Recently, there is a great interest in moving object tracking in the fields of security and surveillance. Object recognition under partial occlusion is the core of any object tracking system. This thesis presents an automatic and real-time color object-recognition system which is not only robust but also occlusion tolerant. The intended use of the system is to recognize and track external vehicles entered inside a secured area like a school campus or any army base. Statistical morphological skeleton is used to represent the visible shape of the vehicle. Simple curve matching and different feature based matching techniques are used to recognize the segmented vehicle. Features of the vehicle are extracted upon entering the secured area. The vehicle is recognized from either a digital video frame or a static digital image when needed. The recognition engine will help the design of a high performance tracking system meant for remote video surveillance.

Did you stand at a door with a bunch of keys and tried to find the right one to unlock the door? Did you hold a flower and wonder the name of it? A need of object recognition could rise anytime and any where in our daily lives. With the development of mobile devices object recognition applications become possible to provide immediate assistance. However, performing complex tasks in even the most advanced mobile platforms still faces great challenges due to the limited computing resources and computing power. In this thesis, we present an object recognition system that resides and executes within a mobile device, which can efficiently extract image features and perform learning and classification. To account for the computing constraint, a novel feature extraction method that minimizes the data size and maintains data consistency is proposed. This system leverages principal component analysis method and is able to update the trained classifier when new examples become available . Our system relieves users from creating a lot of examples and makes it user friendly. The experimental results demonstrate that a learning method trained with a very small number of examples can achieve recognition accuracy above 90% in various acquisition conditions. In addition, the system is able to perform learning efficiently.

Human adolescents exhibit higher levels of sensation seeking behaviour than younger or older individuals, and sensation seeking is higher in males than females from adolescence onwards. Data suggest that changes in gonadal hormone levels during adolescence and differences in the dopamine neurotransmitter system are the bases for why some people exhibit sensation seeking behaviour while others do not. However, causal relationships between physiology and behaviour have been difficult to establish in humans. In order to explore the physiological influences on novelty-seeking behaviour, we looked at response to novelty in a laboratory rodent. This research examined responses to novelty in the conditioned place preference (CPP) task and the novel object recognition (NOR) task in Lister-hooded rats, and assessed the benefits and limitations of each methodology. While the CPP task was not found to provide a reliable measure of response to novelty, the NOR task was more successful. In order to understand the ontogeny of sex differences in novelty responses, both males and females were tested from adolescence through to adulthood. While no sex difference was found in adults in the NOR test, mid-adolescent males exhibited higher novelty preference behaviour than either younger or older males, or females at each stage of development. Since gonadal hormones levels rise during adolescence, a pharmacological agent (a gonadotrophin-releasing hormone antagonist) was used to suppress gonadal hormone levels from early adolescence before again examining responses on the NOR test at mid-adolescence. Gonadal hormone suppression from early adolescence onwards eliminated the sex difference in the NOR test at mid-adolescence by reducing the male response to novelty, while no difference was measured in the female animals. These findings suggest that gonadal hormones play a significant role in the development of response to novelty, especially in males, and the implications for our understanding of human sensation-seeking behaviour are discussed.

Two important components of a visual recognition system are representation and model. Both involves the selection and learning of the features that are indicative for recognition and discarding those features that are uninformative. This thesis, in its general form, proposes different techniques within the frameworks of two learning systems for representation and modeling. Namely, latent support vector machines (latent SVMs) and deep learning. First, we propose various approaches to group the positive samples into clusters of visually similar instances. Given a fixed representation, the sampled space of the positive distribution is usually structured. The proposed clustering techniques include a novel similarity measure based on exemplar learning, an approach for using additional annotation, and augmenting latent SVM to automatically find clusters whose members can be reliably distinguished from background class.  In another effort, a strongly supervised DPM is suggested to study how these models can benefit from privileged information. The extra information comes in the form of semantic parts annotation (i.e. their presence and location). And they are used to constrain DPMs latent variables during or prior to the optimization of the latent SVM. Its effectiveness is demonstrated on the task of animal detection. Finally, we generalize the formulation of discriminative latent variable models, including DPMs, to incorporate new set of latent variables representing the structure or properties of negative samples. Thus, we term them as negative latent variables. We show this generalization affects state-of-the-art techniques and helps the visual recognition by explicitly searching for counter evidences of an object presence. Following the resurgence of deep networks, in the last works of this thesis we have focused on deep learning in order to produce a generic representation for visual recognition. A Convolutional Network (ConvNet) is trained on a largely annotated image classification dataset called ImageNet with $\sim1.3$ million images. Then, the activations at each layer of the trained ConvNet can be treated as the representation of an input image. We show that such a representation is surprisingly effective for various recognition tasks, making it clearly superior to all the handcrafted features previously used in visual recognition (such as HOG in our first works on DPM). We further investigate the ways that one can improve this representation for a task in mind. We propose various factors involving before or after the training of the representation which can improve the efficacy of the ConvNet representation. These factors are analyzed on 16 datasets from various subfields of visual recognition. / <p>QC 20160908</p>

