gall's feature space, but for the same training time, our works lead to identical results, but with higher stability and then better repeatability.

Les interfaces cerveau-machine (ICMs) nous offrent un moyen de fermer la boucle entre notre cerveau et le monde de la technologie numérique. Cela ouvre la porte à une pléthore de nouvelles applications où nous utilisons directement le cerveau comme entrée. S’il est facile de voir le potentiel, il est moins facile de trouver la bonne application avec les bons corrélats neuronaux pour construire un tel système en boucle fermée. Ici, nous explorons une tâche de suivi d’objets multiples en 3D, dans un contexte d’entraînement cognitif (3D-MOT). Notre capacité à suivre plusieurs objets dans un environnement dynamique nous permet d’effectuer des tâches quotidiennes telles que conduire, pratiquer des sports d’équipe et marcher dans un centre commercial achalandé. Malgré plus de trois décennies de littérature sur les tâches MOT, les mécanismes neuronaux sous- jacents restent mal compris. Ici, nous avons examiné les corrélats neuronaux via l’électroencéphalographie (EEG) et leurs changements au cours des trois phases d’une tâche de 3D-MOT, à savoir l’identification, le suivi et le rappel. Nous avons observé ce qui semble être un transfert entre l’attention et la de mémoire de travail lors du passage entre le suivi et le rappel. Nos résultats ont révélé une forte inhibition des fréquences delta et thêta de la région frontale lors du suivi, suivie d’une forte (ré)activation de ces mêmes fréquences lors du rappel. Nos résultats ont également montré une activité de retard contralatérale (CDA en anglais), une activité négative soutenue dans l’hémisphère contralatérale aux positions des éléments visuels à suivre. Afin de déterminer si le CDA est un corrélat neuronal robuste pour les tâches de mémoire de travail visuelle, nous avons reproduit huit études liées au CDA avec un ensemble de données EEG accessible au public. Nous avons utilisé les données EEG brutes de ces huit études et les avons analysées avec le même pipeline de base pour extraire le CDA. Nous avons pu reproduire les résultats de chaque étude et montrer qu’avec un pipeline automatisé de base, nous pouvons extraire le CDA. Récemment, l’apprentissage profond (deep learning / DL en anglais) s’est révélé très prometteur pour aider à donner un sens aux signaux EEG en raison de sa capacité à apprendre de bonnes représentations à partir des données brutes. La question à savoir si l’apprentissage profond présente vraiment un avantage par rapport aux approches plus traditionnelles reste une question ouverte. Afin de répondre à cette question, nous avons examiné 154 articles appliquant le DL à l’EEG, publiés entre janvier 2010 et juillet 2018, et couvrant différents domaines d’application tels que l’épilepsie, le sommeil, les interfaces cerveau-machine et la surveillance cognitive et affective. Enfin, nous explorons la possibilité de fermer la boucle et de créer un ICM passif avec une tâche 3D-MOT. Nous classifions l’activité EEG pour prédire si une telle activité se produit pendant la phase de suivi ou de rappel de la tâche 3D-MOT. Nous avons également formé un classificateur pour les essais latéralisés afin de prédire si les cibles étaient présentées dans l’hémichamp gauche ou droit en utilisant l’activité EEG. Pour la classification de phase entre le suivi et le rappel, nous avons obtenu un 80% lors de l’entraînement d’un SVM sur plusieurs sujets en utilisant la puissance des bandes de fréquences thêta et delta des électrodes frontales. / Brain-computer interfaces (BCIs) offer us a way to close the loop between our brain and the digital world of technology. It opens the door for a plethora of new applications where we use the brain directly as an input. While it is easy to see the disruptive potential, it is less so easy to find the right application with the right neural correlates to build such closed-loop system. Here we explore closing the loop during a cognitive training 3D multiple object tracking task (3D-MOT). Our ability to track multiple objects in a dynamic environment enables us to perform everyday tasks such as driving, playing team sports, and walking in a crowded mall. Despite more than three decades of literature on MOT tasks, the underlying and intertwined neural mechanisms remain poorly understood. Here we looked at the electroencephalography (EEG) neural correlates and their changes across the three phases of a 3D-MOT task, namely identification, tracking and recall. We observed what seems to be a handoff between focused attention and working memory processes when going from tracking to recall. Our findings revealed a strong inhibition in delta and theta frequencies from the frontal region during tracking, followed by a strong (re)activation of these same frequencies during recall. Our results also showed contralateral delay activity (CDA), a sustained negativity over the hemisphere contralateral to the positions of visual items to be remembered. In order to investigate if the CDA is a robust neural correlate for visual working memory (VWM) tasks, we reproduced eight CDA-related studies with a publicly accessible EEG dataset. We used the raw EEG data from these eight studies and analysed all of them with the same basic pipeline to extract CDA. We were able to reproduce the results from all the studies and show that with a basic automated EEG pipeline we can extract a clear CDA signal. Recently, deep learning (DL) has shown great promise in helping make sense of EEG signals due to its capacity to learn good feature representations from raw data. Whether DL truly presents advantages as compared to more traditional EEG processing approaches, however, remains an open question. In order to address such question, we reviewed 154 papers that apply DL to EEG, published between January 2010 and July 2018, and spanning different application domains such as epilepsy, sleep, brain-computer interfacing, and cognitive and affective monitoring. Finally, we explore the potential for closing the loop and creating a passive BCI with a 3D-MOT task. We classify EEG activity to predict if such activity is happening during the tracking or the recall phase of the 3D-MOT task. We also trained a classifier for lateralized trials to predict if the targets were presented on the left or right hemifield using EEG brain activity. For the phase classification between tracking and recall, we obtained 80% accuracy when training a SVM across subjects using the theta and delta frequency band power from the frontal electrodes and 83% accuracy when training within subjects.

No description available.