Computer Vision - ECCV 2002

1. Front Matter

   Pages I-XXVIII

   PDF

2. Active and Real-Time Vision

   1. Tracking with the EM Contour Algorithm

      • Arthur E. C. Pece, Anthony D. Worrall

      Pages 3-17

   2. M2Tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene Using Region-Based Stereo

      • Anurag Mittal, Larry S. Davis

      Pages 18-33

3. Image Features

   1. Analytical Image Models and Their Applications

      • Anuj Srivastava, Xiuwen Liu, Ulf Grenander

      Pages 37-51

   2. Time-Recursive Velocity-Adapted Spatio-Temporal Scale-Space Filters

      • Tony Lindeberg

      Pages 52-67

   3. Combining Appearance and Topology for Wide Baseline Matching

      • Dennis Tell, Stefan Carlsson

      Pages 68-81

   4. Guided Sampling and Consensus for Motion Estimation

      • Ben Tordoff, David W Murray

      Pages 82-96

4. Image Features / Visual Motion

   1. Fast Anisotropic Gauss Filtering

      • Jan-Mark Geusebroek, Arnold W. M. Smeulders, Joost van de Weijer

      Pages 99-112

   2. Adaptive Rest Condition Potentials: Second Order Edge-Preserving Regularization

      • Mariano Rivera, Jose L. Marroquin

      Pages 113-127

   3. An Affine Invariant Interest Point Detector

      • Krystian Mikolajczyk, Cordelia Schmid

      Pages 128-142

   4. Understanding and Modeling the Evolution of Critical Points under Gaussian Blurring

      • Arjan Kuijper, Luc Florack

      Pages 143-157

   5. Image Processing Done Right

      • Jan J. Koenderink, Andrea J. van Doorn

      Pages 158-172

   6. Multimodal Data Representations with Parameterized Local Structures

      • Ying Zhu, Dorin Comaniciu, Stuart Schwartz, Visvanathan Ramesh

      Pages 173-189

   7. The Relevance of Non-generic Events in Scale Space Models

      • Arjan Kuijper, Luc Florack

      Pages 190-204

   8. The Localized Consistency Principle for Image Matching under Non-uniform Illumination Variation and Affine Distortion

      • Bing Wang, Kah Kay Sung, Teck Khim Ng

      Pages 205-219

   9. Resolution Selection Using Generalized Entropies of Multiresolution Histograms

      • Efstathios Hadjidemetriou, Michael D. Grossberg, Shree K. Nayar

      Pages 220-235

   10. Robust Computer Vision through Kernel Density Estimation

       • Haifeng Chen, Peter Meer

       Pages 236-250

   11. Constrained Flows of Matrix-Valued Functions: Application to Diffusion Tensor Regularization

       • C. Chefd’hotel, D. Tschumperlé, R. Deriche, O. Faugeras

       Pages 251-265

   12. A Hierarchical Framework for Spectral Correspondence

       • Marco Carcassoni, Edwin R. Hancock

       Pages 266-281

   13. Phase-Based Local Features

       • Gustavo Carneiro, Allan D. Jepson

       Pages 282-296

Premiering in 1990 in Antibes, France, the European Conference on Computer Vision, ECCV, has been held biennially at venues all around Europe. These conferences have been very successful, making ECCV a major event to the computer vision community. ECCV 2002 was the seventh in the series. The privilege of organizing it was shared by three universities: The IT University of Copenhagen, the University of Copenhagen, and Lund University, with the conference venue in Copenhagen. These universities lie ¨ geographically close in the vivid Oresund region, which lies partly in Denmark and partly in Sweden, with the newly built bridge (opened summer 2000) crossing the sound that formerly divided the countries. We are very happy to report that this year’s conference attracted more papers than ever before, with around 600 submissions. Still, together with the conference board, we decided to keep the tradition of holding ECCV as a single track conference. Each paper was anonymously refereed by three different reviewers. For the ?nal selection, for the ?rst time for ECCV, a system with area chairs was used. These met with the program chairsinLundfortwodaysinFebruary2002toselectwhatbecame45oralpresentations and 181 posters.Also at this meeting the selection was made without knowledge of the authors’identity.

• 3D reconstruction
• Stereo
• calibration
• camera calibration
• cognition
• computational geometry
• computer vision
• geometric computation
• learning
• motion tracking
• object recognition
• robot
• shading
• shape reconstruction
• stereo vision

• Centre for Mathematical Sciences, Lund University, Lund, Sweden

  Anders Heyden, Gunnar Sparr

• The IT University of Copenhagen, Copenhagen, Denmark

  Mads Nielsen

• University of Copenhagen, Copenhagen, Denmark

  Peter Johansen

Policies and ethics