Real-time tracking of multiple objects with locally adaptive correlation filters

Abstract

A tracking algorithm using locally adaptive correlation filtering is proposed. The algorithm is designed to track multiple objects withinvariancetopose,occlusion,clutter,andilluminationvariations. Thealgorithmemploysapredictionschemeandcomposite correlationfilters. Thefiltersaresynthesizedwiththehelpofaniterativealgorithm,whichoptimizesdiscriminationcapabilityfor each target. The filters are adapted online to targets changes using information of current and past scene frames. Results obtained with the proposed algorithm using real-life scenes, are presented and compared with those obtained with state-of-the-art tracking methods in terms of detection efficiency, tracking accuracy, and speed of processing.