Today's smartphones are capable of accomplishing far more advanced tasks than reading emails. With the modern framework TensorFlow, visual object recognition becomes possible using smartphone resources. This thesis shows that the main challenge does not lie in developing an artifact which performs visual object recognition. Instead, the main challenge lies in developing an ecosystem which allows for continuous improvement of the system’s ability to accomplish the given task without laborious and inefficient data collection. This thesis presents four design principles which contribute to an efficient ecosystem with quick initiation of new object classes and efficient data collection which is used to continuously improve the system’s ability to recognize smart meters in varying environments in an automated fashion.

Les études sont mitigées sur les séquelles cognitives des commotions cérébrales, certaines suggèrent qu’elles se résorbent rapidement tandis que d’autres indiquent qu’elles persistent dans le temps. Par contre, aucunes données n’existent pour indiquer si une tâche cognitive comme l’imagerie mentale visuelle fait ressortir des séquelles à la suite d’une commotion cérébrale. Ainsi, la présente étude a pour objet d’évaluer l’effet des commotions cérébrales d’origine sportive sur la capacité d’imagerie mentale visuelle d’objets et d’imagerie spatiale des athlètes. Afin de répondre à cet objectif, nous comparons les capacités d’imagerie mentale chez des joueurs de football masculins de calibre universitaire sans historique répertorié de commotions cérébrales (n=15) et chez un second groupe d’athlète ayant été victime d’au moins une commotion cérébrale (n=15). Notre hypothèse est que les athlètes non-commotionnés ont une meilleure imagerie mentale que les athlètes commotionnés. Les résultats infirment notre hypothèse. Les athlètes commotionnés performent aussi bien que les athlètes non-commotionnés aux trois tests suivants : Paper Folding Test (PFT), Visual Object Identification Task (VOIT) et Vividness of Visual Imagery Questionnaire (VVIQ). De plus, ni le nombre de commotions cérébrales ni le temps écoulé depuis la dernière commotion cérébrale n’influent sur la performance des athlètes commotionnés. / The research is mitigated on the cognitive after-effects of a concussion. Some studies suggest the effects disappear rapidly whereas others observe a continuation in their manifestation. However, no research has been done to indicate whether a cognitive task like mental imagery brings out these effects following a concussion. This study will evaluate the effects of sport-related concussions on object and spatial visual mental imagery of athletes. To achieve this goal, we compare the mental imagery capacity between two groups of male football athletes of University level. The first group (n=15) with no history of concussions and the second group (n=15) with one or more concussions. We hypothesize that the non-concussed athletes visualize better than the concussed athletes. Our results invalidate our hypothesis. Both groups have similar results on the three following measures: Paper Folding Test (PFT), Visual Object Identification Task (VOIT) and Vividness of Visual Imagery Questionnaire (VVIQ). Furthermore, the quantity of concussions and the time past since the last concussion seems to have no impact on the visual mental imagery performance of concussed athletes.

The effects of feature frequency and similarity on object recognition have been examined through behavioral experiments, and a model of the formation of visual object representations and old/new recognition has been proposed. A number of experiments were conducted to test the hypothesis that frequency and similarity of object features affect the old/new responses to test stimuli in a later recognition task. In the first experiment, when the feature frequencies are controlled, there was a significant increase in the percentage of &ldquo / old&rdquo / responses for unstudied objects as the number of frequently repeated features (FRFs) on the object increased. In the second experiment, where all features had equal frequency, similarity of test objects did not affect old/new responses. An evaluation of the models on object recognition and categorization with respect to the experimental results showed that these models can only partially explain experimental results. A comprehensive model for the formation of visual object representations and old/new recognition, called CDZ-VIS, developed on the Convergence-Divergence Zone framework by Damasio (1989), has been proposed. According to this framework, co-occurring object features converge to upper layer units in the hierarchical representation which act as binding units. As more objects are displayed, frequent object features cause grouping of these binding units which converge to upper binding units. The performance of the CDZ-VIS model on the feature frequency and similarity experiments of the present study was shown to be closer to the performance of the human participants, compared to the performance of two models from the categorization literature.

