Benchmarking the Robustness of UAV Tracking Against Common Corruptions
This addresses the problem of assessing and improving UAV tracker robustness for applications like surveillance and robotics, but it is incremental as it builds on existing datasets and methods.
The authors tackled the lack of a dedicated platform for evaluating the robustness of unmanned aerial vehicle (UAV) trackers under common corruptions by proposing UAV-C, a large-scale benchmark with over 10K sequences and 18 corruptions from 4 categories, and found that current trackers are vulnerable, with composite corruptions causing severe degradation.
The robustness of unmanned aerial vehicle (UAV) tracking is crucial in many tasks like surveillance and robotics. Despite its importance, little attention is paid to the performance of UAV trackers under common corruptions due to lack of a dedicated platform. Addressing this, we propose UAV-C, a large-scale benchmark for assessing robustness of UAV trackers under common corruptions. Specifically, UAV-C is built upon two popular UAV datasets by introducing 18 common corruptions from 4 representative categories including adversarial, sensor, blur, and composite corruptions in different levels. Finally, UAV-C contains more than 10K sequences. To understand the robustness of existing UAV trackers against corruptions, we extensively evaluate 12 representative algorithms on UAV-C. Our study reveals several key findings: 1) Current trackers are vulnerable to corruptions, indicating more attention needed in enhancing the robustness of UAV trackers; 2) When accompanying together, composite corruptions result in more severe degradation to trackers; and 3) While each tracker has its unique performance profile, some trackers may be more sensitive to specific corruptions. By releasing UAV-C, we hope it, along with comprehensive analysis, serves as a valuable resource for advancing the robustness of UAV tracking against corruption. Our UAV-C will be available at https://github.com/Xiaoqiong-Liu/UAV-C.