Ces technologies ont poussé les chercheurs à imaginer la possibilité d'automatiser et émuler les capacités de perception visuels des animaux et de l'homme lui-même. Depuis quelques décennies le domaine de la vision par ordinateur a essayé plusieurs approches et une vaste gamma d'applications a été développée avec un succès partielle: la recherche des images basé sur leur contenu, la exploration de donnés à partir des séquences vidéo, la ré-identification des objets par des robots, etc. Quelques applications sont déjà sur le marché et jouissent déjà d'un certain succès commercial.La reconnaissance visuelle c'est un problème étroitement lié à l'apprentissage de catégories visuelles à partir d'un ensemble limité d'instances. Typiquement deux approches sont utilisées pour résoudre ce problème: l'apprentissage des catégories génériques et la ré-identification d'instances d'un objet un particulière. Dans le dernier cas il s'agit de reconnaître un objet ou personne en particulière. D'autre part, la reconnaissance générique s'agit de retrouver tous les instances d'objets qui appartiennent à la même catégorie conceptuel: tous les voitures, les piétons, oiseaux, etc.Cette thèse propose un système de vision par ordinateur capable de détecter et suivre plusieurs objets dans les séquences vidéo. L'algorithme pour la recherche de correspondances proposé se base sur les matrices de covariance obtenues à partir d'un ensemble de propriétés des images (couleur et texture principalement). Son principal avantage c'est qu'il utilise un descripteur qui permet l'introduction des sources d'information très hétérogènes pour représenter les cibles. Cette représentation est efficace pour le suivi d'objets et son ré-identification.Quatre contributions sont introduites dans cette thèse.Tout d'abord cette thèse s'intéresse à l'invariance des algorithmes de suivi face aux changements du contexte. Nous proposons ici une méthodologie pour mesurer l’importance de l'information couleur en fonction de ses niveaux d’illumination et saturation. Puis, une deuxième partie se consacre à l'étude de différentes méthodes de suivi, ses avantages et limitations en fonction du type d'objet à suivre (rigide ou non rigide par exemple) et du contexte (caméra statique ou mobile). Le méthode que nous proposons s'adapte automatiquement et utilise un mécanisme de commutation entre différents méthodes de suivi qui considère ses qualités complémentaires. Notre algorithme se base sur un modèle de covariance qui fusionne les informations couleur-texture et le flot optique (KLT) modifié pour le rendre plus robuste et adaptable face aux changements d’illumination. Une deuxième approche se appuie sur l'analyse des différents espaces et invariants couleur à fin d'obtenir un descripteur qui garde un bon équilibre entre pouvoir discriminant et robustesse face aux changements d'illumination.Une troisième contribution porte sur le problème de suivi multi-cibles ou plusieurs difficultés apparaissent : la confusion d'identités, les occultations, la fusion et division des trajectoires-détections, etc.La dernière partie se consacre à la vitesse des algorithmes à fin de fournir une solution rapide et utilisable dans les applications embarquées. Cette thèse propose une série d'optimisations pour accélérer la mise en correspondance à l'aide de matrices de covariance. Transformations de mise en page de données, la vectorisation des calculs (à l'aide d'instructions SIMD) et certaines transformations de boucle permettent l'exécution en temps réel de l'algorithme non seulement sur les grands processeurs classiques de Intel, mais aussi sur les plateformes embarquées (ARM Cortex A9 et Intel U9300). / Visual recognition is the problem of learning visual categories from a limited set of samples and identifying new instances of those categories, the problem is often separated into two types: the specific case and the generic category case. In the specific case the objective is to identify instances of a particular object, place or person. Whereas in the generic category case we seek to recognize different instances that belong to the same conceptual class: cars, pedestrians, road signs and mugs. Specific object recognition works by matching and geometric verification. In contrast, generic object categorization often includes a statistical model of their appearance and/or shape.This thesis proposes a computer vision system for detecting and tracking multiple