ICCV'07 Workshop on Dynamical Vision 
             Oct 20, 2007, Rio de Janeiro, Brazil 

             http://vision.jhu.edu/iccv2007-wdv/ 
  

The classical multiple-view geometry studies the case with a 
moving camera viewing a static scene. Many real-world applications 
however require the modeling and reconstruction of a scene that 
has much more complex dynamics. That is, the scene may consist of 
multiple moving objects (e.g., a traffic scene) or articulate 
motions (e.g., a walking human) or even non-rigid dynamics (e.g., 
smoke, fire, waterfall). To study the problems of reconstructing 
different dynamical scenes, many new algebraic, geometric, 
statistical, and computational tools have recently emerged in 
computer vision, computer graphics, image processing, and 
vision-based control. 

The goal of this workshop is to converge different aspects of 
the research on dynamical vision and identify common mathematical 
problems, models, and methods for future research in this emerging 
new topic. The workshop welcomes papers that fall into the 
following categories: 

  a. Segmentation, Estimation, Tracking of Multiple Rigid-Body Motions. 
     - Based on Optical Flows or Image Gradients 
     - Based on Feature Correspondences 
     - Integrated Approaches and Hybrid Motion Models 

  b. Segmentation, Estimation, Tracking of Articulate and/or Non-Rigid 
Motions. 
     - Human Motions 
     - Non-Rigid Motions 

  c. Identification and Recognition of Dynamical Scenes from Videos. 
     - Dynamical Textures 
     - Video Segmentation 

  d. Mathematical Tools for Modeling, Analysis, and Synthesis of 
Dynamical Scenes. 
     - Subspace Methods and High-Order Tensors 
     - Dynamical Systems 
     - Stochastic Models (e.g. Hidden Markov Models) 

  e. Applications of Dynamical Vision (e.g., Surveillance, Graphics, and 
Robotics, etc.) 
     - Visual Servoing and Vision-Based Control & Navigation 
     - Localization and Mapping 
  

Submission Guidelines: 

Please submit your paper by midnight (your local time) May 25, 2007 
in PDF format via the web-based submission link: 

           http://vision.jhu.edu/iccv2007-wdv/ 

(Email submission can be offered as an alternative upon early 
request by the authors). 

Paper should not exceed 14 pages in Springer LNCS format. 
All submissions are subject to a double-blind review 
process by the program committee. Therefore, the papers should be 
strictly anonymous. In the submission email, please provide the 
following info (for the organizers only): 

1. Title of your paper: 
2. Authors and their affiliations 
3. Contact info (email, phone, fax) of the corresponding author(s).