L’objectif de cette thèse est de trouver de nouvelles méthodes de compression sémantique compatible avec un encodeur classique tel que H.264/AVC. . L’objectif principal est de maintenir la sémantique et non pas la qualité globale. Un débit cible de 300 kb/s a été fixé pour des applications de sécurité et de défense Pour cela une chaine complète de compression a dû être réalisée. Une étude et des contributions sur les modèles de saillance spatio-temporel ont été réalisées avec pour objectif d’extraire l’information pertinente. Pour réduire le débit, une méthode de redimensionnement dénommée «seam carving » a été combinée à un encodeur H.264/AVC. En outre, une métrique combinant les points SIFT et le SSIM a été réalisée afin de mesurer la qualité des objets sans être perturbée par les zones de moindre contenant la majorité des artefacts. Une base de données pouvant être utilisée pour des modèles de saillance mais aussi pour de la compression est proposée avec des masques binaires. Les différentes approches ont été validées par divers tests. Une extension de ces travaux pour des applications de résumé vidéo est proposée. / The objective of this thesis is to find new methods for semantic video compatible with a traditional encoder like H.264/AVC. The main objective is to maintain the semantic and not the global quality. A target bitrate of 300 Kb/s has been fixed for defense and security applications. To do that, a complete chain of compression has been proposed. A study and new contributions on a spatio-temporal saliency model have been done to extract the important information in the scene. To reduce the bitrate, a resizing method named seam carving has been combined with the H.264/AVC encoder. Also, a metric combining SIFT points and SSIM has been created to measure the quality of objects without being disturbed by less important areas containing mostly artifacts. A database that can be used for testing the saliency model but also for video compression has been proposed, containing sequences with their manually extracted binary masks. All the different approaches have been thoroughly validated by different tests. An extension of this work on video summary application has also been proposed.

[pt] Esta dissertação introduz um estudo sobre os algoritmos de inteligência computacional para o controle autônomo dos robôs móveis, Nesta pesquisa, são desenvolvidos e implementados sistemas inteligentes de controle de um robô móvel construído no Laboratório de Robótica da PUC-Rio, baseado numa modificação do robô ER1. Os experimentos realizados consistem em duas etapas: a primeira etapa de simulação usando o software Player-Stage de simulação do robô em 2-D onde foram desenvolvidos os algoritmos de navegação usando as técnicas de inteligência computacional; e a segunda etapa a implementação dos algoritmos no robô real. As técnicas implementadas para a navegação do robô móvel estão baseadas em algoritmos de inteligência computacional como são redes neurais, lógica difusa e support vector machine (SVM) e para dar suporte visual ao robô móvel foi implementado uma técnica de visão computacional chamado Scale Invariant Future Transform (SIFT), estes algoritmos em conjunto fazem um sistema embebido para dotar de controle autônomo ao robô móvel. As simulações destes algoritmos conseguiram o objetivo, mas na implementação surgiram diferenças muito claras respeito à simulação pelo tempo que demora em processar o microprocessador. / [en] This theses introduces a study on the computational intelligence algorithms for autonomous control of mobile robots, In this research, intelligent systems are developed and implemented for a robot in the Robotics Laboratory of PUC-Rio, based on a modiÞcation of the robot ER1. The verification consist of two stages: the first stage includes simulation using Player-Stage software for simulation of the robot in 2-D with the developed of artiÞcial intelligence; an the second stage, including the implementation of the algorithms in the real robot. The techniques implemented for the navigation of the mobile robot are based on algorithms of computational intelligence as neural networks, fuzzy logic and support vector machine (SVM); and to give visual support to the mobile robot was implemented the visual algorithm called Scale Invariant Future Transform (SIFT), these algorithms in set makes an absorbed system to endow with independent control the mobile robot. The simulations of these algorithms had obtained the objective but in the implementation clear differences had appeared respect to the simulation, it just for the time that delays in processing the microprocessor.