targets in videos. A preliminary work of this thesis consists on the adaptation of color according to lighting variations and relevance of the color. Then, literature shows a wide variety of tracking methods, which have both advantages and limitations, depending on the object to track and the context. Here, a deterministic method is developed to automatically adapt the tracking method to the context through the cooperation of two complementary techniques. A first proposition combines covariance matching for modeling characteristics texture-color information with optical flow (KLT) of a set of points uniformly distributed on the object . A second technique associates covariance and Mean-Shift. In both cases, the cooperation allows a good robustness of the tracking whatever the nature of the target, while reducing the global execution times .The second contribution is the definition of descriptors both discriminative and compact to be included in the target representation. To improve the ability of visual recognition of descriptors two approaches are proposed. The first is an adaptation operators (LBP to Local Binary Patterns ) for inclusion in the covariance matrices . This method is called ELBCM for Enhanced Local Binary Covariance Matrices . The second approach is based on the analysis of different spaces and color invariants to obtain a descriptor which is discriminating and robust to illumination changes.The third contribution addresses the problem of multi-target tracking, the difficulties of which are the matching ambiguities, the occlusions, the merging and division of trajectories.Finally to speed algorithms and provide a usable quick solution in embedded applications this thesis proposes a series of optimizations to accelerate the matching using covariance matrices. Data layout transformations, vectorizing the calculations (using SIMD instructions) and some loop transformations had made possible the real-time execution of the algorithm not only on Intel classic but also on embedded platforms (ARM Cortex A9 and Intel U9300).

Mycobacterium avium ssp. paratuberculosis (Map), agent étiologique de la paratuberculose, a évolué en deuxtypes dénommés, S pour« Sheep » et C pour « Cattle ». L’intestin grêle est le site primaire de l’infection à Map mais les mécanismes moléculaires impliqués dans l’implantation du bacille restent largement méconnus. L’objectif de mon projet de thèse visait à identifier et caractériser les adhésines exprimées par Map par des approches génétiques et biochimiques. J’ai ainsi purifié la HBHA et la LBP par chromatographie d’affinité puis les ai identifiés en spectrométrie de masse. L’originalité de ce travail repose sur le polymorphisme de ces adhésines observé entre les souches de type C et S. Cette variabilité a été mise en évidence sur le domaine d’interaction avec les sucres sulfatés de la cellule hôte influençant l’affinité des adhésines pour l’héparine. Ce travail de thèse a permis de caractériser pour la première fois ces deux adhésines produites par Map. Le polymorphisme de la HBHA et de la LBP, discriminant les types C et S, ouvre de nombreuses perspectives sur l’évolution de l’espèce M. avium et le rôle de ces adhésines sur le tropisme intestinal, la préférence d’hôte de Map ou encore leur potentiel diagnostic. / Mycobacterium avium subsp. paratuberculosis (Map), the etiological agent of paratuberculosis, has evolved into two types called, S for "Sheep" and C for "Cattle." The small intestine is the primary site of Map infection but the molecular mechanisms involved in the establishment of bacilli are still unknown. The aim of my thesis was to identify and characterize the adhesins expressed by Map by genetic and biochemical approaches. I purified HBHA and LBP by affinity chromatography then identified them by mass spectrometry. The originality of this work is based on the polymorphism of these adhesins observed between strains of type C and S. This variability has been demonstrated in the binding domain involved in interaction with sulfated sugars of host cell influences adhesins affinity for heparin. This thesis has characterized for the first time these two adhesins produced by Map. Specific polymorphism highlighted related to the evolution of the species avium, opens large number questions on their role on the pathogenesis of Map including the cellular tropism, host preference or interest of these antigens to improve diagnostic.

