Fast Multi-Object Tracking with Feature Pyramid and Region Proposal Networks

Many computer vision applications require real-time processing speeds, which prevents them from running an object detector on every frame. In such circumstances, motion estimation techniques are needed to maintain target identities. Instantiating multiple single-object trackers is feasible only for a few targets, while global frame-feature methods can produce features with limited semantic information and inefficient multiscale tests. SiamFAST addresses these problems with a feature-pyramid-based region-of-interest extractor for object exemplars and search areas, a pairwise depthwise region proposal network to compute similarities for several dozen objects, and a multi-object penalization module to suppress distractors. The method is validated on three public benchmarks and achieves leading performance against state-of-the-art trackers.