Relational Prior for Multi-Object Tracking

Artem Moskalev, Ivan Sosnovik, Arnold Smeulders; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 1081-1085

Tracking multiple objects individually differs from tracking groups of related objects. When an object is a part of the group, its trajectory is conditioned on the trajectories of the other group members. Most of the current state-of-the-art trackers follow the approach of tracking each object independently, with the mechanism to handle the overlapping trajectories where necessary. Such an approach does not take inter-object relations into account, which may cause unreliable tracking for the members of the groups, especially in crowded scenarios, where individual cues become unreliable. To overcome these limitations, we propose a plug-in Relation Encoding Module (REM). REM encodes relations between tracked objects by running a message passing over a spatio-temporal graph of tracked instances, computing the relation embeddings. The relation embeddings then serve as a prior for predicting future positions of the objects. Our experiments on MOT17 and MOT20 benchmarks demonstrate that extending a tracker with relational prior improves tracking quality.