La croissance exponentielle et les progrès de la technologie ont rendu très pratique le partage de données visuelles, d'images et de données vidéo par le biais d’une vaste prépondérance de platesformes disponibles. Avec le développement rapide des technologies Internet et multimédia, l’efficacité de la gestion et du stockage, la rapidité de transmission et de partage, l'analyse en temps réel et le traitement des ressources multimédias numériques sont progressivement devenus un élément indispensable du travail et de la vie de nombreuses personnes. Sans aucun doute, une telle croissance technologique a rendu le forgeage de données visuelles relativement facile et réaliste sans laisser de traces évidentes. L'abus de ces données falsifiées peut tromper le public et répandre la désinformation parmi les masses. Compte tenu des faits mentionnés ci-dessus, la criminalistique des images doit être utilisée pour authentifier et maintenir l'intégrité des données visuelles. Pour cela, nous proposons une technique de détection passive de falsification d'images basée sur les incohérences de texture et de bruit introduites dans une image du fait de l'opération de falsification. De plus, le réseau de détection de falsification d'images (IFD-Net) proposé utilise une architecture basée sur un réseau de neurones à convolution (CNN) pour classer les images comme falsifiées ou vierges. Les motifs résiduels de texture et de bruit sont extraits des images à l'aide du motif binaire local (LBP) et du modèle Noiseprint. Les images classées comme forgées sont ensuite utilisées pour mener des expériences afin d'analyser les difficultés de localisation des pièces forgées dans ces images à l'aide de différents modèles de segmentation d'apprentissage en profondeur. Les résultats expérimentaux montrent que l'IFD-Net fonctionne comme les autres méthodes de détection de falsification d'images sur l'ensemble de données CASIA v2.0. Les résultats discutent également des raisons des difficultés de segmentation des régions forgées dans les images du jeu de données CASIA v2.0. / The exponential growth and advancement of technology have made it quite convenient for people to share visual data, imagery, and video data through a vast preponderance of available platforms. With the rapid development of Internet and multimedia technologies, performing efficient storage and management, fast transmission and sharing, real-time analysis, and processing of digital media resources has gradually become an indispensable part of many people’s work and life. Undoubtedly such technological growth has made forging visual data relatively easy and realistic without leaving any obvious visual clues. Abuse of such tampered data can deceive the public and spread misinformation amongst the masses. Considering the facts mentioned above, image forensics must be used to authenticate and maintain the integrity of visual data. For this purpose, we propose a passive image forgery detection technique based on textural and noise inconsistencies introduced in an image because of the tampering operation. Moreover, the proposed Image Forgery Detection Network (IFD-Net) uses a Convolution Neural Network (CNN) based architecture to classify the images as forged or pristine. The textural and noise residual patterns are extracted from the images using Local Binary Pattern (LBP) and the Noiseprint model. The images classified as forged are then utilized to conduct experiments to analyze the difficulties in localizing the forged parts in these images using different deep learning segmentation models. Experimental results show that both the IFD-Net perform like other image forgery detection methods on the CASIA v2.0 dataset. The results also discuss the reasons behind the difficulties in segmenting the forged regions in the images of the CASIA v2.0 dataset.

LPS wird von Gram-negativen Bakterien freigesetzt und führt mit Hilfe von LBP zur Ausschüttung proinflammatorischer Zytokine aus Monozyten und Makrophagen. Diese von LPS ausgelöste Kaskade, ist entscheidend an der Entstehung der Sepsis beteiligt. In dieser Arbeit wurde gezeigt, daß die LPS-induzierte Stimulation von Makrophagen durch murines Serum gehemmt werden kann. Außerdem konnte im Rahmen dieser Arbeit im Mausmodell verdeutlicht werden, welche Rolle Lipoproteine und LBP bei dem protektiven Serumeffekt spielen. Von den in Mausseren verschiedener Mausstämme bestimmten Parametern korrelierte der Phospholipidgehalt relativ gut mit dem inhibitorischen Serumeffekt. Eine Depletion von Lipoproteinen aus den Seren führte zu einer starken Reduktion des inhibitorischen Serumpotentials, während die Verwendung von LBP-defizienten