This dissertation, "A Factorization-based Approach to Projective Reconstruction From Line Correspondences in Multiple Images" by Tuen-pui, Ng, 吳端珮, was obtained from The University of Hong Kong (Pokfulam, Hong Kong) and is being sold pursuant to Creative Commons: Attribution 3.0 Hong Kong License. The content of this dissertation has not been altered in any way. We have altered the formatting in order to facilitate the ease of printing and reading of the dissertation. All rights not granted by the above license are retained by the author. Abstract: 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 to take advantage of the success of factorization-based methods for points, the proposed method treats the 3D reconstruction from lines as a point-based problem in which a 3D line is determined by reconstructing two 3D points lying on it. Unlike existing factorization-based methods for points, the input points do not necessarily have to be corresponding points, as long as they lie on the corresponding lines. In other words, a measured line segment in a view can correspond to the measured line segments in other views, even though they are from different portions of a 3D line. The proposed method therefore has high tolerance for the location of end points on measured lines, and can handle occlusion in measured lines. Real and synthetic experiments have demonstrated that the proposed method converges robustly to good results, and therefore offers a feasible solution to line reconstruction. DOI: 10.5353/th_b3010949 Subjects: Image reconstruction Image processing Computer vision

This book constitutes the refereed proceedings of the 7th International Conference on Computer Analysis of Images and Patterns, CAIP '97, held in Kiel, Germany, in September 1997. The volume presents 92 revised papers selected during a double-blind reviewing process from a total of 150 high-quality submissions. The papers are organized in topical sections on pattern analysis, object recognition and tracking, invariants, applications, shape, texture analysis, motion calibration, low-level processing, structure from motion, stereo and correspondence, segmentation and grouping, mathematical morphology, pose estimation, and face analysis.

This volume contains the ?nal version of the papers originally presented at the second SMILE workshop 3D Structure from Multiple Images of Large-scale Environments, which was held on 1-2 July 2000 in conjunction with the Sixth European Conference in Computer Vision at Trinity College Dublin. The subject of the workshop was the visual acquisition of models of the 3D world from images and their application to virtual and augmented reality. Over the last few years tremendous progress has been made in this area. On the one hand important new insightshavebeenobtainedresultinginmore exibilityandnewrepresentations.Onthe other hand a number of techniques have come to maturity, yielding robust algorithms delivering good results on real image data. Moreover supporting technologies – such as digital cameras, computers, disk storage, and visualization devices – have made things possible that were infeasible just a few years ago. Opening the workshop was Paul Debevec s invited presentation on image-based modeling,rendering,andlighting.Hepresentedanumberoftechniquesforusingdigital images of real scenes to create 3D models, virtual camera moves, and realistic computer animations.Theremainderoftheworkshopwasdividedintothreesessions:Computation and Algorithms, Visual Scene Representations, and Extended Environments. After each session there was a panel discussion that included all speakers. These panel discussions were organized by Bill Triggs, Marc Pollefeys, and Tomas Pajdla respectively, who introduced the topics and moderated the discussion. Asubstantialpartoftheseproceedingsarethetranscriptsofthediscussionsfollowing each paper and the full panel sessions. These discussions were of very high quality and were an integral part of the workshop.

A basic problem in computer vision is to understand the structure of a real world scene given several images of it. Techniques for solving this problem are taken from projective geometry and photogrammetry. Here, the authors cover the geometric principles and their algebraic representation in terms of camera projection matrices, the fundamental matrix and the trifocal tensor. The theory and methods of computation of these entities are discussed with real examples, as is their use in the reconstruction of scenes from multiple images. The new edition features an extended introduction covering the key ideas in the book (which itself has been updated with additional examples and appendices) and significant new results which have appeared since the first edition. Comprehensive background material is provided, so readers familiar with linear algebra and basic numerical methods can understand the projective geometry and estimation algorithms presented, and implement the algorithms directly from the book.

The excellently received call for papers of the 13th Scandinavian Conference on Image Analysis, June 29-July 2 (SCIA 2003) resulted in the selected articles of this proceedings. Additionally the volume also contains invited contributions from - Ivar Austvoll, Stavanger University College (NO), - Lars B? a? ath, Halmstad University (SE), - Ewert Bengtsson, Uppsala University (SE), - Rasmus Larsen, Technical University of Denmark (DK), - Jussi Parkkinen, University of Joensuu (FI), - Pietro Perona, California Institute of Technology (US) which brings the total number of articles to 152. The theme of the papers are dominated by the categories - Feature extraction - Depth and surface - Medical image processing - Shape analysis - Segmentation and spatial grouping - Coding and representation - Motion analysis - Texture analysis - Color analysis - Indexing and categorization which also represent the topical groupings of this book. The particularly strong response to the feature extraction, depth and surface, and medical image processing themes makes us believe that these areas are c- rently expansive, partly because of the rich set of problems which remain to be addressed.

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.