Humans can visually track objects mostly effortlessly. However, it is hard for a computer to track a fast moving object under varying illumination and occlusions, in clutter, and with varying appearance in camera projective space due to its relaxed rigidity or change in viewpoint. Since a generic, precise, robust, and fast tracker could trigger many applications, object tracking has been a fundamental problem of practical importance since the beginnings of computer vision. The first contribution of the thesis is a computationally efficient approach to tracking objects of various shapes and motions. It describes a unifying tracking system that can be configured to track the pose of a deformable object in a low or high-dimensional state-space. The object is decomposed into a chained assembly of segments of multiple parts that are arranged under a hierarchy of tailored spatio-temporal constraints. The robustness and generality of the approach is widely demonstrated on tracking various flexible and articulated objects. Haar-like features are widely used in tracking. The second contribution of the thesis is a parser of ensembles of Haar-like features to compute them efficiently. The features are decomposed into simpler kernels, possibly shared by subsets of features, thus forming multi-pass convolutions. Discovering and aligning these kernels within and between passes allows forming recursive trees of kernels that require fewer memory operations than the classic computation, thereby producing the same result but more efficiently. The approach is validated experimentally on popular examples of Haar-like features

Mapas topologicamente ordenados sÃo tÃcnicas de representaÃÃo de dados baseadas em reduÃÃo de dimensionalidade com a propriedade especial de preservaÃÃo da vizinhanÃa espacial entre os protÃtipos no espaÃo dos dados e entre suas respectivas posiÃÃes no espaÃo de saÃda. Com base nesta propriedade, mapas topologicamente ordenados sÃo aplicados principalmente em agrupamento, quantizaÃÃo vetorial ou reduÃÃo de dimensionalidade e visualizaÃÃo de dados. Esta tese propÃe uma nova classificaÃÃo para os algoritmos de formaÃÃo de mapas topologicamente ordenados baseada no mecanismo de correlaÃÃo entre os espaÃos de entrada e de saÃda, e descreve um novo algoritmo, baseado em computaÃÃo evolucionÃria, denominado EvSOM, para a formaÃÃo de mapas topologicamente ordenado. As principais propriedades do novo algoritmo sÃo a sua flexibilidade para ponderaÃÃo pelo usuÃrio da importÃncia relativa das propriedades de quantizaÃÃo vetorial e de preservaÃÃo de topologia no mapa final, alÃm de boa rejeiÃÃo a outliers quando comparado ao algoritmo SOM de Kohonen. O trabalho desenvolve uma avaliaÃÃo empÃrica destas propriedades. O EvSOM Ã um algoritmo hÃbrido, neural-evolucionÃrio, biologicamente inspirado, que se utiliza de conceitos de redes neurais competitivas, computaÃÃo evolucionÃria, otimizaÃÃo e aproximaÃÃo iterativa. Para validar sua viabilidade de aplicaÃÃo, o EvSOM Ã estendido e especializado para a soluÃÃo de dois problemas bÃsicos relevantes em processamento de imagens e visÃo computacional, quais sejam, o problema de registro de imagens mÃdicas e o problema de rastreamento visual de objetos em vÃdeo. O algoritmo apresentou desempenho satisfatÃrio nas duas aplicaÃÃes. / Topologically ordered maps are data representation techniques based on dimensionality reduction with the special property of preserving the neighborhood between the data prototypes lying in the data space and their positions on to the output space. Based on this property, topologically ordered maps are applied mainly in clustering projected, vector quantization or dimensionality reduction and data visualization. This thesis proposes a new classification for the existing algorithms devoted to the formation of topologically ordered maps, which is based on the mechanism of correlation between the input and output spaces, and describes a new algorithm based on evolutionary computation, called EvSOM, for the topologically ordered maps formation. The main properties of the new algorithm are its flexibility for consideration by the user of the relative importance of the properties of vector quantization and topology preservation of the final map, and good outliers rejection when compared to the Kohonen SOM algorithm. The work provides an empirical evaluation of these properties. The EvSOM is a hybrid , neural-evolutionary, biologically inspired algorithm, which uses concepts of competitive neural networks, evolutionary computing, optimization and iterative approximation approximation. To validate its application feasibility, EvSOM is extended and specialized to solve two relevant basic problems in image processing and computer vision, namely, the medical image registration problem and the visual tracking of objects in video problem. The algorithm exhibits satisfactory performance in both aplications.

