Explicit contour model for vehicle tracking with automatic hypothesis validation

This paper addresses the problem of vehicle tracking under a single static, uncalibrated camera without any constraints on the scene or on the motion direction of vehicles. We introduce an explicit contour model, which not only provides a good approximation to the contours of all classes of vehicles but also embeds the contour dynamics in its parameterized template. We integrate the model into a Bayesian framework with multiple cues for vehicle tracking, and evaluate the correctness of a target hypothesis, with the information implied by the shape, by monitoring any conflicts within the hypothesis of every single target as well as between the hypotheses of all targets. We evaluated the proposed method using some real sequences, and demonstrated its effectiveness in tracking vehicles, which have their shape changed significantly while moving on curly, uphills roads.