This thesis focuses on bare hand gesture recognition by proposing a new architecture to solve the problem of real-time vision-based hand detection, tracking, and gesture recognition for interaction with an application via hand gestures. The first stage of our system allows detecting and tracking a bare hand in a cluttered background using face subtraction, skin detection and contour comparison. The second stage allows recognizing hand gestures using bag-of-features and multi-class Support Vector Machine (SVM) algorithms. Finally, a grammar has been developed to generate gesture commands for application control. Our hand gesture recognition system consists of two steps: offline training and online testing. In the training stage, after extracting the keypoints for every training image using the Scale Invariance Feature Transform (SIFT), a vector quantization technique will map keypoints from every training image into a unified dimensional histogram vector (bag-of-words) after K-means clustering. This histogram is treated as an input vector for a multi-class SVM to build the classifier. In the testing stage, for every frame captured from a webcam, the hand is detected using my algorithm. Then, the keypoints are extracted for every small image that contains the detected hand posture and fed into the cluster model to map them into a bag-of-words vector, which is fed into the multi-class SVM classifier to recognize the hand gesture. Another hand gesture recognition system was proposed using Principle Components Analysis (PCA). The most eigenvectors and weights of training images are determined. In the testing stage, the hand posture is detected for every frame using my algorithm. Then, the small image that contains the detected hand is projected onto the most eigenvectors of training images to form its test weights. Finally, the minimum Euclidean distance is determined among the test weights and the training weights of each training image to recognize the hand gesture. Two application of gesture-based interaction with a 3D gaming virtual environment were implemented. The exertion videogame makes use of a stationary bicycle as one of the main inputs for game playing. The user can control and direct left-right movement and shooting actions in the game by a set of hand gesture commands, while in the second game, the user can control and direct a helicopter over the city by a set of hand gesture commands.

This thesis focuses on bare hand gesture recognition by proposing a new architecture to solve the problem of real-time vision-based hand detection, tracking, and gesture recognition for interaction with an application via hand gestures. The first stage of our system allows detecting and tracking a bare hand in a cluttered background using face subtraction, skin detection and contour comparison. The second stage allows recognizing hand gestures using bag-of-features and multi-class Support Vector Machine (SVM) algorithms. Finally, a grammar has been developed to generate gesture commands for application control. Our hand gesture recognition system consists of two steps: offline training and online testing. In the training stage, after extracting the keypoints for every training image using the Scale Invariance Feature Transform (SIFT), a vector quantization technique will map keypoints from every training image into a unified dimensional histogram vector (bag-of-words) after K-means clustering. This histogram is treated as an input vector for a multi-class SVM to build the classifier. In the testing stage, for every frame captured from a webcam, the hand is detected using my algorithm. Then, the keypoints are extracted for every small image that contains the detected hand posture and fed into the cluster model to map them into a bag-of-words vector, which is fed into the multi-class SVM classifier to recognize the hand gesture. Another hand gesture recognition system was proposed using Principle Components Analysis (PCA). The most eigenvectors and weights of training images are determined. In the testing stage, the hand posture is detected for every frame using my algorithm. Then, the small image that contains the detected hand is projected onto the most eigenvectors of training images to form its test weights. Finally, the minimum Euclidean distance is determined among the test weights and the training weights of each training image to recognize the hand gesture. Two application of gesture-based interaction with a 3D gaming virtual environment were implemented. The exertion videogame makes use of a stationary bicycle as one of the main inputs for game playing. The user can control and direct left-right movement and shooting actions in the game by a set of hand gesture commands, while in the second game, the user can control and direct a helicopter over the city by a set of hand gesture commands.

This thesis focuses on bare hand gesture recognition by proposing a new architecture to solve the problem of real-time vision-based hand detection, tracking, and gesture recognition for interaction with an application via hand gestures. The first stage of our system allows detecting and tracking a bare hand in a cluttered background using face subtraction, skin detection and contour comparison. The second stage allows recognizing hand gestures using bag-of-features and multi-class Support Vector Machine (SVM) algorithms. Finally, a grammar has been developed to generate gesture commands for application control. Our hand gesture recognition system consists of two steps: offline training and online testing. In the training stage, after extracting the keypoints for every training image using the Scale Invariance Feature Transform (SIFT), a vector quantization technique will map keypoints from every training image into a unified dimensional histogram vector (bag-of-words) after K-means clustering. This histogram is treated as an input vector for a multi-class SVM to build the classifier. In the testing stage, for every frame captured from a webcam, the hand is detected using my algorithm. Then, the keypoints are extracted for every small image that contains the detected hand posture and fed into the cluster model to map them into a bag-of-words vector, which is fed into the multi-class SVM classifier to recognize the hand gesture. Another hand gesture recognition system was proposed using Principle Components Analysis (PCA). The most eigenvectors and weights of training images are determined. In the testing stage, the hand posture is detected for every frame using my algorithm. Then, the small image that contains the detected hand is projected onto the most eigenvectors of training images to form its test weights. Finally, the minimum Euclidean distance is determined among the test weights and the training weights of each training image to recognize the hand gesture. Two application of gesture-based interaction with a 3D gaming virtual environment were implemented. The exertion videogame makes use of a stationary bicycle as one of the main inputs for game playing. The user can control and direct left-right movement and shooting actions in the game by a set of hand gesture commands, while in the second game, the user can control and direct a helicopter over the city by a set of hand gesture commands.

