Conventional tracking approaches assume proximity in space, time and appearance of objects in successive observations. However, observations of objects are often widely separated in time and space when viewed from multiple non-overlapping cameras. To address this problem, we present a novel approach for establishing object correspondence in a system of non-overlapping cameras. We observe that people or vehicles follow the same paths in most cases, i.e roads, walk ways, corridors etc. Our method exploits this redundancy in paths traversed by using both motion trends and appearance of objects for tracking. Our system does not require any inter-camera calibration, instead the system learns the camera topology and path probabilities of objects using Parzen windows during a training phase. Once the training is complete, correspondences are assigned using the maximum a posteriori (MAP) estimation framework. The learned parameters are updated with changing trajectory patterns. Experiments with real world videos are reported which validate the proposed approach.


Associated publications:
Javed O, Rasheed Z, Shafique K and Shah M.
Tracking Across Multiple Cameras With Disjoint Views, The Ninth IEEE International Conference on Computer Vision, Nice, France, 2003

Omar Javed, Khurram Shafique, Zeeshan Rasheed and Mubarak Shah
Modeling inter-camera spacetime and appearance relationships for tracking across non-overlapping views, Computer Vision and Image Understanding, Volume 109, Issue 2, February 2008, Pages 146-162.

Omar Javed, Khurram Shafique, Zeeshan Rasheed and Mubarak Shah
Appearance Modeling for Tracking in Multiple Non-overlapping Cameras, IEEE CVPR 2005, San Diego, June 20-26.

For Power Point presentation click here