On the Optimization of Advanced DCF-Trackers

Trackers based on discriminative correlation filters (DCF) have recently seen widespread success and in this work we dive into their numerical core. DCF-based trackers interleave learning of the target detector and target state inference based on this detector. Whereas the original formulation includes a closed-form solution for the filter learning, recently introduced improvements to the framework no longer have known closed-form solutions. Instead a large-scale linear least squares problem must be solved each time the detector is updated. We analyze the procedure used to optimize the detector and let the popular scheme introduced with ECO serve as a baseline. The ECO implementation is revisited in detail and several mechanisms are provided with alternatives. With comprehensive experiments we show which configurations are superior in terms of tracking capabilities and optimization performance.Funding agencies: Swedish Foundation for Strategic Research (SymbiCloud); Swedish Research Council (EMC 2)Swedish Research Council [201605543]; CENIIT grant [18.14]; Swedish National Infrastructure for Computing; Wallenberg AI, Autonomous Systems and Software Program (WASP