Abstract According to the development of industry, conventional surveillance system has not already satisfied by the demand today. The combination application of the CCD camera and image analysis technology in personal computer could enhance the functionality and more and more get a lot of attraction on it. Therefore, CCD camera is gradually popular in people live and industry application. However, CCD camera depends on the process ability of personal computer very much. Furthermore, it can¡¦t work well independently on the application. Based on these problems, this paper proposes an effective monitoring technique to establish an image servo module through using the embedding Ethernet controller with CMOS image sensor. The ¡§image servo module¡¨ can execute independently the designate image monitor work. Eventually, an ¡§Internet-based remote visual monitoring system¡¨ was built by integrating ¡§image servo module¡¨ and ¡§database service system¡¨ to widely promote the application on surveillance system. From the experiment system, user can use the IE explore or Netscape to supervise the internet-based image monitor system from web-server. In addition, a real-time monitor system based on VB program tool was also developed for any computer to monitor or setup the remote image server module to achieve the designated work. The transfer speed of Internet image server system is 7~8 frames/s. Keywords¡Gimage servo module, Internet-based remote visual monitoring systems

Ants typically use path integration and vision for navigation when the environment precludes the use of pheromones for trails. Recent simulations have been able to accurately mimic the retinotopic navigation behaviour of these ants using simple models of movement and memory of unprocessed visual images. Naturally it is interesting to test these navigation algorithms in more realistic circumstances, particularly with actual route data from the ant, in an accurate facsimile of the ant world and with visual input that draws on the characteristics of the animal. While increasing the complexity of the visual processing to include skyline extraction, inhomogeneous sampling and motion processing was conjectured to improve the performance of the simulations, the reverse appears to be the case. Examining closely the assumptions about motion, analysis of ants in the field shows that they experience considerable displacement of the head which when applied to the simulation leads to significant degradation in performance. The family of simulations rely upon continuous visual monitoring of the scene to determine heading and it was decided to test whether the animals were similarly dependent on this input. A field study demonstrated that ants with only visual navigation cues can return the nest when largely facing away from the direction of travel (moving backwards) and so it appears that ant visual navigation is not a process of continuous retinotopic image matching. We conclude ants may use vision to determine an initial heading by image matching and then continue to follow this direction using their celestial compass, or they may use a rotationally invariant form of the visual world for continuous course correction.

L'objectif principal de cette thèse est le développement d'algorithmes événementiels pour la détection et le suivi d'objets. Ces algorithmes sont spécifiquement conçus pour travailler avec une sortie produite par des caméras neuromorphiques. Ce type de caméras sont un nouveau type de capteurs bio inspirés, dont le principe de fonctionnement s'inspire de la rétine: chaque pixel est indépendant et génère des événements de manière asynchrone lorsqu'un changement de luminosité suffisamment important est détecté à la position correspondante du plan focal. Cette nouvelle façon d'encoder l'information visuelle requiert de nouvelles méthodes pour la traiter. D'abord, un suiveur (tracker) plan est décrit. Cet algorithme associe à un objet une série de formes simples reliées par des ressorts. Le système mécanique virtuel résultant est mis à jour pour chaque événement. Le chapitre suivant présente un algorithme de détection de lignes et de segments, pouvant constituer une caractéristique (feature) événementielle de bas niveau. Ensuite, deux méthodes événementielles pour l'estimation de la pose 3D sont présentées. Le premier de ces algorithmes 3D est basé sur l'hypothèse que l'estimation de la pose est toujours proche de la position réelle, et requiert donc une initialisation manuelle. Le deuxième de ces algorithmes 3D est conçu pour surmonter cette limitation. Toutes les méthodes présentées mettent à jour l'estimation de la position (2D ou 3D) pour chaque événement. Cette thèse montre que la vision événementielle permet de reformuler une vaste série de problèmes en vision par ordinateur, souvent donnant lieu à des algorithmes plus simples mais toujours précis. / The main goal of this thesis is the development of event-based algorithms for visual detection and tracking. This algorithms are specifically designed to work on the output of neuromorphic event-based cameras. This type of cameras are a new type of bioinspired sensors, whose principle of operation is based on the functioning of the retina: every pixel is independent and generates events asynchronously when a sufficient amount of change is detected in the luminance at the corresponding position on the focal plane. This new way of encoding visual information calls for new processing methods. First, a part-based shape tracking is presented, which represents an object as a set of simple shapes linked by springs. The resulting virtual mechanical system is simulated with every incoming event. Next, a line and segment detection algorithm is introduced, which can be employed as an event-based low level feature. Two event-based methods for 3D pose estimation are then presented. The first of these 3D algorithms is based on the assumption that the current estimation is close to the true pose of the object, and it consequently requires a manual initialization step. The second of the 3D methods is designed to overcome this limitation. All the presented methods update the estimated position (2D or 3D) of the tracked object with every incoming event. This results in a series of trackers capable of estimating the position of the tracked object with microsecond resolution. This thesis shows that event-based vision allows to reformulate a broad set of computer vision problems, often resulting in simpler but accurate algorithms.