Seren keinen Einfluß auf den Serumhemmeffekt hatte. Lipoproteine sehr geringer, geringer und hoher Dichte verursachten in Gegenwart von LBP eine deutliche Reduktion der LPS-Effekte, die gut mit ihrem Phospholipidgehalt korrelierte. In Abwesenheit von Serum und LBP konnten Lipoproteine LPS-Effekte auch bei hohen Phospholipidkonzentrationen kaum noch inhibieren. In nativen murinen Lipoproteinen hoher Dichte und lipoproteindefizientem Serum ließ sich LBP nachweisen. Die Ergebnisse dieser Arbeit zeigen, daß native Lipoproteine sehr geringer, geringer und hoher Dichten als Akzeptoren für LPS dienen können. Ihr inhibitorisches Potential korreliert am besten mit ihrem Phospholipidgehalt. Der Transport von LPS in diese Lipoproteine wird durch LBP katalysiert, was den protektiven Effekt hoher LBP-Konzentrationen erklärt. Weiterhin konnte gezeigt werden, daß LBP nicht der einzige Bestandteil von murinem Serum ist, der LPS in Lipoproteine transferiert. Vermutlich ist bei den, in dieser Arbeit verwendeten Serumkonzentrationen der PLTP-Gehalt ausreichend, diesen LPS-Transfer in Abwesenheit von LBP zu vollziehen. Bei der Interaktion zwischen Lipoproteinen und LPS handelt es sich um einen physiologischen Weg des Organismus, um auf bakterielle Endotoxine zu reagieren und so der Sepsis entgegenzuwirken. Mit genaueren Kenntnissen über diese Interaktion, bei der Lipidtransferproteine wie LBP und PLTP eine entscheidende Rolle spielen, können eventuell in Zukunft Methoden gefunden werden, diese physiologischen Vorgänge des Körpers zu unterstützen, um so eine Sepsis zu therapieren. / LPS released by gram-negative bacteria is bound by LBP and initiates the release of proinflammatory cytokines in makrophages and monocytes. These cytokines are thought to play a central role in the pathophysiology of sepsis. In these studies I was able to show an inhibitory effect of murine serum on the LPS-induced stimulation of macrophages. Furthermore the role of lipoproteins and LBP in this protective effect of serum was investigated. The inhibitory effect of serum from different mouse strains was best correlated to its phospholipid content. Depletion of serum from lipoproteins strongly reduced its LPS-inhibitory potential while depletion of serum from LBP had no effect. Murine VLDL, LDL and HDL were found to be potent inhibitors of LPS-effects in presence of LBP. In abscence of LBP the inhibitory effect was much weaker. LBP could be detected in murine HDL and murine lipoproteindeficient serum. My data shows that HDL, LDL and VLDL can act as acceptors of LPS. Their inhibitory potential is best correlated to their phospholipid content. LBP catalyses transport of LPS into lipoproteins. This could be an explanation for its protective effect in high doses. Furthermore it could be shown that LBP is not the only serum component that transfers LPS into Lipoproteins. Possibly the used serum contained enough PLTP to perform this transfer in absence of LBP. The interaction between Lipoproteins and LPS is a physiological way of the organism to react on endotoxines and inhibit the development of sepsis. PLTP and LBP play major roles in this interaction. Understanding the pathways of LPS-detoxification may help to support the organism s physiological answer and establish new methods to treat sepsis.

INTRODUÇÃO: A Artrite aguda do joelho é o tipo mais comum de artrite, e sua prevalência aumenta em paralelo com o aumento da idade da população. Há muitas evidências de benefícios clínicos do laser para o tratamento da osteoartrite. No entanto, existem poucos estudos abordando os efeitos de 810 nm laser. Aqui nós iremos investigar os efeitos de Laser de Baixa Potencia (infra-vermelho, 810 nm). MATERIAL E MÉTODOS: Ratos Wistar machos (230 - 250g) foram anestesiados com halotano antes da injeção de pró-inflamatórios compostos. Carragenina e Kaolin, ambos a 3%, em solução diluída em soro Fisiológico, administrado intra-articular. Os grupos tratados receberam irradiação laser no local. Após 6 horas todos os animais foram anestesiados e mortos por deslocamento cervical para coleta de cavidade articular e lavado para celulares e análise bioquímica. O tecido articular foi analisado por PCR em tempo real análise, a fim de avaliar a expressão de COX-1 e COX-2. IL-1, TNF-alfa e IL-6 e a mieloperoxidase (MPO) também foi realizada. RESULTADOS E DISCUSSÃO: A terapia com laser de baixa potência foi capaz de inibir o número total de leucócitos, atividade de mieloperoxidase, o extravasamento vascular, IL-1b, TNF-a, IL-6 e Prostaglandina E2. / Introduction. Arthritis of the knee (AK) is the most common type of osteoarthritis, and its prevalence is rising in parallel