Statistical Methods in Video Processing

1. Front Matter

   PDF

2. 3D Geometry

   1. Towards Complete Free-Form Reconstruction of Complex 3D Scenes from an Unordered Set of Uncalibrated Images

      • H. Cornelius, R. Šára, D. Martinec, T. Pajdla, O. Chum, J. Matas

      Pages 1-12

   2. Geometric Structure of Degeneracy for Multi-body Motion Segmentation

      • Yasuyuki Sugaya, Kenichi Kanatani

      Pages 13-25

   3. Virtual Visual Hulls: Example-Based 3D Shape Inference from Silhouettes

      • Kristen Grauman, Gregory Shakhnarovich, Trevor Darrell

      Pages 26-37

   4. Unbiased Errors-In-Variables Estimation Using Generalized Eigensystem Analysis

      • Matthias Mühlich, Rudolf Mester

      Pages 38-49

3. Tracking

   1. Probabilistic Tracking of the Soccer Ball

      • Kyuhyoung Choi, Yongdeuk Seo

      Pages 50-60

   2. Multi-Model Component-Based Tracking Using Robust Information Fusion

      • Bogdan Georgescu, Dorin Comaniciu, Tony X. Han, Xiang Sean Zhou

      Pages 61-70

   3. A Probabilistic Approach to Large Displacement Optical Flow and Occlusion Detection

      • Christoph Strecha, Rik Fransens, Luc Van Gool

      Pages 71-82

   4. Mean-Shift Blob Tracking with Kernel-Color Distribution Estimate and Adaptive Model Update Criterion

      • Ning-Song Peng, Jie Yang

      Pages 83-93

   5. Combining Simple Models to Approximate Complex Dynamics

      • Leonid Taycher, John W. Fisher III, Trevor Darrell

      Pages 94-104

4. Background Modeling

   1. Online Adaptive Gaussian Mixture Learning for Video Applications

      • Dar-Shyang Lee

      Pages 105-116

   2. Novelty Detection in Image Sequences with Dynamic Background

      • Fredrik Kahl, Richard Hartley, Volker Hilsenstein

      Pages 117-128

   3. A Framework for Foreground Detection in Complex Environments

      • Junxian Wang, How-Lung Eng, Alvin H. Kam, Wei-Yun Yau

      Pages 129-140

   4. A Background Maintenance Model in the Spatial-Range Domain

      • Daniel Kottow, Mario Köppen, Javier Ruiz-del-Solar

      Pages 141-152

5. Image/Video Analysis

   1. A New Robust Technique for Stabilizing Brightness Fluctuations in Image Sequences

      • François Pitié, Rozenn Dahyot, Francis Kelly, Anil Kokaram

      Pages 153-164

   2. Factorization of Natural 4 × 4 Patch Distributions

      • Kostadin Koroutchev, José R. Dorronsoro

      Pages 165-174

   3. Parametric and Non-parametric Methods for Linear Extraction

      • Benedicte Bascle, Xiang Gao, Visvanathan Ramesh

      Pages 175-186

   4. Crowd Segmentation Through Emergent Labeling

      • Peter H. Tu, Jens Rittscher

      Pages 187-198

6. Back Matter

   PDF

The 2nd International Workshop on Statistical Methods in Video Processing, SMVP 2004, was held in Prague, Czech Republic, as an associated workshop of ECCV 2004, the 8th European Conference on Computer Vision. A total of 30 papers were submitted to the workshop. Of these, 17 papers were accepted for presentation and included in these proceedings, following a double-blind review process. The workshop had 42 registered participants. The focus of the meeting was on recent progress in the application of - vanced statistical methods to solve computer vision tasks. The one-day scienti?c program covered areas of high interest in vision research, such as dense rec- struction of 3D scenes, multibody motion segmentation, 3D shape inference, errors-in-variables estimation, probabilistic tracking, information fusion, optical ?owcomputation,learningfornonstationaryvideodata,noveltydetectionin- namic backgrounds, background modeling, grouping using feature uncertainty, and crowd segmentation from video. We wish to thank the authors of all submitted papers for their interest in the workshop.Wealsowishtothankthemembersofourprogramcommitteeandthe external reviewers for their commitment of time and e?ort in providing valuable recommendations for each submission. We are thankful to Vaclav Hlavac, the General Chair of ECCV 2004, and to Radim Sara, for the local organization of the workshop and registration management. We hope you will ?nd these proceedings both inspiring and of high scienti?c quality.

• 3D
• 3D shape inference
• Variable
• calculus
• computational geometry
• computer vision
• image processing
• image sequences
• learning
• modeling
• multi-body motion segmentation
• statistical methods
• statistical pattern recognition
• system analysis
• video processing
• algorithm analysis and problem complexity

• Integrated Data Systems Dept., Siemens Corporate Research, Princeton, USA

  Dorin Comaniciu

• Visual Sensorics and Information Processing Lab, J.W. Goethe University, Frankfurt, Germany

  Rudolf Mester

• Department of Computer Science, Okayama University, Okayama, Japan

  Kenichi Kanatani

• Institute for Vision Systems Engineering, Department of Electrical and Computer Systems Engineering, Monash University, Australia

  David Suter

Policies and ethics