Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.05970 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915839203082240 |
|---|---|
| author | Ye, Jingtao Zhang, Kexin Ma, Xunchi Li, Yuehan Zhu, Guangming Shen, Peiyi Jiang, Linhua Zhang, Xiangdong Zhang, Liang |
| author_facet | Ye, Jingtao Zhang, Kexin Ma, Xunchi Li, Yuehan Zhu, Guangming Shen, Peiyi Jiang, Linhua Zhang, Xiangdong Zhang, Liang |
| contents | The rapid movements and agile maneuvers of unmanned aerial vehicles (UAVs) induce significant observational challenges for multi-object tracking (MOT). However, existing UAV-perspective MOT benchmarks often lack these complexities, featuring predominantly predictable camera dynamics and linear motion patterns. To address this gap, we introduce DynUAV, a new benchmark for dynamic UAV-perspective MOT, characterized by intense ego-motion and the resulting complex apparent trajectories. The benchmark comprises 42 video sequences with over 1.7 million bounding box annotations, covering vehicles, pedestrians, and specialized industrial categories such as excavators, bulldozers and cranes. Compared to existing benchmarks, DynUAV introduces substantial challenges arising from ego-motion, including drastic scale changes and viewpoint changes, as well as motion blur. Comprehensive evaluations of state-of-the-art trackers on DynUAV reveal their limitations, particularly in managing the intertwined challenges of detection and association under such dynamic conditions, thereby establishing DynUAV as a rigorous benchmark. We anticipate that DynUAV will serve as a demanding testbed to spur progress in real-world UAV-perspective MOT, and we will make all resources available at link. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05970 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditions Ye, Jingtao Zhang, Kexin Ma, Xunchi Li, Yuehan Zhu, Guangming Shen, Peiyi Jiang, Linhua Zhang, Xiangdong Zhang, Liang Computer Vision and Pattern Recognition The rapid movements and agile maneuvers of unmanned aerial vehicles (UAVs) induce significant observational challenges for multi-object tracking (MOT). However, existing UAV-perspective MOT benchmarks often lack these complexities, featuring predominantly predictable camera dynamics and linear motion patterns. To address this gap, we introduce DynUAV, a new benchmark for dynamic UAV-perspective MOT, characterized by intense ego-motion and the resulting complex apparent trajectories. The benchmark comprises 42 video sequences with over 1.7 million bounding box annotations, covering vehicles, pedestrians, and specialized industrial categories such as excavators, bulldozers and cranes. Compared to existing benchmarks, DynUAV introduces substantial challenges arising from ego-motion, including drastic scale changes and viewpoint changes, as well as motion blur. Comprehensive evaluations of state-of-the-art trackers on DynUAV reveal their limitations, particularly in managing the intertwined challenges of detection and association under such dynamic conditions, thereby establishing DynUAV as a rigorous benchmark. We anticipate that DynUAV will serve as a demanding testbed to spur progress in real-world UAV-perspective MOT, and we will make all resources available at link. |
| title | Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.05970 |