The TRACAB Image Tracking System is used by ChyronHego for the tracking of ball and players on football fields. It requires the calibration of the cameras around the arena which is disrupted by fences and other mesh structures that are positioned between the camera and the field as a safety measure for the public. The purpose of this work was the implementation of a cycle consistent Generative Adversarial Network (cycle-GAN) for removing the fence from the image using unpaired data. Cycle-GANs are part of the state-of-the-art of image-to-image translation and can solve this kind of problem without the need of paired images. This makes it an exciting and powerful method and, according to the latest investigations in the current work, it has never been used for this kind of application before. The model was able to strongly attenuate, and in some cases completely remove, the net structure from images. To quantify the impact of the net removal a homography matching was performed. Then, it was compared with the homography associated to the baseline of blurring the image with a gaussian filter and the original image without the use of any filter. The results showed that the identification of key-points was harder on synthetic images than on the original image with or without small Gaussian filters, but it showed a better performance against images blurred with filters with a standard deviation of 3 pixels or more. Despite the performance not being better than the baseline in all the cases it always added new key-points, and sometimes, it was able to find correct homographies where the baseline could not. Therefore, the cycle-GAN model proved to complement the baseline. / TRACAB Image Tracking System används av ChyronHego för spårning av bollen och spelaren påfotbollsplaner. Detta kräver kalibrering av kamerorna runt arenan som störs av staket och andra nätstrukturer som är placerade mellan kameran och fältet som en säkerhetsåtgärd för publiken. Detta examensabrete fokuserar påimplementeringen av en cycle-GAN för borttagning av nätet från bilden med hjälp av oparade data. Cycle-GAN är en bild-till-bild-översättning state-of-the-art teknik och det kan lösa denna typ av problem utan parade bilder. Detta gör det till en spännande och kraftfull metod och enligt den senaste forskningen har det aldrig använts för denna typ av tillämpning förut. Modellen kunde kraftigt dämpa och i vissa fall helt ta bort nätstrukturen från bilder. För att kvantifiera effekterna av avlägsnandet av nätet utfördes en homografimatchning. Därefter jämfördes det med homografin associerad med baslinjen där bilden görs suddig med ett gaussiskt filter och originalbilden utan användning av något filter. Resultaten visade att identifieringen av nyckelpunkter var svårare påsyntetiska bilder än påoriginalbilder med eller utan småGauss-filter, men det visade bättre prestanda än bilder som var suddigt med filter med en standardavvikelse på 3 pixlar eller mer. Trots att prestandan inte var bättre än baslinjen i alla fall lade versionen utan nätet alltid till nya nyckelpunkter, och ibland kunde den hitta korrekta homografier där baslinjen misslyckades. Därför, cycle-GAN-modellen kompletterar baslinjen.

This thesis focuses on visual multiple-target tracking (MTT) from a UAV. Typical state-of-the-art multiple-target trackers rely on an object detector as the primary detection source. However, object detectors usually require a GPU to process images in real-time, which may not be feasible to carry on-board a UAV. Additionally, they often do not produce consistent detections for small objects typical of UAV imagery.In our method, we instead detect motion to identify objects of interest in the scene. We detect motion at corners in the image using optical flow. We also track points long-term to continue tracking stopped objects. Since our motion detection algorithm generates multiple detections at each time-step, we use a hybrid probabilistic data association filter combined with a single iteration of expectation maximization to improve tracking accuracy.We also present a motion detection algorithm that accounts for parallax in non-planar UAV imagery. We use the essential matrix to distinguish between true object motion and apparent object motion due to parallax. Instead of calculating the essential matrix directly, which can be time-consuming, we design a new algorithm that optimizes the rotation and translation between frames. This new algorithm requires only 4 ms instead of 47 ms per frame of the video sequence.We demonstrate the performance of these algorithms on video data. These algorithms are shown to improve tracking accuracy, reliability, and speed. All these contributions are capable of running in real-time without a GPU.

