COST: An Approach for Camera Selection and Multi-Object Inference Ordering in Dynamic Scenes

Development of multiple camera based vision systems for analysis of dynamic objects such as humans is challenging due to occlusions and similarity in the appearance of a person with the background and other people- visual “confusion”. Since occlusion and confusion depends on the presence of other people in the scene, it leads to a dependency structure where there are often loops in the resulting Bayesian network. While approaches such as loopy belief propagation can be used for inference, they are computationally expensive and convergence is not guaranteed in many situations. We present a unified approach, COST, that reasons about such dependencies and yields an order for the inference of each person in a group of people and a set of cameras to be used for inferences for a person. Using the probabilistic distribution of the positions and appearances of people, COST performs visibility and confusion analysis for each part of each person and computes the amount of information that ...

• Type: Conference
• Year: 2007
• Where: ICCV
• Authors: Abhinav Gupta, Anurag Mittal, Larry S. Davis
• Keywords: Camera Based Vision, Computer Vision, Dynamic Objects, ICCV 2007, Loopy Belief Propagation