Community evolution model for network flow based multiple object tracking

Multiple object tracking is a research hotspot in the artificial intelligent field, and tracking-by-detection is one of the most popular paradigms in recent years. Among these methods, the network flow based tracker is quite popular due to its computational efficiency and optimality, but it still has one main drawback: Object detection is the processing unit, so high-order information is hard to be taken into consideration directly, and it is usually processed hierarchically, which leads to error propagation. To address this problem, we propose community evolution model for network flow based trackers. We introduce a novel community, which maintains detections and tracklets dynamically. The community allows modeling the connectivities of detections and tracklets jointly, which adaptively incorporates all-level correlations among detections and tracklets, including low-level optical flow, mid-level color histogram, and high-level ranking model. We demonstrate the validity of our method on PETS09 dataset and the MOT17 benchmark, and our method achieves competitive results. Our results on the MOT17 benchmark are available on the website.