An expert system is useful when conventional programming techniques fall short of capturing human expert knowledge and making decisions using this information. In this study, we describe a framework for capturing expert knowledge under a decision tree form and this framework can be used for making decisions based on captured knowledge. The framework proposed in this study is generic and can be used to create domain specific expert systems for different problems. Features are created or processed by the nodes of decision tree and a final conclusion is reached for each feature. Framework supplies 3 types of nodes to construct a decision tree. First type is the decision node, which guides the search path with its answers. Second type is the operator node, which creates new features using the inputs. Last type of node is the end node, which corresponds to a conclusion about a feature. Once the nodes of the tree are developed, then user can interactively create the decision tree and run the supplied inference engine to collect the result on a specific problem. The framework proposed is experimented with two case studies / &quot / Airport Runway Detection in High Resolution Satellite Images&quot / and &quot / Urban Area Detection in High Resolution Satellite Images&quot / . In these studies linear features are used for structural decisions and Scale Invariant Feature Transform (SIFT) features are used for testing existence of man made structures.

Ένα σημαντικό πρόβλημα είναι η αντιστοίχιση εικόνων με σκοπό τη δημιουργία πανοράματος. Στην παρούσα εργασία έχουν χρησιμοποιηθεί αλγόριθμοι που βασίζονται στη χρήση σημείων κλειδιών. Αρχικά στην εργασία βρίσκονται σημεία κλειδιά για κάθε εικόνα που μένουν ανεπηρέαστα από τις αναμενόμενες παραμορφώσεις με την βοήθεια του αλγορίθμου SIFT (Scale Invariant Feature Transform). Έχοντας τελειώσει αυτή τη διαδικασία για όλες τις εικόνες, προσπαθούμε να βρούμε το πρώτο ζευγάρι εικόνων που θα ενωθεί. Για να δούμε αν δύο εικόνες μπορούν να ενωθούν, ακολουθεί ταίριασμα των σημείων κλειδιών τους. Όταν ένα αρχικό σετ αντίστοιχων χαρακτηριστικών έχει υπολογιστεί, πρέπει να βρεθεί ένα σετ που θα παράγει υψηλής ακρίβειας αντιστοίχιση. Αυτό το πετυχαίνουμε με τον αλγόριθμο RANSAC, μέσω του οποίου βρίσκουμε το γεωμετρικό μετασχηματισμό ανάμεσα στις δύο εικόνες, ομογραφία στην περίπτωσή μας. Αν ο αριθμός των κοινών σημείων κλειδιών είναι επαρκής, δηλαδή ταιριάζουν οι εικόνες, ακολουθεί η ένωσή τους. Αν απλώς ενώσουμε τις εικόνες, τότε θα έχουμε σίγουρα κάποια προβλήματα, όπως το ότι οι ενώσεις των δύο εικόνων θα είναι πολύ εμφανείς. Γι’ αυτό, για την εξάλειψη αυτού του προβλήματος, χρησιμοποιούμε τη μέθοδο των Λαπλασιανών πυραμίδων. Επαναλαμβάνεται η παραπάνω διαδικασία μέχρι να δημιουργηθεί το τελικό πανόραμα παίρνοντας κάθε φορά σαν αρχική την τελευταία εικόνα που φτιάξαμε στην προηγούμενη φάση. / Stitching multiple images together to create high resolution panoramas is one of the most popular consumer applications of image registration and blending. At this work, feature-based registration algorithms have been used. The first step is to extract distinctive invariant features from every image which are invariant to image scale and rotation, using SIFT (Scale Invariant Feature Transform) algorithm. After that, we try to find the first pair of images in order to stitch them. To check if two images can be stitched, we match their keypoints (the results from SIFT). Once an initial set of feature correspondences has been computed, we need to find the set that is will produce a high-accuracy alignment. The solution at this problem is RANdom Sample Consensus (RANSAC). Using this algorithm (RANSAC) we find the motion model between the two images (homography). If there is enough number of correspond points, we stitch these images. After that, seams are visible. As solution to this problem is used the method of Laplacian Pyramids. We repeat the above procedure using as initial image the ex panorama which has been created.

