Computer Vision - ECCV 2004: 8th European Conference on Computer Vision, Prague, Czech Republic, May 11-14, 2004. Proceedings, Part I (Lecture Notes in Computer Science (3021))

Welcome to the proceedings of the 8th European Conference on Computer - sion! Following a very successful ECCV 2002, the response to our call for papers was almost equally strong – 555 papers were submitted. We accepted 41 papers for oral and 149 papers for poster presentation. Several innovations were introduced into the review process. First, the n- ber of program committee members was increased to reduce their review load. We managed to assign to program committee members no more than 12 papers. Second, we adopted a paper ranking system. Program committee members were asked to rank all the papers assigned to them, even those that were reviewed by additional reviewers. Third, we allowed authors to respond to the reviews consolidated in a discussion involving the area chair and the reviewers. Fourth, thereports,thereviews,andtheresponsesweremadeavailabletotheauthorsas well as to the program committee members. Our aim was to provide the authors with maximal feedback and to let the program committee members know how authors reacted to their reviews and how their reviews were or were not re?ected in the ?nal decision. Finally, we reduced the length of reviewed papers from 15 to 12 pages. ThepreparationofECCV2004wentsmoothlythankstothee?ortsofthe- ganizing committee, the area chairs, the program committee, and the reviewers. We are indebted to Anders Heyden, Mads Nielsen, and Henrik J. Nielsen for passing on ECCV traditions and to Dominique Asselineau from ENST/TSI who kindly provided his GestRFIA conference software. We thank Jan-Olof Eklundh and Andrew Zisserman for encouraging us to organize ECCV 2004 in Prague. Front Matter....Pages - A Unified Algebraic Approach to 2-D and 3-D Motion Segmentation....Pages 1-15 Enhancing Particle Filters Using Local Likelihood Sampling....Pages 16-27 A Boosted Particle Filter: Multitarget Detection and Tracking....Pages 28-39 Simultaneous Object Recognition and Segmentation by Image Exploration....Pages 40-54 Recognition by Probabilistic Hypothesis Construction....Pages 55-68 Human Detection Based on a Probabilistic Assembly of Robust Part Detectors....Pages 69-82 Model Selection for Range Segmentation of Curved Objects....Pages 83-94 High-Contrast Color-Stripe Pattern for Rapid Structured-Light Range Imaging....Pages 95-107 Using Inter-feature-Line Consistencies for Sequence-Based Object Recognition....Pages 108-120 Discriminant Analysis on Embedded Manifold....Pages 121-132 Multiscale Inverse Compositional Alignment for Subdivision Surface Maps....Pages 133-145 A Fourier Theory for Cast Shadows....Pages 146-162 Surface Reconstruction by Propagating 3D Stereo Data in Multiple 2D Images....Pages 163-174 Visibility Analysis and Sensor Planning in Dynamic Environments....Pages 175-189 Camera Calibration from the Quasi-affine Invariance of Two Parallel Circles....Pages 190-202 Texton Correlation for Recognition....Pages 203-214 Multiple View Feature Descriptors from Image Sequences via Kernel Principal Component Analysis....Pages 215-227 An Affine Invariant Salient Region Detector....Pages 228-241 A Visual Category Filter for Google Images....Pages 242-256 Scene and Motion Reconstruction from Defocused and Motion-Blurred Images via Anisotropic Diffusion....Pages 257-269 Semantics Discovery for Image Indexing....Pages 270-281 Hand Gesture Recognition within a Linguistics-Based Framework....Pages 282-296 Line Geometry for 3D Shape Understanding and Reconstruction....Pages 297-309 Extending Interrupted Feature Point Tracking for 3-D Affine Reconstruction....Pages 310-321 Many-to-Many Feature Matching Using Spherical Coding of Directed Graphs....Pages 322-335 Coupled-Contour Tracking through Non-orthogonal Projections and Fusion for Echocardiography....Pages 336-349 A Statistical Model for General Contextual Object Recognition....Pages 350-362 Reconstruction from Projections Using Grassmann Tensors....Pages 363-375 Co-operative Multi-target Tracking and Classification....Pages 376-389 A Linguistic Feature Vector for the Visual Interpretation of Sign Language....Pages 390-401 Fast Object Detection with Occlusions....Pages 402-413 Pose Estimation of Free-Form Objects....Pages 414-427 Interactive Image Segmentation Using an Adaptive