with the increasing age of the population.. Here we investigate the effects of Low Level Laser Therapy (infra-red, 810 nm) in experimentally induced rat knee osteoarthritis. Methods. Male wistar rats (150 200g) were anaesthetized with halothane 1% prior the injection of pro-inflammatory compounds. Carrageenan and Kaolin (both 3%) administered intra-articular. After 6 hours all animals were killed by decaptation and articular cavity was washed and collected. Articular Tissue was carefully removed for edema and Real-time PCR analysis in order to evaluate COX-1 and COX-2 expression. Total and differential cell account, mieloperoxidase activity, IL-b, TNF-a, IL-6 was also analysed. Results. Low Level laser therapy was able to significantly inhibit the total number of leukocytes as well as the mieloperoxidase activity, polymorphonuclear cells at the inflammatory site, vascular extravasation, IL-1, TNF-alpha, IL-6 and prostaglandin E2. Conclusions. Low Level Laser Therapy operating in 810 nm markedly reduced inflammation in carrageenan, kaolin-induced knee osteoarthritis.

<div>Information security practitioners and researchers who possess sufficient depth of conceptual understanding to reconstitute systems after attacks or adapt information security concepts to novel situations are in short supply. Education of new information security professionals with sufficient conceptual depth is one method by which this shortage can be reduced. This study reports research that instructed two groups of ten undergraduate, pre-cryptography students majoring in Computer Science in cryptography concepts using representational understanding first and representational fluency first instructional treatment methods. This study compared learning results between the treatment groups using traditional paper-based measures of cognitions and fMRI scans of brain activity during cryptography problem solving. Analysis found no statistical difference in measures of cognitions or in cognitive processing, but did build a statistical model describing the relationships between explanatory variables and cryptography learning, and found common areas of cognitive processing of cryptography among the study’s twenty subjects.</div>

INTRODUÇÃO: A Artrite aguda do joelho é o tipo mais comum de artrite, e sua prevalência aumenta em paralelo com o aumento da idade da população. Há muitas evidências de benefícios clínicos do laser para o tratamento da osteoartrite. No entanto, existem poucos estudos abordando os efeitos de 810 nm laser. Aqui nós iremos investigar os efeitos de Laser de Baixa Potencia (infra-vermelho, 810 nm). MATERIAL E MÉTODOS: Ratos Wistar machos (230 - 250g) foram anestesiados com halotano antes da injeção de pró-inflamatórios compostos. Carragenina e Kaolin, ambos a 3%, em solução diluída em soro Fisiológico, administrado intra-articular. Os grupos tratados receberam irradiação laser no local. Após 6 horas todos os animais foram anestesiados e mortos por deslocamento cervical para coleta de cavidade articular e lavado para celulares e análise bioquímica. O tecido articular foi analisado por PCR em tempo real análise, a fim de avaliar a expressão de COX-1 e COX-2. IL-1, TNF-alfa e IL-6 e a mieloperoxidase (MPO) também foi realizada. RESULTADOS E DISCUSSÃO: A terapia com laser de baixa potência foi capaz de inibir o número total de leucócitos, atividade de mieloperoxidase, o extravasamento vascular, IL-1b, TNF-a, IL-6 e Prostaglandina E2. / Introduction. Arthritis of the knee (AK) is the most common type of osteoarthritis, and its prevalence is rising in parallel with the increasing age of the population.. Here we investigate the effects of Low Level Laser Therapy (infra-red, 810 nm) in experimentally induced rat knee osteoarthritis. Methods. Male wistar rats (150 200g) were anaesthetized with halothane 1% prior the injection of pro-inflammatory compounds. Carrageenan and Kaolin (both 3%) administered intra-articular. After 6 hours all animals were killed by decaptation and articular cavity was washed and collected. Articular Tissue was carefully removed for edema and Real-time PCR analysis in order to evaluate COX-1 and COX-2 expression. Total and differential cell account, mieloperoxidase activity, IL-b, TNF-a, IL-6 was also analysed. Results. Low Level laser therapy was able to significantly inhibit the total number of leukocytes as well as the mieloperoxidase activity, polymorphonuclear cells at the inflammatory site, vascular extravasation, IL-1, TNF-alpha, IL-6 and prostaglandin E2. Conclusions. Low Level Laser Therapy operating in 810 nm markedly reduced inflammation in carrageenan, kaolin-induced knee osteoarthritis.

