Dynamical Vision

1. Front Matter

   PDF

2. Motion Segmentation and Estimation

   1. The Space of Multibody Fundamental Matrices: Rank, Geometry and Projection

      • Xiaodong Fan, René Vidal

      Pages 1-17

   2. Direct Segmentation of Multiple 2-D Motion Models of Different Types

      • Dheeraj Singaraju, René Vidal

      Pages 18-33

   3. Motion Segmentation Using an Occlusion Detector

      • Doron Feldman, Daphna Weinshall

      Pages 34-47

   4. Robust 3D Segmentation of Multiple Moving Objects Under Weak Perspective

      • Levente Hajder, Dmitry Chetverikov

      Pages 48-59

   5. Nonparametric Estimation of Multiple Structures with Outliers

      • Wei Zhang, Jana Kǒsecká

      Pages 60-74

3. Human Motion Analysis, Tracking and Recognition

   1. Articulated Motion Segmentation Using RANSAC with Priors

      • Jingyu Yan, Marc Pollefeys

      Pages 75-85

   2. Articulated-Body Tracking Through Anisotropic Edge Detection

      • David Knossow, Joost van de Weijer, Radu Horaud, Rémi Ronfard

      Pages 86-99

   3. Homeomorphic Manifold Analysis: Learning Decomposable Generative Models for Human Motion Analysis

      • Chan-Su Lee, Ahmed Elgammal

      Pages 100-114

   4. View-Invariant Modeling and Recognition of Human Actions Using Grammars

      • Abhijit S. Ogale, Alap Karapurkar, Yiannis Aloimonos

      Pages 115-126

4. Dynamic Textures

   1. Segmenting Dynamic Textures with Ising Descriptors, ARX Models and Level Sets

      • Atiyeh Ghoreyshi, René Vidal

      Pages 127-141

   2. Spatial Segmentation of Temporal Texture Using Mixture Linear Models

      • Lee Cooper, Jun Liu, Kun Huang

      Pages 142-150

   3. Online Video Registration of Dynamic Scenes Using Frame Prediction

      • Alex Rav-Acha, Yael Pritch, Shmuel Peleg

      Pages 151-164

   4. Dynamic Texture Recognition Using Volume Local Binary Patterns

      • Guoying Zhao, Matti Pietikäinen

      Pages 165-177

5. Motion Tracking

   1. A Rao-Blackwellized Parts-Constellation Tracker

      • Grant Schindler, Frank Dellaert

      Pages 178-189

   2. Bayesian Tracking with Auxiliary Discrete Processes. Application to Detection and Tracking of Objects with Occlusions

      • Patrick Pérez, Jaco Vermaak

      Pages 190-202

   3. Tracking of Multiple Objects Using Optical Flow Based Multiscale Elastic Matching

      • Xingzhi Luo, Suchendra M. Bhandarkar

      Pages 203-217

   4. Real-Time Tracking with Classifiers

      • Thierry Chateau, Vincent Gay-Belille, Frederic Chausse, Jean-Thierry Lapresté

      Pages 218-231

6. Rigid and Non-rigid Motion Analysis

   1. A Probabilistic Framework for Correspondence and Egomotion

      • Justin Domke, Yiannis Aloimonos

      Pages 232-242

   2. Estimating the Pose of a 3D Sensor in a Non-rigid Environment

      • Adrien Bartoli

      Pages 243-256

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.

• 3D
• Augmented Reality
• HCI
• Textur
• articulated motions
• cognition
• dynamical models
• dynamical scene analysis
• human motion
• hybrid motion models
• learning
• mapping
• modeling
• motion tracking
• non-rigid dynamics

Policies and ethics