With the advent of ever smaller and more powerful portable computing devices, and ever smaller cameras, wearable computing is becoming more feasible. The ever increasing numbers of augmented reality applications are allowing users to view additional data about their world overlaid on their world using portable computing devices. The main aim of this research is to enable a user of a wearable robot to explore large environments automatically viewing augmented reality at locations and on objects of interest. To implement this research a wearable visual robotic assistant is designed and constructed. Evaluation of the different technologies results in a final design that combines a shoulder mounted self stabilizing active camera, and a hand held magic lens into a single portable system. To enable the wearable assistant to locate known objects, a system is designed that combines an established method for appearance-based recognition with one for simultaneous localization and mapping using a single camera. As well as identifying planar objects, the objects are located relative to the camera in 3D by computing the image-to-database homography. The 3D positions of the objects are then used as additional measurements in the SLAM process, which routinely uses other point features to acquire and maintain a map of the surroundings, irrespective of whether objects are present or not. The monocular SLAM system is then replaced with a new method for building maps and tracking. Instead of tracking and mapping in a linear frame-rate driven manner, this adopted method separates the mapping from the tracking. This allows higher density maps to be constructed, and provides more robust tracking. The flexible framework provided by this method is extended to support multiple independent cameras, and multiple independent maps, allowing the user of the wearable two-camera robot to escape the confines of the desk top and explore arbitrarily sized environments. The final part of the work brings together the parallel tracking and multiple mapping system with the recognition and localization of planar objects from a database. The method is able to build multiple feature rich maps of the world and simultaneously recognize, reconstruct and localize objects within these maps. The object reconstruction process uses the spatially separated keyframes from the tracking and mapping processes to recognize and localize known objects in the world. These are then used for augmented reality overlays related to the objects.

Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal.

