Multi-Pedestrian Tracking Based on Improved Two Step Data Association

The multi-object tracking (MOT) algorithms based on tracking by detection framework are the state-of-the-art trackers in recent years. Association optimization and association affinity model are two key parts in MOT, which have attracted attention to build effective association model to overcome ambiguous detection responses. In this paper, we have proposed an online multi-pedestrian tracking algorithm that uses a two-step data association with the help of improved sparse based appearance affinity model and rank based motion affinity model. The association framework is constructed by fusing the trajectory dynamic information and confidence based two-step data associations. The missing frames of a tracklet are counted based on the sparse reconstruction error of a target. An incremental SVD and downdate SVD decomposition is devised to estimate the rank of the Hankel matrix in rank based motion model. The estimated result is fed back to compute the tracklets confidence during association optimization. Both those strategies are beneficial to eliminate ambiguous detection responses during association. By this association optimization strategy, the fragmented tracklets in online tracking are reduced in some extent. We evaluate our method on four public available challenging datasets. The experimental results, both qualitative and quantitative, demonstrate that the proposed tracking algorithm has a good tracking performance compared with several state-of-the-art multi-object trackers.