Tracking of Extended Crossing Objects Using the Viterbi Algorithm

Tracking, which means determining the positions of the humans in the surrounding, is one of the goals in the field of mobile robots that operate in populated environments. This paper is concerned with the special problem of tracking expanded objects under such constraints. A solution in form of a Viterbi based algorithm, which can be useful for real–time systems, is presented. Thus a Maximum–a–posteriori (MAP) filtering technique is applied to perform the tracking process. The mathematical background of the algorithm is proposed. The method uses the robots’ sensors in form of laser range finders and a motion and observation model of the objects being tracked. The special problem of the crossing of two expanded objects is considered. The mathematical background for this problem is enlightened and a solution for it in form of a heuristic algorithm is proposed. This algorithm is tested on simulated and real data.