Stochastic car tracking with line- and color-based features

Color- and edge-based trackers can often be "distracted", causing them to track the wrong object. Many researchers have dealt with this problem by using multiple features, as it is unlikely that all will be distracted at the same time. It is also important for the tracker to maintain multiple hypotheses for the state; sequential Monte Carlo filters have been shown to be a convenient and straightforward means of maintaining multiple hypotheses. In this paper, we improve the accuracy and robustness of real-time tracking by combining a color histogram feature with an edge-gradient-based shape feature under a sequential Monte Carlo framework.