Towards Realtime Visual Based Tracking in Cluttered Traffic Scenes

Dieter Koller, Joseph Weber , and Jitendra Malik

In Proc. of the Intelligent Vehicles Symposium 1994, pp. 201-206, October 24-26, 1994, Paris, France

Abstract

Automatic traffic scene analysis has gained great interest in the context of Advanced Transportation Management Systems. Major improvements in performance and quality of results of machine vision based traffic surveillance systems allow connections to symbolic reasoning components that attain a level of accuracy and reliability well above previous proposed systems. We apply a new approach for detecting and tracking vehicles in road traffic scenes with high accuracy and reliability. High accuracy and reliability are obtained by using an explicit occlusion reasoning step. For that purpose we represent moving vehicles by closed contours and employ a contour tracker based on intensity and motion boundaries. Motion and contour estimation is performed by linear Kalman Filters based on an affine motion model. Occlusion detection is performed by intersecting the depth ordered regions associated to the objects. The intersection is then excluded in the motion and shape update. A contour associated to a moving region is initialized using a motion segmentation step which is based on differences between filter outputs of an acquired image and a continuously updated background image. Symbolic reasoning of the traffic scene based on the extracted car tracks is performed using a belief network. Belief networks provide a flexible and theoretically sound framework for traffic scene analysis because of their inherent ability to model uncertainties. We show the validity of our approach and present results of experiments with real world traffic scenes. Preliminary results of an implementation on special purpose hardware using C-40 Digital Signal Processors show that near real-time performance can be achieved without further improvements.

The document is available online in application/postscript (538572 Bytes)


Last modified on Tuesday, November 20, 1996, Dieter Koller (koller@vision.caltech.edu)