Abstract In recent years, facial expression recognition has become a useful scheme for computers to affectively understand the emotional state of human beings. Facial representation and facial expression recognition under unconstrained environments have been two critical issues for facial expression recognition systems. This thesis contributes to the research and development of facial expression recognition systems from two aspects: first, feature extraction for facial expression recognition, and second, applications to challenging conditions. Spatial and temporal feature extraction methods are introduced to provide effective and discriminative features for facial expression recognition. The thesis begins with a spatial feature extraction method. This descriptor exploits magnitude while it improves local quantized pattern using improved vector quantization. It also makes the statistical patterns domain-adaptive and compact. Then, the thesis discusses two spatiotemporal feature extraction methods. The first method uses monogenic signal analysis as a preprocessing stage and extracts spatiotemporal features using local binary pattern. The second method extracts sparse spatiotemporal features using sparse cuboids and spatiotemporal local binary pattern. Both methods increase the discriminative capability of local binary pattern in the temporal domain. Based on feature extraction methods, three practical conditions, including illumination variations, facial occlusion and pose changes, are studied for the applications of facial expression recognition. First, with near-infrared imaging technique, a discriminative component-based single feature descriptor is proposed to achieve a high degree of robustness and stability to illumination variations. Second, occlusion detection is proposed to dynamically detect the occluded face regions. A novel system is further designed for handling effectively facial occlusion. Lastly, multi-view discriminative neighbor preserving embedding is developed to deal with pose change, which formulates multi-view facial expression recognition as a generalized eigenvalue problem. Experimental results on publicly available databases show that the effectiveness of the proposed approaches for the applications of facial expression recognition. / Tiivistelmä Kasvonilmeiden tunnistamisesta on viime vuosina tullut tietokoneille hyödyllinen tapa ymmärtää affektiivisesti ihmisen tunnetilaa. Kasvojen esittäminen ja kasvonilmeiden tunnistaminen rajoittamattomissa ympäristöissä ovat olleet kaksi kriittistä ongelmaa kasvonilmeitä tunnistavien järjestelmien kannalta. Tämä väitöskirjatutkimus myötävaikuttaa kasvonilmeitä tunnistavien järjestelmien tutkimukseen ja kehittymiseen kahdesta näkökulmasta: piirteiden irrottamisesta kasvonilmeiden tunnistamista varten ja kasvonilmeiden tunnistamisesta haastavissa olosuhteissa. Työssä esitellään spatiaalisia ja temporaalisia piirteenirrotusmenetelmiä, jotka tuottavat tehokkaita ja erottelukykyisiä piirteitä kasvonilmeiden tunnistamiseen. Ensimmäisenä työssä esitellään spatiaalinen piirteenirrotusmenetelmä, joka parantaa paikallisia kvantisoituja piirteitä käyttämällä parannettua vektorikvantisointia. Menetelmä tekee myös tilastollisista malleista monikäyttöisiä ja tiiviitä. Seuraavaksi työssä esitellään kaksi spatiotemporaalista piirteenirrotusmenetelmää. Ensimmäinen näistä käyttää esikäsittelynä monogeenistä signaalianalyysiä ja irrottaa spatiotemporaaliset piirteet paikallisia binäärikuvioita käyttäen. Toinen menetelmä irrottaa harvoja spatiotemporaalisia piirteitä käyttäen harvoja kuusitahokkaita ja spatiotemporaalisia paikallisia binäärikuvioita. Molemmat menetelmät parantavat paikallisten binärikuvioiden erottelukykyä ajallisessa ulottuvuudessa. Piirteenirrotusmenetelmien pohjalta työssä tutkitaan kasvonilmeiden tunnistusta kolmessa käytännön olosuhteessa, joissa esiintyy vaihtelua valaistuksessa, okkluusiossa ja pään asennossa. Ensiksi ehdotetaan lähi-infrapuna kuvantamista hyödyntävää diskriminatiivistä komponenttipohjaista yhden piirteen kuvausta, jolla saavutetaan korkea suoritusvarmuus valaistuksen vaihtelun suhteen. Toiseksi ehdotetaan menetelmä okkluusion havainnointiin, jolla dynaamisesti havaitaan peittyneet kasvon alueet. Uudenlainen menetelmä on kehitetty käsittelemään kasvojen okkluusio tehokkaasti. Viimeiseksi työssä on kehitetty moninäkymäinen diskriminatiivisen naapuruston säilyttävään upottamiseen pohjautuva menetelmä käsittelemään pään asennon vaihtelut. Menetelmä kuvaa moninäkymäisen kasvonilmeiden tunnistamisen yleistettynä ominaisarvohajotelmana. Kokeelliset tulokset julkisilla tietokannoilla osoittavat tässä työssä ehdotetut menetelmät suorituskykyisiksi kasvonilmeiden tunnistamisessa.