GMMRF Model....Pages 428-441 Can We Consider Central Catadioptric Cameras and Fisheye Cameras within a Unified Imaging Model....Pages 442-455 Image Clustering with Metric, Local Linear Structure, and Affine Symmetry....Pages 456-468 Face Recognition with Local Binary Patterns....Pages 469-481 Steering in Scale Space to Optimally Detect Image Structures....Pages 482-494 Hand Motion from 3D Point Trajectories and a Smooth Surface Model....Pages 495-507 A Robust Probabilistic Estimation Framework for Parametric Image Models....Pages 508-522 Keyframe Selection for Camera Motion and Structure Estimation from Multiple Views....Pages 523-535 Omnidirectional Vision: Unified Model Using Conformal Geometry....Pages 536-548 A Robust Algorithm for Characterizing Anisotropic Local Structures....Pages 549-561 Dimensionality Reduction by Canonical Contextual Correlation Projections....Pages 562-573 Accuracy of Spherical Harmonic Approximations for Images of Lambertian Objects under Far and Near Lighting....Pages 574-587 Characterization of Human Faces under Illumination Variations Using Rank, Integrability, and Symmetry Constraints....Pages 588-601 User Assisted Separation of Reflections from a Single Image Using a Sparsity Prior....Pages 602-613 The Quality of Catadioptric Imaging – Application to Omnidirectional Stereo....Pages 614-627 Back Matter....Pages - Welcome to the proceedings of the 8th European Conference on Computer - sion! Following a very successful ECCV 2002, the response to our call for papers was almost equally strong - 555 papers were submitted. We accepted 41 papers for oral and 149 papers for poster presentation. Several innovations were introduced into the review process. First, the n- ber of program committee members was increased to reduce their review load. We managed to assign to program committee members no more than 12 papers. Second, we adopted a paper ranking system. Program committee members were asked to rank all the papers assigned to them, even those that were reviewed by additional reviewers. Third, we allowed authors to respond to the reviews consolidated in a discussion involving the area chair and the reviewers. Fourth, thereports, thereviews, andtheresponsesweremadeavailabletotheauthorsas well as to the program committee members. Our aim was to provide the authors with maximal feedback and to let the program committee members know how authors reacted to their reviews and how their reviews were or were not re?ected in the?nal decision. Finally, we reduced the length of reviewed papers from 15 to 12 pages. ThepreparationofECCV2004wentsmoothlythankstothee?ortsofthe- ganizing committee, the area chairs, the program committee, and the reviewers. We are indebted to Anders Heyden, Mads Nielsen, and Henrik J. Nielsen for passing on ECCV traditions and to Dominique Asselineau from ENST/TSI who kindly provided his GestRFIA conference software. We thank Jan-Olof Eklundh and Andrew Zisserman for encouraging us to organize ECCV 2004 in Prague

The four-volume set comprising LNCS volumes 3021/3022/3023/3024 constitutes the refereed proceedings of the 8th European Conference on Computer Vision, ECCV 2004, held in Prague, Czech Republic, in May 2004.

The 190 revised papers presented were carefully reviewed and selected from a total of 555 papers submitted. The four books span the entire range of current issues in computer vision. The papers are organized in topical sections on tracking; feature-based object detection and recognition; geometry; texture; learning and recognition; information-based image processing; scale space, flow, and restoration; 2D shape detection and recognition; and 3D shape representation and reconstruction.

Annotation The four-volume set comprising LNCS volumes 3021/3022/3023/3024 constitutes the refereed proceedings of the 8th European Conference on Computer Vision, ECCV 2004, held in Prague, Czech Republic, in May 2004. The 190 revised papers presented were carefully reviewed and selected from a total of 555 papers submitted. The four books span the entire range of current issues in computer vision. The papers are organized in topical sections on tracking; feature-based object detection and recognition; geometry; texture; learning and recognition; information-based image processing; scale space, flow, and restoration; 2D shape detection and recognition; and 3D shape representation and reconstruction