(Uncorrected OCR) Abstract of thesis entitled A Factorization-Based Approach to Projective Reconstruction from Line Correspondences in Multiple Images Submitted by Ng Tuen Pui for the degree of Master of Philosophy at The University of Hong Kong in August 2004 This study addresses the problems of using line correspondences for the reconstruction of 3D scene from multiple images. Compared with planar images, a 3D model is a more informative mode of presentation. Existing methods of reconstructing 3D objects from images mainly make use of feature point correspondences across images. Straight lines, nevertheless, are more flexible in dealing with occlusion and less sensitive to noise. Besides, as most modern man-made structures are largely rectangular, straight line is an appropriate medium for describing these structures. The possibility of using straight lines as features for reconstruction is therefore a worthwhile topic for research. Before reconstruction can be carried out from an image sequence, the images must be analyzed. This process includes the detection of line features and the matching of corresponding line features across different images. As the quality of the detected and matched lines is critical to the performance of the reconstruction, this study initially explores methods of image analysis. Practical experience in edge detection was obtained in order to identify difficulties and take appropriate measures to ensure satisfactory 3D reconstruction. It was found that the main difficulty in line features extraction was to determine the end points of the lines accurately. Given the success of the factorization method in point reconstruction, an existing factorization-based method for line reconstruction was studied in detail. However, the line factorization method was found to be very sensitive to noise, and was unable to offer a practical solution to the problem. In the light of these studies, an efficient line reconstruction method is proposed. In order.

It is with great pleasure that we present the proceedings of the 6th Inter- tional, Symposium on Visual Computing (ISVC 2010), which was held in Las Vegas, Nevada. ISVC provides a common umbrella for the four main areas of visual computing including vision, graphics, visualization, and virtual reality. The goal is to provide a forum for researchers, scientists, engineers, and pr- titioners throughout the world to present their latest research ?ndings, ideas, developments, and applications in the broader area of visual computing. This year, the program consisted of 14 oral sessions, one poster session, 7 special tracks, and 6 keynote presentations. The response to the call for papers was very good; we received over 300 submissions for the main symposium from which we accepted 93 papers for oral presentation and 73 papers for poster p- sentation. Special track papers were solicited separately through the Organizing and Program Committees of each track. A total of 44 papers were accepted for oral presentation and 6 papers for poster presentation in the special tracks.

Computational methodologies of signal processing and imaging analysis, namely considering 2D and 3D images, are commonly used in different applications of the human society. For example, Computational Vision systems are progressively used for surveillance tasks, traf?c analysis, recognition process, inspection p- poses, human-machine interfaces, 3D vision and deformation analysis. One of the main characteristics of the Computational Vision domain is its int- multidisciplinary. In fact, in this domain, methodologies of several more fundam- tal sciences, such as Informatics, Mathematics, Statistics, Psychology, Mechanics and Physics are usually used. Besides this inter-multidisciplinary characteristic, one of the main reasons that contributes for the continually effort done in this domain of the human knowledge is the number of applications in the medical area. For instance, it is possible to consider the use of statistical or physical procedures on medical images in order to model the represented structures. This modeling can have different goals, for example: shape reconstruction, segmentation, registration, behavior interpretation and simulation, motion and deformation analysis, virtual reality, computer-assisted therapy or tissue characterization. The main objective of the ECCOMAS Thematic Conferences on Computational Vision and Medical Image Processing (VIPimage) is to promote a comprehensive forum for discussion on the recent advances in the related ?elds trying to id- tify widespread areas of potential collaboration between researchers of different sciences.

This title is part of a two volume set that constitutes the refereed proceedings of the 8th Asian Conference on Computer Vision, ACCV 2007. Coverage includes shape and texture, image and video processing, face and gesture, tracking, camera networks, learning, motion and tracking, retrieval and search, human pose estimation, matching, face/gesture/action detection and recognition, low level vision and phtometory, motion and tracking, human detection, and segmentation.

This book constitutes the strictly refereed post-workshop proceedings of the European Workshop on 3D Structure from Multiple Images of Large-Scale Environments, SMILE'98, held in conjunction with ECCV'98 in Freiburg, Germany, in June 1998. The 21 revised full papers presented went through two cycles of reviewing and were carefully selected for inclusion in the book. The papers are organized in sections on multiview relations and correspondence search, 3D structure from multiple images, callibration and reconstruction using scene constraints, range integration and augmented reality application.