La vidéosurveillance a pour objectif principal de protéger les personnes et les biens en détectant tout comportement anormal. Ceci ne serait possible sans la détection de mouvement dans l’image. Ce processus complexe se base le plus souvent sur une opération de soustraction de l’arrière-plan statique d’une scène sur l’image. Mais il se trouve qu’en vidéosurveillance, des caméras sont souvent en mouvement, engendrant ainsi, un changement significatif de l’arrière-plan; la soustraction de l’arrière-plan devient alors problématique. Nous proposons dans ce travail, une méthode de détection de mouvement et particulièrement de chutes qui s’affranchit de la soustraction de l’arrière-plan et exploite la rotation de la caméra dans la détection du mouvement en utilisant le calcul homographique. Nos résultats sur des données synthétiques et réelles démontrent la faisabilité de cette approche. / The main objective of video surveillance is to protect persons and property by detecting any abnormal behavior. This is not possible without detecting motion in the image. This process is often based on the concept of subtraction of the scene background. However in video tracking, the cameras are themselves often in motion, causing a significant change of the background. So, background subtraction techniques become problematic. We propose in this work a motion detection approach, with the example application of fall detection. This approach is free of background subtraction for a rotating surveillance camera. The method uses the camera rotation to detect motion by using homographic calculation. Our results on synthetic and real video sequences demonstrate the feasibility of this approach.

Dans la première partie de ma thèse, il est démontré, dans les espaces de Banach et de Fréchet de suites, un résultat d'existence d'un sous-espace fermé de dimension infinie dont les éléments non-nuls sont des séries universelles.La deuxième partie est consacrée à l'étude des opérateurs de composition sur des espaces de fonctions holomorphes de plusieurs variables complexes. Dans un premier temps, le spectre et la dynamique des opérateurs de composition hyperboliques sur les espaces de Hardy de la boule sont décrits complètement.Dans un second temps, la continuité et la compacité des opérateurs de composition sur les espaces de Hardy-Orlicz et de Bergman-Orlicz de la boule sont caractérisées. On en déduit en particulier l'existence d'une classe de fonctions d'Orlicz définissant des espaces du type précédent sur lesquels tout opérateur de composition est continu. / In the first part of my thesis, a result on the existence of a closed infinite-dimensional subspace, whose non-zero elements are universal series, is given in Banach and Fréchet spaces framework.The second part is devoted to the study of composition operators on spaces of several variables analytic functions. First, the spectrum and the dynamics of hyperbolic composition operators acting on Hardy spaces on the ball are completely described.Second, continuity and compactness of composition operators on Hardy-Orlicz and Bergman-Orlicz spaces on the ball are characterized. In particular, we deduce from the treatment of the continuity that there exists a class of Orlicz functions which define Hardy-Orlicz and Bergman-Orlicz spaces, on which every composition operator is bounded.

In this paper, a method for determining ground plane features in a sequence of images captured by a mobile camera is presented. The hardware of the mobile system consists of a monocular camera that is mounted on an inertial measurement unit (IMU). An image processing procedure is proposed, first to extract image features and match them across consecutive image frames, and second to detect the ground plane features using a two-step algorithm. In the first step, the planar homography of the ground plane is constructed using an IMU-camera motion estimation approach. The obtained homography constraints are used to detect the most likely ground features in the sequence of images. To reject the remaining outliers, as the second step, a new plane normal vector computation approach is proposed. To obtain the normal vector of the ground plane, only three pairs of corresponding features are used for a general camera transformation. The normal-based computation approach generalizes the existing methods that are developed for specific camera transformations. Experimental results on real data validate the reliability of the proposed method. / <p>QC 20121107</p>

La vidéosurveillance a pour objectif principal de protéger les personnes et les biens en détectant tout comportement anormal. Ceci ne serait possible sans la détection de mouvement dans l’image. Ce processus complexe se base le plus souvent sur une opération de soustraction de l’arrière-plan statique d’une scène sur l’image. Mais il se trouve qu’en vidéosurveillance, des caméras sont souvent en mouvement, engendrant ainsi, un changement significatif de l’arrière-plan; la soustraction de l’arrière-plan devient alors problématique. Nous proposons dans ce travail, une méthode de détection de mouvement et particulièrement de chutes qui s’affranchit de la soustraction de l’arrière-plan et exploite la rotation de la caméra dans la détection du mouvement en utilisant le calcul homographique. Nos résultats sur des données synthétiques et réelles démontrent la faisabilité de cette approche. / The main objective of video surveillance is to protect persons and property by detecting any abnormal behavior. This is not possible without detecting motion in the image. This process is often based on the concept of subtraction of the scene background. However in video tracking, the cameras are themselves often in motion, causing a significant change of the background. So, background subtraction techniques become problematic. We propose in this work a motion detection approach, with the example application of fall detection. This approach is free of background subtraction for a rotating surveillance camera. The method uses the camera rotation to detect motion by using homographic calculation. Our results on synthetic and real video sequences demonstrate the feasibility of this approach.

