DeTrack: A Benchmark and Altitude-Aware Dual World Model for Drone-embodied Tracking
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917505660878848 |
|---|---|
| author | Hu, Guyue Liu, Haoming Song, Siyuan Li, Chenglong Chen, Feng Tang, Jin |
| author_facet | Hu, Guyue Liu, Haoming Song, Siyuan Li, Chenglong Chen, Feng Tang, Jin |
| contents | Aerial object tracking has broad applications in public safety, emergency rescue, wildlife monitoring, and related fields. However, existing aerial tracking benchmarks are mainly based on passive 2D video sequences captured from fixed camera locations or predefined flight paths, where drones are treated as passive cameras rather than embodied agents that actively perceive, interact, and control their motion in dynamic 3D scenes. In this paper, we define a new drone-embodied tracking task, termed DeTrack, which requires a drone to track a target in interactive 3D environments using online egocentric observations and active flight control in a closed loop. We build a large-scale benchmark containing 11,368 target trajectories across diverse scenes, rendering conditions, semantic regions, and moving distractors, together with evaluation metrics for target visibility, tracking accuracy, and trajectory success. We further propose AaDWorlds, an altitude-aware dual world model framework for drone-embodied tracking. AaDWorlds consists of an altitude-aware perception module and dual world models that imagine future states under both high- and low-altitude regimes. By combining pseudo altitude-aware observations and imagined future states, AaDWorlds alleviates the intrinsic altitude-mediated contradiction between target visibility and flight safety. Experiments on the DeTrack benchmark demonstrate that AaDWorlds improves closed-loop tracking performance across all evaluation metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17451 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DeTrack: A Benchmark and Altitude-Aware Dual World Model for Drone-embodied Tracking Hu, Guyue Liu, Haoming Song, Siyuan Li, Chenglong Chen, Feng Tang, Jin Computer Vision and Pattern Recognition Aerial object tracking has broad applications in public safety, emergency rescue, wildlife monitoring, and related fields. However, existing aerial tracking benchmarks are mainly based on passive 2D video sequences captured from fixed camera locations or predefined flight paths, where drones are treated as passive cameras rather than embodied agents that actively perceive, interact, and control their motion in dynamic 3D scenes. In this paper, we define a new drone-embodied tracking task, termed DeTrack, which requires a drone to track a target in interactive 3D environments using online egocentric observations and active flight control in a closed loop. We build a large-scale benchmark containing 11,368 target trajectories across diverse scenes, rendering conditions, semantic regions, and moving distractors, together with evaluation metrics for target visibility, tracking accuracy, and trajectory success. We further propose AaDWorlds, an altitude-aware dual world model framework for drone-embodied tracking. AaDWorlds consists of an altitude-aware perception module and dual world models that imagine future states under both high- and low-altitude regimes. By combining pseudo altitude-aware observations and imagined future states, AaDWorlds alleviates the intrinsic altitude-mediated contradiction between target visibility and flight safety. Experiments on the DeTrack benchmark demonstrate that AaDWorlds improves closed-loop tracking performance across all evaluation metrics. |
| title | DeTrack: A Benchmark and Altitude-Aware Dual World Model for Drone-embodied Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.17451 |