This work focuses on analysing and improving feature detection and matching. After creating an initial framework of study, four main areas of work are researched. These areas make up the main chapters within this thesis and focus on using the Scale Invariant Feature Transform (SIFT).The preliminary analysis of the SIFT investigates how this algorithm functions. Included is an analysis of the SIFT feature descriptor space and an investigation into the noise properties of the SIFT. It introduces a novel use of the a contrario methodology and shows the success of this method as a way of discriminating between images which are likely to contain corresponding regions from images which do not. Parameter analysis of the SIFT uses both parameter sweeps and genetic algorithms as an intelligent means of setting the SIFT parameters for different image types utilising a GPGPU implementation of SIFT. The results have demonstrated which parameters are more important when optimising the algorithm and the areas within the parameter space to focus on when tuning the values. A multi-exposure, High Dynamic Range (HDR), fusion features process has been developed where the SIFT image features are matched within high contrast scenes. Bracketed exposure images are analysed and features are extracted and combined from different images to create a set of features which describe a larger dynamic range. They are shown to reduce the effects of noise and artefacts that are introduced when extracting features from HDR images directly and have a superior image matching performance. The final area is the development of a novel, 3D-based, SIFT weighting technique which utilises the 3D data from a pair of stereo images to cluster and class matched SIFT features. Weightings are applied to the matches based on the 3D properties of the features and how they cluster in order to attempt to discriminate between correct and incorrect matches using the a contrario methodology. The results show that the technique provides a method for discriminating between correct and incorrect matches and that the a contrario methodology has potential for future investigation as a method for correct feature match prediction.

Nous étudions ici l’intérêt des descripteurs locaux pour les images satellites optiques et radar. Ces descripteurs, par leurs invariances et leur représentation compacte, offrent un intérêt pour la comparaison d’images acquises dans des conditions différentes. Facilement applicables aux images optiques, ils offrent des performances limitées sur les images radar, en raison de leur fort bruit multiplicatif. Nous proposons ici un descripteur original pour la comparaison d’images radar. Cet algorithme, appelé SAR-SIFT, repose sur la même structure que l’algorithme SIFT (détection de points-clés et extraction de descripteurs) et offre des performances supérieures pour les images radar. Pour adapter ces étapes au bruit multiplicatif, nous avons développé un opérateur différentiel, le Gradient par Ratio, permettant de calculer une norme et une orientation du gradient robustes à ce type de bruit. Cet opérateur nous a permis de modifier les étapes de l’algorithme SIFT. Nous présentons aussi deux applications pour la télédétection basées sur les descripteurs. En premier, nous estimons une transformation globale entre deux images radar à l’aide de SAR-SIFT. L’estimation est réalisée à l’aide d’un algorithme RANSAC et en utilisant comme points homologues les points-clés mis en correspondance. Enfin nous avons mené une étude prospective sur l’utilisation des descripteurs pour la détection de changements en télédétection. La méthode proposée compare les densités de points-clés mis en correspondance aux densités de points-clés détectés pour mettre en évidence les zones de changement. / We study here the interest of local features for optical and SAR images. These features, because of their invariances and their dense representation, offer a real interest for the comparison of satellite images acquired under different conditions. While it is easy to apply them to optical images, they offer limited performances on SAR images, because of their multiplicative noise. We propose here an original feature for the comparison of SAR images. This algorithm, called SAR-SIFT, relies on the same structure as the SIFT algorithm (detection of keypoints and extraction of features) and offers better performances for SAR images. To adapt these steps to multiplicative noise, we have developed a differential operator, the Gradient by Ratio, allowing to compute a magnitude and an orientation of the gradient robust to this type of noise. This operator allows us to modify the steps of the SIFT algorithm. We present also two applications for remote sensing based on local features. First, we estimate a global transformation between two SAR images with help of SAR-SIFT. The estimation is realized with help of a RANSAC algorithm and by using the matched keypoints as tie points. Finally, we have led a prospective study on the use of local features for change detection in remote sensing. The proposed method consists in comparing the densities of matched keypoints to the densities of detected keypoints, in order to point out changed areas.