Dans cette thèse, en collaboration avec l'entreprise AéroDRONES, le Laboratoire Bordelais de Recherche en Informatique et l'INRIA, nous abordons le problème de la perception de l'environnement à partir d'une caméra embarquée sur un drone léger. Nous avons conçu, développé et validé de nouvelles méthodes de traitement qui optimisent l'exploitation des données produites par des systèmes de prise de vue aéroportés bas coût. D'une part, nous présentons une méthode d'autocalibrage de la caméra et de la tourelle d'orientation, sans condition spécifique sur l'environnement observé. Ensuite nous proposons un nouvel algorithme pour extraire la rotation de la caméra calibrée entre deux images (gyroscope visuel) et l'appliquons à la stabilisation vidéo en temps réel. D'autre part, nous proposons une méthode de géoréférencement des images par fusion avec un fond cartographique existant. Cette méthode permet d'enrichir des bases de données de photos aériennes, en gérant les cas de non-planéité du terrain. / The last decade has seen the emergence of many Unmanned Aerial Vehicles (UAV) which are becoming increasingly cheap and miniaturized. A mounted video-camera is standard equipment and can be found on any such UAVs. In this context, we present robust techniques to enhance autonomy levels of airborne vision systems based on mini-UAV technologies. First, we present a camera autocalibration method based on central projection based image \dimension{2}-invariants analysis and we compare it to classical Dual Image of the Absolute Conic (DIAC) technique. We present also a method to detect and calibrate turret's effectors hierarchy. Then, we propose a new algorithm to extract a calibrated camera self-rotation (visual gyroscope) and we apply it to propose a real-time video stabilizer with full perspective correction.

This work deals with the orientation of the camera in real-time with a single camera. Offline methods are described and used as a reference for comparison of a real-time metods. Metods work in real-time Monocular SLAM and PTAM methods are there described and compared. Further, paper shows hints of advanced methods whereas future work is possible.

This thesis deals with problematics of PTZ-camera re-calibration during movement. The objective of this work is to keep the camera in calibration mode from default status when the known positions of Vanishing Points are in the image. With their use during movement, which is changing with motion of the camera, their positions are kept with help of two implemented methods. The first method is based on the principle of homography, the second on the principle of cross ratio. The results show that both of these methods work especially for keeping the positions of First Vanishing Points. In the case of the Second Vanishing Points there appear various problems and the results are often quite inaccurate.

Cette thèse traite des caméras light-field en tant que caméra ayant des capacités 3D. Les images brutes, acquises avec ces systèmes, sont généralement inexploitables directement. L’obstacle majeur concernant l'utilisation de ces caméras réside dans la complexité du traitement des images acquises. Cette thèse vise à dépasser ces limitations en s'intéressant aux dispositifs multi-vues et multi-caméras. De plus, comme l'un des domaines d'application envisagé est la vision industrielle, les images sont acquises en lumière naturelle afin de conserver la possibilité d'effectuer des traitements conventionnels par vision sur les images. Le travail de thèse repose sur trois axes : l'étude et la conception optique de systèmes light-field multi-caméras et multi-vues, le calibrage de ces dispositifs et le développement d’algorithmes et enfin leur mise en application pour montrer les intérêts de ces caméras dans divers domaines. / This thesis deals with light-field cameras as cameras having 3D capacities. The raw images. acquired with these systems, are generally unusable directly. The main obstacle about their use lies in the complex processing of the recorded images. This thesis aims to overcome these limitations by focusing on multi-views and multi-camera devices. Morcover, as one of the application domains is the industrial vision, the images are acquired in natural lightning in order to conserve the possibility to make conventional treatments by vision on the images. The work is based on three axis: the study and'the optical desien of light-field systems, the calibration of these devices and the development of algorithms to show the intercsts of these cameras in various fields.