Robust thermal infrared object tracking with continuous correlation filters and adaptive feature fusion

Thermal infrared (TIR) object tracking is one of the most challenging tasks in computer vision. This paper proposes a robust TIR tracker based on the continuous correlation filters and adaptive feature fusion (RCCF-TIR). Firstly, the Efficient Convolution Operators (ECO) framework is selected to build the new tracker. Secondly, an optimized feature set for TIR tracking is adopted in the framework. Finally, a new strategy of feature fusion based on average peak-to-correlation energy (APCE) is employed. Experiments on the VOT-TIR2016 (Visual Object Tracking-TIR2016) and PTB-TIR (A Thermal Infrared Pedestrian Tracking Benchmark) dataset are carried out and the results indicate that the proposed RCCF-TIR tracker combines good accuracy and robustness, performs better than the state-of-the-art trackers and has the ability to handle various challenges.