La profondeur possible d’imagerie en laser-scanning microscopie est limitée non seulement par la distance de travail des lentilles de objectifs mais également par la dégradation de l’image causée par une atténuation et une diffraction de la lumière passant à travers l’échantillon. Afin d’étendre cette limite, il est possible, soit de retourner le spécimen pour enregistrer les images depuis chaque côté, or couper progressivement la partie supérieure de l’échantillon au fur et à mesure de l‘acquisition. Les différentes images prises de l’une de ces manières doivent ensuite être combinées pour générer un volume unique. Cependant, des mouvements de l’échantillon durant les procédures d’acquisition engendrent un décalage non seulement sur en translation selon les axes x, y et z mais également en rotation autour de ces même axes, rendant la fusion entres ces multiples images difficile. Nous avons développé une nouvelle approche appelée 2D-SIFT-in-3D-Space utilisant les SIFT (scale Invariant Feature Transform) pour atteindre un recalage robuste en trois dimensions de deux images. Notre méthode recale les images en corrigeant séparément les translations et rotations sur les trois axes grâce à l’extraction et l’association de caractéristiques stables de leurs coupes transversales bidimensionnelles. Pour évaluer la qualité du recalage, nous avons également développé un simulateur d’images de laser-scanning microscopie qui génère une paire d’images 3D virtuelle dans laquelle le niveau de bruit et les angles de rotations entre les angles de rotation sont contrôlés avec des paramètres connus. Pour une concaténation précise et naturelle de deux images, nous avons également développé un module permettant une compensation progressive de la luminosité et du contraste en fonction de la distance à la surface de l’échantillon. Ces outils ont été utilisés avec succès pour l’obtention d’images tridimensionnelles de haute résolution du cerveau de la mouche Drosophila melanogaster, particulièrement des neurones dopaminergiques, octopaminergiques et de leurs synapses. Ces neurones monoamines sont particulièrement important pour le fonctionnement du cerveau et une étude de leur réseau et connectivité est nécessaire pour comprendre leurs interactions. Si une évolution de leur connectivité au cours du temps n’a pas pu être démontrée via l’analyse de la répartition des sites synaptiques, l’étude suggère cependant que l’inactivation de l’un de ces types de neurones entraine des changements drastiques dans le réseau neuronal. / Although laser scanning microscopy is a powerful tool for obtaining thin optical sections, the possible depth of imaging is limited by the working distance of the microscope objective but also by the image degradation caused by the attenuation of both excitation laser beam and the light emitted from the fluorescence-labeled objects. Several workaround techniques have been employed to overcome this problem, such as recording the images from both sides of the sample, or by progressively cutting off the sample surface. The different views must then be combined in a unique volume. However, a straightforward concatenation is often not possible, because the small rotations that occur during the acquisition procedure, not only in translation along x, y and z axes but also in rotation around those axis, making the fusion uneasy. To address this problem we implemented a new algorithm called 2D-SIFT-in-3D-Space using SIFT (scale Invariant Feature Transform) to achieve a robust registration of big image stacks. Our method register the images fixing separately rotations and translations around the three axes using the extraction and matching of stable features in 2D cross-sections. In order to evaluate the registration quality, we created a simulator that generates artificial images that mimic laser scanning image stacks to make a mock pair of image stacks one of which is made from the same stack with the other but is rotated arbitrarily with known angles and filtered with a known noise. For a precise and natural-looking concatenation of the two images, we also developed a module progressively correcting the sample brightness and contrast depending on the sample surface. Those tools we successfully used to generate tridimensional high resolution images of the fly Drosophila melanogaster brain, in particular, its octopaminergic and dopaminergic neurons and their synapses. Those monoamine neurons appear to be determinant in the correct operating of the central nervous system and a precise and systematic analysis of their evolution and interaction is necessary to understand its mechanisms. If an evolution over time could not be highlighted through the pre-synaptic sites analysis, our study suggests however that the inactivation of one of these neuron types triggers drastic changes in the neural network.