Correlation filter based single object tracking: A review

Abstract

In recent years, correlation filter-based (CF) tracking algorithms have gained momentum in the field of visual tracking. CF tracking algorithms have achieved compelling performance by addressing its limitations such as boundary effect and filter corruption during various tracking and target appearance variations. Many researchers have attempted to provide better efficiency and tracking results by extracting handcrafted and deep features either from vision sensors or specialized sensors in the CF tracking framework. Handcrafted features are integrated with deep features, thermal features, and depth features to prevent tracking failures during dense tracking challenges. To provide a detailed understanding of CF-based trackers, the tracking algorithms are categorized either as kernelized CF trackers or fusion-based CF trackers in this work. This is the first review of its kind, which categorizes various correlation-based tracking algorithms based on the key methodologies and the exploited features in the appearance model. Under each category, salient features, detailed overview, and current advancement are discussed and tabulated to provide future research directions. In addition, the performance of CF-based state-of-the-art is experimentally evaluated on multiple datasets namely, OTB100 and VOT2017 under tough tracking situations.