Many methods have been developed for visual tracking of generic objects. The vast majority of these assume the world is two-dimensional, either ignoring the third dimension or only dealing with it indirectly. This causes difficulties for the tracker when the target approaches or moves away from the camera, is occluded or moves out of the camera frame. Unmanned aerial vehicles (UAVs) are increasingly used in civilian applications and some of these will undoubtedly carry tracking systems in the future. As they move around, these trackers will encounter both scale changes and occlusions. To improve the tracking performance in these cases, the third dimension should be taken into account. This thesis extends the capabilities of a 2D tracker to three dimensions, with the assumption that the target moves on a ground plane. The position of the tracker camera is established by matching the video it produces to a sparse point-cloud map built with off-the-shelf structure-from-motion software. A target is tracked with a generic 2D tracker and subsequently positioned on the ground. Should the target disappear from view, its motion on the ground is predicted. In combination, these simple techniques are shown to improve the robustness of a tracking system on a moving platform under target scale changes and occlusions.

Le suivi visuel d’objet est une fonction élémentaire de la vision par ordinateur ayant fait l’objet de nombreux travaux. La dérive au cours du temps est l'un des phénomènes les plus critiques à maîtriser, car elle aboutit à la perte définitive de la cible suivie. Malgré les nombreuses approches proposées dans la littérature pour contrer ce phénomène, aucune ne surpasse une autre en terme de robustesse face aux diverses sources de perturbations visuelles : variation d'illumination, occultation, mouvement brusque de caméra, changement d'aspect. L’objectif de cette thèse est d’exploiter la complémentarité d’un ensemble d'algorithmes de suivi, « trackers », en développant des stratégies de fusion en ligne capables de les combiner génériquement. La chaîne de fusion proposée a consisté à sélectionner les trackers à partir d'indicateurs de bon fonctionnement, à combiner leurs sorties et à les corriger. La prédiction en ligne de dérive a été étudiée comme un élément clé du mécanisme de sélection. Plusieurs méthodes sont proposées pour chacune des étapes de la chaîne, donnant lieu à 46 configurations de fusion possibles. Évaluées sur 3 bases de données, l’étude a mis en évidence plusieurs résultats principaux : une sélection performante améliore considérablement la robustesse de suivi ; une correction de mise à jour est préférable à une réinitialisation ; il est plus avantageux de combiner un petit nombre de trackers complémentaires et de performances homogènes qu'un grand nombre ; la robustesse de fusion d’un petit nombre de trackers est corrélée à la mesure d’incomplétude, ce qui permet de sélectionner la combinaison de trackers adaptée à un contexte applicatif donné. / Visual object tracking is an elementary function of computer vision that has been the subject of numerous studies. Drift over time is one of the most critical phenomena to master because it leads to the permanent loss of the target being tracked. Despite the numerous approaches proposed in the literature to counter this phenomenon, none outperforms another in terms of robustness to the various sources of visual perturbations: variation of illumination, occlusion, sudden movement of camera, change of aspect. The objective of this thesis is to exploit the complementarity of a set of tracking algorithms by developing on-line fusion strategies capable of combining them generically. The proposed fusion chain consists of selecting the trackers from indicators of good functioning, combining their outputs and correcting them. On-line drift prediction was studied as a key element of the selection mechanism. Several methods are proposed for each step of the chain, giving rise to 46 possible fusion configurations. Evaluated on 3 databases, the study highlighted several key findings: effective selection greatly improves robustness; The correction improves the robustness but is sensitive to bad selection, making updating preferable to reinitialization; It is more advantageous to combine a small number of complementary trackers with homogeneous performances than a large number; The robustness of fusion of a small number of trackers is correlated to the incompleteness measure, which makes it possible to select the appropriate combination of trackers to a given application context.

