Abstract
Visual object tracking (VOT) is a fundamental task in computer vision that underpins many higher-level tasks. Previous VOT methods have explored various approaches to improve the performance of VOT tasks and achieve predetermined goals. However, due to the limitations of a single view, issues such as visual blind spots and glitches in photographic devices present insurmountable challenges, often causing the visual features of the tracked object to vanish entirely or partially. Providing supplementary images from another view is an effective way to improve tracking performance by eliminating blind spots and enhancing the reliability of image sources. In this work, we propose a novel benchmark called the Aerial and Ground Cooperation Dataset for VOT (AGVOT). AGVOT consists of 643 sequences from aerial and ground views, comprising 119,859 image pairs. These image pairs were collected from 15 scenes and span 26 object categories. Every sequence is strictly time-aligned and annotated with 4-point bounding boxes. For comprehensive evaluation, AGVOT is further categorized into 12 challenging attributes, each labeled at the frame level. Moreover, we introduce an Aerial and Ground Cooperation Tracking Network (AGTrack) to demonstrate dual-view feature integration and cross-view tracking cooperation. Extensive experiments show that AGTrack outperforms 10 state-of-the-art (SOTA) methods in the computer vision community when tested on AGVOT’s dataset and its challenging attributes. These results demonstrate that implementing VOT tasks with cooperative views achieves more accurate and reliable tracking performance. The project source is available at the link.
Funding Information
  • National Natural Science Foundation of China (62162065)
  • Yunnan Province Visual and Cultural Innovation Team (202505AS350009)
  • Joint Special Project Research Foundation of Yunnan Province (202401BF070001-023)
  • Yunnan Fundamental Research Projects (202201AT070167)