Layer-Guided UAV Tracking: Enhancing Efficiency and Occlusion Robustness

TL;DR

LGTrack is a UAV tracking framework that improves occlusion robustness and efficiency by integrating dynamic layer selection, a lightweight attention module, and similarity-guided layer adaptation, achieving real-time performance.

Contribution

Introduces LGTrack, a novel UAV tracking method combining lightweight modules for enhanced occlusion handling and efficiency, with state-of-the-art real-time speed.

Findings

LGTrack achieves 258.7 FPS on UAVDT dataset.

Maintains 82.8% precision in tracking accuracy.

Outperforms existing methods in real-time UAV tracking.

Abstract

Visual object tracking (VOT) plays a pivotal role in unmanned aerial vehicle (UAV) applications. Addressing the trade-off between accuracy and efficiency, especially under challenging conditions like unpredictable occlusion, remains a significant challenge. This paper introduces LGTrack, a unified UAV tracking framework that integrates dynamic layer selection, efficient feature enhancement, and robust representation learning for occlusions. By employing a novel lightweight Global-Grouped Coordinate Attention (GGCA) module, LGTrack captures long-range dependencies and global contexts, enhancing feature discriminability with minimal computational overhead. Additionally, a lightweight Similarity-Guided Layer Adaptation (SGLA) module replaces knowledge distillation, achieving an optimal balance between tracking precision and inference efficiency. Experiments on three datasets demonstrate LGTrack's state-of-the-art real-time speed (258.7 FPS on UAVDT) while maintaining competitive tracking accuracy (82.8\% precision). Code is available at https://github.com/XiaoMoc/LGTrack