Dynamical Vision: ICCV 2005 and ECCV 2006 Workshops, WDV 2005 and WDV 2006, Beijing, China, October 21, 2005, Graz, Austria, May 13, 2006. Revised Papers

Xiaodong Fan, René Vidal (auth.), René Vidal, Anders Heyden, Yi Ma (eds.)3540709312, 9783540709312

Classical multiple-view geometry studies the reconstruction of a static scene – served by a rigidly moving camera. However, in many real-world applications the scene may undergo much more complex dynamical changes. For instance, the scene may consist of multiple moving objects (e.g., a tra?c scene) or arti- lated motions (e.g., a walking human) or even non-rigid dynamics (e.g., smoke, ?re, or a waterfall). In addition, some applications may require interaction with the scene through a dynamical system (e.g., vision-guided robot navigation and coordination). To study the problem of reconstructing dynamical scenes, many new al- braic, geometric, statistical, and computational tools have recently emerged in computer vision, computer graphics, image processing, and vision-based c- trol. The goal of the International Workshop on Dynamical Vision (WDV) is to converge di?erent aspects of the research on dynamical vision and to identify common mathematical problems, models, and methods for future research in this emerging and active area.

---

Table of contents :
Front Matter….Pages –
The Space of Multibody Fundamental Matrices: Rank, Geometry and Projection….Pages 1-17
Direct Segmentation of Multiple 2-D Motion Models of Different Types….Pages 18-33
Motion Segmentation Using an Occlusion Detector….Pages 34-47
Robust 3D Segmentation of Multiple Moving Objects Under Weak Perspective….Pages 48-59
Nonparametric Estimation of Multiple Structures with Outliers….Pages 60-74
Articulated Motion Segmentation Using RANSAC with Priors….Pages 75-85
Articulated-Body Tracking Through Anisotropic Edge Detection….Pages 86-99
Homeomorphic Manifold Analysis: Learning Decomposable Generative Models for Human Motion Analysis….Pages 100-114
View-Invariant Modeling and Recognition of Human Actions Using Grammars….Pages 115-126
Segmenting Dynamic Textures with Ising Descriptors, ARX Models and Level Sets….Pages 127-141
Spatial Segmentation of Temporal Texture Using Mixture Linear Models….Pages 142-150
Online Video Registration of Dynamic Scenes Using Frame Prediction….Pages 151-164
Dynamic Texture Recognition Using Volume Local Binary Patterns….Pages 165-177
A Rao-Blackwellized Parts-Constellation Tracker….Pages 178-189
Bayesian Tracking with Auxiliary Discrete Processes. Application to Detection and Tracking of Objects with Occlusions….Pages 190-202
Tracking of Multiple Objects Using Optical Flow Based Multiscale Elastic Matching….Pages 203-217
Real-Time Tracking with Classifiers….Pages 218-231
A Probabilistic Framework for Correspondence and Egomotion….Pages 232-242
Estimating the Pose of a 3D Sensor in a Non-rigid Environment….Pages 243-256
A Batch Algorithm for Implicit Non-rigid Shape and Motion Recovery….Pages 257-269
Using a Connected Filter for Structure Estimation in Perspective Systems….Pages 270-284
Recursive Structure from Motion Using Hybrid Matching Constraints with Error Feedback….Pages 285-298
Force/Vision Based Active Damping Control of Contact Transition in Dynamic Environments….Pages 299-313
Segmentation and Guidance of Multiple Rigid Objects for Intra-operative Endoscopic Vision….Pages 314-327
Back Matter….Pages –