Target identity-aware network flow for online multiple target tracking

In this paper we show that multiple object tracking (MOT) can be formulated in a framework, where the de-tection and data-association are performed simultaneously. Our method allows us to overcome the confinements of data association based MOT approaches; where the per-formance is dependent on the object detection results pro-vided at input level. At the core of our method lies struc-tured learning which learns a model for each target and infers the best location of all targets simultaneously in a video clip. The inference of our structured learning is done through a new Target Identity-aware Network Flow (TINF), where each node in the network encodes the probability of each target identity belonging to that node. The proposed Lagrangian relaxation optimization finds the high quality solution to the network. During optimization a soft spatial constraint is enforced between the nodes of the graph which helps reducing the ambiguity caused by nearby targets with similar appearance in crowded scenarios. We show that au-tomatically detecting and tracking targets in a single frame-work can help resolve the ambiguities due to frequent oc-clusion and heavy articulation of targets. Our experiments involve challenging yet distinct datasets and show that our method can achieve results better than the state-of-art. 1