Until recently induced gamma-band activity (GBA) was considered a neural marker of cortical object representation. However, induced GBA in the electroencephalogram (EEG) is susceptible to artifacts caused by miniature fixational saccades. Recent studies have demonstrated that fixational saccades also reflect high-level representational processes. Do high-level as opposed to low-level factors influence fixational saccades? What is the effect of these factors on artifact-free GBA? To investigate this, we conducted separate eye tracking and EEG experiments using identical designs. Participants classified line drawings as objects or non-objects. To introduce low-level differences, contours were defined along different directions in cardinal color space: S-cone-isolating, intermediate isoluminant, or a full-color stimulus, the latter containing an additional achromatic component. Prior to the classification task, object discrimination thresholds were measured and stimuli were scaled to matching suprathreshold levels for each participant. In both experiments, behavioral performance was best for full-color stimuli and worst for S-cone isolating stimuli. Saccade rates 200–700 ms after stimulus onset were modulated independently by low and high-level factors, being higher for full-color stimuli than for S-cone isolating stimuli and higher for objects. Low-amplitude evoked GBA and total GBA were observed in very few conditions, showing that paradigms with isoluminant stimuli may not be ideal for eliciting such responses. We conclude that cortical loops involved in the processing of objects are preferentially excited by stimuli that contain achromatic information. Their activation can lead to relatively early exploratory eye movements even for foveally-presented stimuli.

Les humains sont capables de suivre visuellement des objets sans effort. Cependant les algorithmes de vision artificielle rencontrent des limitations pour suivre des objets en mouvement rapide, sous un éclairage variable, en présence d'occultations, dans un environnement complexe ou dont l'apparence varie à cause de déformations et de changements de point de vue. Parce que des systèmes génériques, précis, robustes et rapides sont nécessaires pour de nombreuses d’applications, le suivi d’objets reste un problème pratique important en vision par ordinateur. La première contribution de cette thèse est une approche calculatoire rapide pour le suivi d'objets de forme et de mouvement variable. Elle consiste en un système unifié et configurable pour estimer l'attitude d’un objet déformable dans un espace d'états de dimension petite ou grande. L’objet est décomposé en une suite de segments composés de parties et organisés selon une hiérarchie spatio-temporelle contrainte. L'efficacité et l’universalité de cette approche sont démontrées expérimentalement sur de nombreux exemples de suivi de divers objets flexibles et articulés. Les caractéristiques de Haar (HLF) sont abondement utilisées pour le suivi d’objets. La deuxième contribution est une méthode de décomposition des HLF permettant de les calculer de manière efficace. Ces caractéristiques sont décomposées en noyaux plus simples, éventuellement réutilisables, et reformulées comme des convolutions multi-passes. La recherche et l'alignement des noyaux dans et entre les passes permet de créer des arbres récursifs de noyaux qui nécessitent moins d’opérations en mémoire que les systèmes de calcul classiques, pour un résultat de convolution identique et une mise en œuvre plus efficace. Cette approche a été validée expérimentalement sur des exemples de HLF très utilisés / Humans can visually track objects mostly effortlessly. However, it is hard for a computer to track a fast moving object under varying illumination and occlusions, in clutter, and with varying appearance in camera projective space due to its relaxed rigidity or change in viewpoint. Since a generic, precise, robust, and fast tracker could trigger many applications, object tracking has been a fundamental problem of practical importance since the beginnings of computer vision. The first contribution of the thesis is a computationally efficient approach to tracking objects of various shapes and motions. It describes a unifying tracking system that can be configured to track the pose of a deformable object in a low or high-dimensional state-space. The object is decomposed into a chained assembly of segments of multiple parts that are arranged under a hierarchy of tailored spatio-temporal constraints. The robustness and generality of the approach is widely demonstrated on tracking various flexible and articulated objects. Haar-like features are widely used in tracking. The second contribution of the thesis is a parser of ensembles of Haar-like features to compute them efficiently. The features are decomposed into simpler kernels, possibly shared by subsets of features, thus forming multi-pass convolutions. Discovering and aligning these kernels within and between passes allows forming recursive trees of kernels that require fewer memory operations than the classic computation, thereby producing the same result but more efficiently. The approach is validated experimentally on popular examples of Haar-like features