The aim of this research was to make recommendations how parents and educators can select and use audio-visual media for supporting learners with behavioural problems (LBP). A literature study was conducted on behavioural problems and on the use of audio-visual media to address these. Thereafter an empirical investigation was done by means of a case study design. A purposive sample was chosen from Grades 10 and 12 learners in Pietermaritzburg. Websites were also selected for addressing a variety of topics. The most important findings were that audio-visual media can be selected by means of five criteria related to content accuracy and appropriateness, diversity and quality. The findings indicate that visual media can stimulate cognitive skills (including problem solving and critical thinking) and reflection about the acceptance of responsibility, positive attitudes and respect for authority, among others. It is concluded that audio-visual media can be used by educators to support LBP. / Educational Studies / M.Ed. (Specialisation in Psychology of Education)

Visual recognition is the problem of learning visual categories from a limited set of samples and identifying new instances of those categories, the problem is often separated into two types: the specific case and the generic category case. In the specific case the objective is to identify instances of a particular object, place or person. Whereas in the generic category case we seek to recognize different instances that belong to the same conceptual class: cars, pedestrians, road signs and mugs. Specific object recognition works by matching and geometric verification. In contrast, generic object categorization often includes a statistical model of their appearance and/or shape.This thesis proposes a computer vision system for detecting and tracking multiple targets in videos. A preliminary work of this thesis consists on the adaptation of color according to lighting variations and relevance of the color. Then, literature shows a wide variety of tracking methods, which have both advantages and limitations, depending on the object to track and the context. Here, a deterministic method is developed to automatically adapt the tracking method to the context through the cooperation of two complementary techniques. A first proposition combines covariance matching for modeling characteristics texture-color information with optical flow (KLT) of a set of points uniformly distributed on the object . A second technique associates covariance and Mean-Shift. In both cases, the cooperation allows a good robustness of the tracking whatever the nature of the target, while reducing the global execution times .The second contribution is the definition of descriptors both discriminative and compact to be included in the target representation. To improve the ability of visual recognition of descriptors two approaches are proposed. The first is an adaptation operators (LBP to Local Binary Patterns ) for inclusion in the covariance matrices . This method is called ELBCM for Enhanced Local Binary Covariance Matrices . The second approach is based on the analysis of different spaces and color invariants to obtain a descriptor which is discriminating and robust to illumination changes.The third contribution addresses the problem of multi-target tracking, the difficulties of which are the matching ambiguities, the occlusions, the merging and division of trajectories.Finally to speed algorithms and provide a usable quick solution in embedded applications this thesis proposes a series of optimizations to accelerate the matching using covariance matrices. Data layout transformations, vectorizing the calculations (using SIMD instructions) and some loop transformations had made possible the real-time execution of the algorithm not only on Intel classic but also on embedded platforms (ARM Cortex A9 and Intel U9300).