La capacité du système visuel humain à compléter une image partiellement dévoilée et à en dériver une forme globale à partir de ses fragments visibles incomplets est un phénomène qui suscite, jusqu’à nos jours, l’intérêt de nombreux scientifiques œuvrant dans différents milieux de recherche tels que l’informatique, l’ingénierie en intelligence artificielle, la perception et les neurosciences. Dans le cadre de la présente thèse, nous nous sommes intéressés spécifiquement sur les substrats neuronaux associés à ce phénomène de clôture perceptive. La thèse actuelle a donc pour objectif général d’explorer le décours spatio-temporel des corrélats neuronaux associés à la clôture perceptive au cours d’une tâche d’identification d’objets. Dans un premier temps, le premier article visera à caractériser la signature électrophysiologique liée à la clôture perceptive chez des personnes à développement typique dans le but de déterminer si les processus de clôture perceptive reflèteraient l’interaction itérative entre les mécanismes de bas et de haut-niveau et si ceux-ci seraient sollicités à une étape précoce ou tardive lors du traitement visuel de l’information. Dans un deuxième temps, le second article a pour objectif d’explorer le décours spatio-temporel des mécanismes neuronaux sous-tendant la clôture perceptive dans le but de déterminer si les processus de clôture perceptive des personnes présentant un trouble autistique se caractérisent par une signature idiosyncrasique des changements d’amplitude des potentiels évoqués (PÉs). En d’autres termes, nous cherchons à déterminer si la clôture perceptive en autisme est atypique et nécessiterait davantage la contribution des mécanismes de bas-niveau et/ou de haut-niveau. Les résultats du premier article indiquent que le phénomène de clôture perceptive est associé temporellement à l’occurrence de la composante de PÉs N80 et P160 tel que révélé par des différences significatives claires entre des objets et des versions méconnaissables brouillées. Nous proposons enfin que la clôture perceptive s’avère un processus de transition reflétant les interactions proactives entre les mécanismes neuronaux œuvrant à apparier l’input sensoriel fragmenté à une représentation d’objets en mémoire plausible. Les résultats du second article révèlent des effets précoces de fragmentation et d’identification obtenus au niveau de composantes de potentiels évoqués N80 et P160 et ce, en toute absence d’effets au niveau des composantes tardives pour les individus avec autisme de haut niveau et avec syndrome d’Asperger. Pour ces deux groupes du trouble du spectre autistique, les données électrophysiologiques suggèrent qu’il n’y aurait pas de pré-activation graduelle de l’activité des régions corticales, entre autres frontales, aux moments précédant et menant vers l’identification d’objets fragmentés. Pour les participants autistes et avec syndrome d’Asperger, les analyses statistiques démontrent d’ailleurs une plus importante activation au niveau des régions postérieures alors que les individus à développement typique démontrent une activation plus élevée au niveau antérieur. Ces résultats pourraient suggérer que les personnes du spectre autistique se fient davantage aux processus perceptifs de bas-niveau pour parvenir à compléter les images d’objets fragmentés. Ainsi, lorsque confrontés aux images d’objets partiellement visibles pouvant sembler ambiguës, les individus avec autisme pourraient démontrer plus de difficultés à générer de multiples prédictions au sujet de l’identité d’un objet qu’ils perçoivent. Les implications théoriques et cliniques, les limites et perspectives futures de ces résultats sont discutées. / The human visual system has come to prevail over partially hidden boundaries and edges of objects in order to render a unified and holistic representation of the surrounding world. This phenomenon, also referred to as perceptual closure, was further investigated in the context of this current thesis. More precisely, this doctoral thesis aimed at examining the neural mechanisms underlying perceptual closure processes. In order to achieve this goal, the first study to track the spatio-temporal dynamics of electrical brain activity during a pictorial object recognition task to determine whether closure processes are reflect an interplay between low-level and higher-level mechanisms and whether they are solicited during early or late stages of visual processing. We found that perceptual closure is temporally linked to the occurrence of the N80 and P160 which is the earliest negative ERP component sensitive to closure processes reported until now in previous similar studies. Results indicate that closure processes are implicated earlier during visual processing of fragmented object images. We propose here that perceptual closure is a transitional process that reflects the proactive interactions between neural mechanisms trying to match fragmented current sensory input with memory representations. Furthermore, the second study sought to explore the time-course of neural correlates underpinning perceptual closure, during an object recognition task, to determine whether closure processes are associated with an abrupt or gradual change in ERP responses in adults with high functioning autism (HFA), Asperger’s Syndrome (AS) and in typically developing (TD) individuals. We found that, in individuals with HFA and AS, perceptual closure was associated with changes in early ERP (N80 and P160) responses for fragmentation and identification effects, while there were no significant modulations of later ERP responses. However, for TD individuals, perceptual closure was characterized by significant differences in early ERP responses (N80 and P160) between objects and non-objects as well as gradual modulations in late ERP responses for identification effects (450-550ms). Our results suggest that adults with autism rely mostly on low-level processes to achieve closure and do not illustrate the characteristic interplay between early and late ERP responses observed in typically developed individuals, thus revealing the atypicality of perceptual closure mechanisms in this population. We propose here that the interactive matching of incoming fragmented visual information with corresponding candidate object representations is atypical in individuals with autism. Following these articles, we will discuss the theoretical and clinical implications of this work. Finally, we will also propose limitations within our studies and discuss new perspectives for future research.

