A Robust Correlation Filtering Tracker with Resampling-Detection and Adaptive Fusion Multi-features

Abstract

Recently, correlation filter is widely used in visual tracking for its robust and accuracy. However, it is still a challenge in tracking with complex situations such as target blurring, occlusion, and scale variation. In this paper, a correlation filter-based tracker with resampling-detection and scale estimation is proposed. We use multiple features with adaptive fusion to describe the target appearance, and resampling-detection module will be performed on the frame which tracking confidence determined by PSR is lower than a threshold. Besides, scale pyramid is introduced to estimate the scale. The extensive experimental evaluates on the OTB benchmark and results show that our approach outperforms the baseline trackers and has excellent performance in accuracy and robust, especially on the challenge of fast motion and motion blur. Additionally, our approach is computationally efficient and suitable for real-time applications.