Cette dissertation traite du problème du suivi d'objets visuels, dont le but est de localiser un objet et de déterminer sa trajectoire au cours du temps. En particulier, nous nous concentrons sur les scénarios difficiles, dans lesquels les objets subissent d'importantes déformations et occlusions, ou quittent le champs de vision. A cette fin, nous proposons deux méthodes robustes qui apprennent un modèle pour l'objet d'intérêt et le mettent à jour, afin de refléter ses changements au cours du temps.Notre première méthode traite du problème du suivi dans le cas où les objets subissent d'importantes transformations géométriques comme une rotation ou un changement d'échelle. Nous présentons un nouvel algorithme de sélection de propositions, qui étend l'approche traditionnelle de ``suivi par détection''. Cette méthode procède en deux étapes: proposition puis sélection. Dans l'étape de proposition, nous construisons un ensemble de candidats qui représente les localisations potentielles de l'objet en estimant de manière robuste les transformations géométriques. La meilleure proposition est ensuite sélectionnée parmi cet ensemble de candidats pour précisément localiser l'objet en utilisant des indices d'apparence et de mouvement.Dans un second temps, nous traitons du problème de la mise à jour de modèles dans le suivi visuel, c'est-à-dire de déterminer quand il est besoin de mettre à jour le modèle de la cible, lequel peut subir une occlusion, ou quitter le champs de vision. Pour résoudre cela, nous utilisons des indices de mouvement pour identifier l'état d'un objet de manière automatique et nous mettons à jour le modèle uniquement lorsque l'objet est entièrement visible. En particulier, nous utilisons des trajectoires à long terme ainsi qu'une technique basée sur la coup de graphes pour estimer les parties de l'objet qui sont visibles.Nous avons évalué nos deux approches de manière étendue sur différents bancs d'essai de suivi, en particulier sur le récent banc d'essai de suivi en ligne et le jeu de donnée du concours de suivi visuel. Nos deux approches se comparent favorablement à l'état de l'art et font montre d'améliorations significatives par rapport à plusieurs autres récents suiveurs. Notre soumission au concours de suivi d'objets visuels de 2015 a par ailleurs remporté l'une de ces compétitions. / In this dissertation we address the problem of visual object tracking, whereinthe goal is to localize an object and determine its trajectory over time. Inparticular, we focus on challenging scenarios where the object undergoessignificant transformations, becomes occluded or leaves the field of view. Tothis end, we propose two robust methods which learn a model for the object ofinterest and update it, to reflect its changes over time.Our first method addresses the tracking problem in the context of objectsundergoing severe geometric transformations, such as rotation, change in scale.We present a novel proposal-selection algorithm, which extends the traditionaldiscriminative tracking-by-detection approach. This method proceeds in twostages -- proposal followed by selection. In the proposal stage, we compute acandidate pool that represents the potential locations of the object byrobustly estimating the geometric transformations. The best proposal is thenselected from this candidate set to localize the object precisely usingmultiple appearance and motion cues.Second, we consider the problem of model update in visual tracking, i.e.,determining when to update the model of the target, which may become occludedor leave the field of view. To address this, we use motion cues to identify thestate of the object in a principled way, and update the model only when theobject is fully visible. In particular, we utilize long-term trajectories incombination with a graph-cut based technique to estimate parts of the objectsthat are visible.We have evaluated both our approaches extensively on several trackingbenchmarks, notably, recent online tracking benchmark and the visual objecttracking challenge datasets. Both our approaches compare favorably to thestate of the art and show significant improvement over several other recenttrackers. Specifically, our submission to the visual object tracking challengeorganized in 2015 was the winner in one of the competitions.