Coupling Multiple Alignments and Re-ranking for Low-Latency Online Multi-target Tracking

Previous works for multi-target tracking employ two strategies: global optimization and online state estimation. In time-critical applications, the former methods have long temporal latency, and the latter can’t recover from erroneous association or drifting. In this paper, we combine these two strategies, and propose a new low-latency online tracking approach. Unlike previous multi-hypotheses methods, which are always suffered from combinational explosion, our approach keeps the candidate associations using multiple alignments only in ambiguous cases. The novel features based on previous multi-frame associations are designed for re-ranking of the multiple linkages. The experimental results illustrate the advantage and robustness of these features based on prediction of previously generated tracks, and their discrimination to find optimal ones. Comparison with five state-of-the-art methods proves that our proposed method is competitive to global optimal ones and is superior to other online tracking algorithms.