External Tracker
External trackers aim to accurately estimate the position and orientation (6 DoF) of objects or individuals over time, finding applications in diverse fields like robotics, virtual reality, and video surveillance. Current research emphasizes improving tracking robustness and accuracy in challenging conditions (e.g., low light, occlusion, crowded scenes) using various approaches, including transformer networks, graph neural networks, and Siamese networks, often incorporating appearance and motion features for improved data association. These advancements are driving progress in areas such as autonomous driving, human-computer interaction, and medical imaging, where precise and reliable object tracking is crucial.
Papers
Improving Siamese Based Trackers with Light or No Training through Multiple Templates and Temporal Network
Ali Sekhavati, Won-Sook Lee
The Second-place Solution for ECCV 2022 Multiple People Tracking in Group Dance Challenge
Fan Yang, Shigeyuki Odashima, Shoichi Masui, Shan Jiang
The Second-place Solution for CVPR 2022 SoccerNet Tracking Challenge
Fan Yang, Shigeyuki Odashima, Shoichi Masui, Shan Jiang