Quasi-Random Sampling for Condensation

The problem of tracking pedestrians from a moving car is a challenging one. The Condensation tracking algorithm is appealing for its generality and potential for real-time implementation. However, the conventional Condensation tracker is known to have diculty with high-dimensional state spaces and unknown motion models. This paper presents an improved algorithm that addresses these problems by using a simplified motion model, and employing quasi-Monte Carlo techniques to eciently sample the resulting tracking problem in the high-dimensional state space. For N sample points, these techniques achieve sampling errors of O(N31 ), as opposed to O(N31/2 ) for conventional Monte Carlo techniques. We illustrate the algorithm by tracking objects in both synthetic and real sequences, and show that it achieves reliable tracking and significant speed-ups over conventional Monte Carlo techniques.

• Type: Conference
• Year: 2000
• Where: ECCV
• Authors: Vasanth Philomin, Ramani Duraiswami, Larry S. Davis
• Keywords: Computer Vision, Condensation Tracking Algorithm, Conventional Condensation Tracker, Conventional Monte Carlo, ECCV 2000, Monte Carlo Techniques, Quasi-monte Carlo Techniques