Notre système visuel extrait d'ordinaire l'information en basses fréquences spatiales (FS) avant celles en hautes FS. L'information globale extraite tôt peut ainsi activer des hypothèses sur l'identité de l'objet et guider l'extraction d'information plus fine spécifique par la suite. Dans les troubles du spectre autistique (TSA), toutefois, la perception des FS est atypique. De plus, la perception des individus atteints de TSA semble être moins influencée par leurs a priori et connaissances antérieures. Dans l'étude décrite dans le corps de ce mémoire, nous avions pour but de vérifier si l'a priori de traiter l'information des basses aux hautes FS était présent chez les individus atteints de TSA. Nous avons comparé le décours temporel de l'utilisation des FS chez des sujets neurotypiques et atteints de TSA en échantillonnant aléatoirement et exhaustivement l'espace temps x FS. Les sujets neurotypiques extrayaient les basses FS avant les plus hautes: nous avons ainsi pu répliquer le résultat de plusieurs études antérieures, tout en le caractérisant avec plus de précision que jamais auparavant. Les sujets atteints de TSA, quant à eux, extrayaient toutes les FS utiles, basses et hautes, dès le début, indiquant qu'ils ne possédaient pas l'a priori présent chez les neurotypiques. Il semblerait ainsi que les individus atteints de TSA extraient les FS de manière purement ascendante, l'extraction n'étant pas guidée par l'activation d'hypothèses. / Our visual system usually samples low spatial frequency (SF) information before higher SF information. The coarse information thereby extracted can activate hypotheses in regard to the object's identity and guide further extraction of specific finer information. In autism spectrum disorder (ASD) however, SF perception is atypical. Moreover, individuals with ASD seem to rely less on their prior knowledge when perceiving objects. In the present study, we aimed to verify if the prior according to which we sample visual information in a coarse-to-fine fashion is existent in ASD. We compared the time course of SF sampling in neurotypical and ASD subjects by randomly and exhaustively sampling the SF x time space. Neurotypicals were found to sample low SFs before higher ones, thereby replicating the finding from many other studies, but characterizing it with much greater precision. ASD subjects were found, for their part, to extract SFs in a more fine-to-coarse fashion, extracting all relevant SFs upon beginning. This indicated that they did not possess a coarse-to-fine prior. Thus, individuals with ASD seem to sample information in a purely bottom-up fashion, without the guidance from hypotheses activated by coarse information.

Dans cette thèse, nous présentons tout d'abord une contribution visant à pallier ce problème de robustesse pour la reconnaissance d'instances, puis une extension directe de cette contribution à la reconnaissance et la localisation de classes d'objets. Dans un premier temps, nous avons développé une méthode inspiré de l'appariement de graphe (i.e. graph matching) afin de traiter le problème de la reconnaissance rapide d'instances d'objets spécifiques dans des conditions bruitées. Cette méthode permet de rajouter facilement un nombre quelconque d’autres types de caractéristiques locales (e.g. contours, textures…) moins affectées par le bruit tout en contournant le problème de la normalisation et sans pénaliser la vitesse de détection. Nos expériences sur plusieurs bases de test ont montré la pertinence de notre approche. Notre approche est globalement légèrement moins robuste à l'occultation que les approches existantes, mais elle produit des performances supérieures aux approches standard en conditions bruitées. Dans un second temps, nous avons développé une approche pour la détection de classes d'objets dans le même esprit que celui du sac de mots visuels. Pour cela, nous utilisons nos cascades de micro-classifieurs pour reconnaître des mots visuels plus distinctifs que les mots basés simplement sur des points d'intérêts. L'apprentissage se divise en deux parties: dans un premier temps, nous générons des cascades de micro-classifieurs servant à reconnaître des parties locales des images modèles ; puis dans un second temps, nous utilisons un classifieur afin de modéliser la frontière de décision entre les images de classe et celles de non-classe. Nous montrons que l'association de mots classiques (à partir de points d'intérêts) et de nos mots plus distincts produit une amélioration significative des performances pour un temps de calcul assez faible. / In this thesis, we first present a contribution to overcome this problem of robustness for the recognition of object instances, then we straightly extend this contribution to the detection and localization of classes of objects. In a first step, we have developed a method inspired by graph matching to address the problem of fast recognition of instances of specific objects in noisy conditions. This method allows to easily combine any types of local features (eg contours, textures ...) less affected by noise than keypoints, while bypassing the normalization problem and without penalizing too much the detection speed. Unlike other methods based on a global rigid transformation, our approach is robust to complex deformations such as those due to perspective or those non-rigid inherent to the model itself (e.g. a face, a flexible magazine). Our experiments on several datasets have showed the relevance of our approach. It is overall slightly less robust to occlusion than existing approaches, but it produces better performances in noisy conditions. In a second step, we have developed an approach for detecting classes of objects in the same spirit as the bag-of-visual-words model. For this we use our cascaded micro-classifiers to recognize visual words more distinctive than the classical words simply based on visual dictionaries. Training is divided into two parts: First, we generate cascades of micro-classifiers for recognizing local parts of the model pictures and then in a second step, we use a classifier to model the decision boundary between images of class and those of non-class. We show that the association of classical visual words (from keypoints patches) and our disctinctive words results in a significant improvement. The computation time is generally quite low, given the structure of the cascades that minimizes the detection time and the form of the classifier is extremely fast to evaluate.