Made available in DSpace on 2014-12-17T14:55:11Z (GMT). No. of bitstreams: 1 DanielGC_TESE_Capa_pag90.pdf: 3923138 bytes, checksum: b23776867381c62bd332c913640275ac (MD5) Previous issue date: 2013-04-29 / The development of wireless sensor networks for control and monitoring functions has created a vibrant investigation scenario, covering since communication aspects to issues related with energy efficiency. When source sensors are endowed with cameras for visual monitoring, a new scope of challenges is raised, as transmission and monitoring requirements are considerably changed. Particularly, visual sensors collect data following a directional sensing model, altering the meaning of concepts as vicinity and redundancy but allowing the differentiation of source nodes by their sensing relevancies for the application. In such context, we propose the combined use of two differentiation strategies as a novel QoS parameter, exploring the sensing relevancies of source nodes and DWT image coding. This innovative approach supports a new scope of optimizations to improve the performance of visual sensor networks at the cost of a small reduction on the overall monitoring quality of the application. Besides definition of a new concept of relevance and the proposition of mechanisms to support its practical exploitation, we propose five different optimizations in the way images are transmitted in wireless visual sensor networks, aiming at energy saving, transmission with low delay and error recovery. Putting all these together, the proposed innovative differentiation strategies and the related optimizations open a relevant research trend, where the application monitoring requirements are used to guide a more efficient operation of sensor networks / O desenvolvimento de redes de sensores sem fio para fun??es de controle e monitoramento tem criado um pulsante cen?rio de investiga??o, abrangendo desde aspectos da comunica??o em rede at? quest?es como efici?ncia energ?tica. Quando sensores s?o equipados com c?meras para fun??es de monitoramento visual, um novo escopo de desafios ? lan?ado, uma vez que h? uma mudan?a significativa nos requisitos de monitoramento e transmiss?o. Em particular, sensores visuais coletam dados seguindo um modelo direcional de monitoramento, alterando conceitos j? estabelecidos de vizinhan?a e redund?ncia, por?m tornando poss?vel a diferencia??o de sensores pelas suas relev?ncias de monitoramento para a aplica??o. Nesse contexto, propomos que a relev?ncia de monitoramento dos sensores fontes sejam exploradas em conjunto com a codifica??o de imagens por transformada DWT, unindo assim dois diferentes escopos de relev?ncia para a cria??o de novos par?metros de QoS. Essa abordagem inovadora permite uma nova gama de otimiza??es da opera??o da rede, possibilitando aumento de desempenho com pequenas perdas na qualidade global de monitoramento. Al?m da defini??o de um novo conceito de relev?ncia e a proposi??o de mecanismos para suportar sua utiliza??o pr?tica, cinco diferentes otimiza??es da transmiss?o de imagens em redes de sensores visuais sem fio s?o propostas, visando economia de energia, transmiss?o com baixo atraso e recupera??o de erros. Em conjunto, as estrat?gias de diferencia??o e as otimiza??es relacionadas abrem uma importante vertente de pesquisa, onde os requisitos de monitoramento das aplica??es s?o utilizados para guiar uma opera??o mais eficiente da rede