FocusTrack: A Self-Adaptive Local Sampling Algorithm for Efficient Anti-UAV Tracking

Anti-unmanned aerial vehicle (UAV) tracking poses significant challenges, including small target sizes, abrupt camera motion, and cluttered infrared backgrounds. Existing tracking paradigms can be broadly categorized into global-based and local-based methods. Global-based trackers, such as SiamDT and SiamSTA, achieve high accuracy by scanning the entire field of view but suffer from excessive computational overhead, limiting real-world deployment. In contrast, local-based methods, including OSTrack and ROMTrack, efficiently restrict the search region but struggle when targets undergo significant displacements due to the abrupt camera motion. Through preliminary experiments, it is evident that a local tracker, when paired with adaptive search region adjustment (SRA), can significantly enhance the tracking accuracy, narrowing the gap between local and global trackers. To address this challenge, we propose FocusTrack, a novel framework that dynamically refines the search region and strengthens feature representations, achieving an optimal balance between computational efficiency and tracking accuracy. Specifically, our SRA strategy estimates the target presence probability and adaptively adjusts the field of view, ensuring the target remains within focus. Furthermore, to counteract feature degradation caused by varying search regions, the attention-to-mask (ATM) module is proposed. This module integrates the hierarchical information, enriching the target representations with fine-grained details. Experimental results demonstrate that FocusTrack achieves state-of-the-art performance, obtaining 67.7% area under curve (AUC) on AntiUAV and 62.8% AUC on AntiUAV410, outperforming the baseline tracker by 8.5% and 9.1% AUC, respectively. In terms of efficiency, FocusTrack surpasses global-based trackers, requiring only 30G MACs and achieving 143 frames/s with FocusTrack (SRA) and 44 frames/s with the full version, both enabling real-time tracking. Code and models are available at: https://github.com/vero1925/FocusTrack