Submitted by Marcos Anselmo (marcos.anselmo@unipampa.edu.br) on 2018-09-27T15:14:42Z No. of bitstreams: 1 MARIZA LIMA.pdf: 1903438 bytes, checksum: 3dd92f0052ecc6a9e39c2d2a9519ff7d (MD5) / Approved for entry into archive by Marcos Anselmo (marcos.anselmo@unipampa.edu.br) on 2018-09-27T15:15:30Z (GMT) No. of bitstreams: 1 MARIZA LIMA.pdf: 1903438 bytes, checksum: 3dd92f0052ecc6a9e39c2d2a9519ff7d (MD5) / Made available in DSpace on 2018-09-27T15:15:30Z (GMT). No. of bitstreams: 1 MARIZA LIMA.pdf: 1903438 bytes, checksum: 3dd92f0052ecc6a9e39c2d2a9519ff7d (MD5) Previous issue date: 2017 / A Doença de Alzheimer (DA) é uma enfermidade incurável que causa perda das funções cognitivas (memória, orientação, atenção e linguagem). As lesões cerebrais são características dessa doença, sendo as principais alterações: as placas senis decorrentes do depósito de proteína beta-amiloide (βa) anormalmente produzida, e os emaranhados neurofibrilares. Atualmente, muitas abordagens são propostas para tratar ou prevenir a DA, mas os estudos geralmente usam protocolos que dificilmente permitem o estabelecimento da relação causa-efeito, pois envolvem mais de uma variável que poderia ter benefícios no cérebro com DA. O objetivo deste trabalho foi avaliar e isolar os efeitos neuroprotetores do enriquecimento ambiental, do exercício físico anaeróbio, e do enriquecimento social, em déficits de memória relacionados à neurotoxicidade induzida pela beta-amiloide (βa) em um modelo animal. Para isto, foram utilizados ratos Wistar submetidos às intervenções propostas por 8 semanas, e, logo após, à cirurgia estereotáxica para a injeção de βa no hipocampo. A memória foi avaliada pelos testes de reconhecimento de objetos e reconhecimento social, considerando memória de curta e de longa duração. O estado de oxidativo do hipocampo (níveis de espécies reativas de oxigênio, peroxidação lipídica e capacidade antioxidante total - ROS, TBARS e FRAP) e a atividade da enzima acetilcolinesterase (AChE) também foram verificados. Os dados mostram que a injeção de βa resultou em déficits de memória e danos oxidativos no hipocampo. O enriquecimento ambiental e o exercício físico 8 evitaram todos os déficits de memória e a peroxidação lipídica (TBARS) hipocampal induzida por βa. O enriquecimento social evitou apenas o déficit de memória de reconhecimento social induzido pela beta-amiloide e aumentou a capacidade antioxidante total (FRAP). / Alzheimer's Disease (AD) is an incurable disease that causes loss of cognitive functions (memory, orientation, attention, and language). Brain lesions are characteristic of this disease, in which main alterations being: senile plaques arisvel from the deposition of abnormally produced beta-amyloid protein (βa) and neurofibrillary tangles. Many approaches have been proposed to treat or prevent AD, but studies generally use protocols that becouse difficult to attribute a cause-effect relationship because they involve more than one variable that could be benefical in observed changes. The objective of this work was to evaluate and isolate the neuroprotective effects of environmental enrichment, anaerobic physical exercise, and social enrichment on memory deficits related to beta-amyloid neurotoxicity in an animal model. For this, Wistar rats were submitted to 8 weeks of intervention, and soon thereafter underwent stereotactic surgery for the injection of βa into the hippocampus. The memory was evaluated by object recognition and social recognition memory tests, considering short and long term memory. The oxidative state of the hippocampus (ROS, TBARS and FRAP) and acetylcholinesterase (AChE) activity are also verified. The data show that the injection of βa resulted in memory deficits and oxidative damage in the hippocampus. Environmental enrichment and exercise avoided all memory deficits and hippocampal lipid peroxidation (TBARS) induced by βa. Social enrichment avoided only the social 10 recognition memory deficit and avoided the total antioxidant capacity (FRAP) decrease induced by βa.