AerialMind: Towards Referring Multi-Object Tracking in UAV Scenarios
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908683567366144 |
|---|---|
| author | Chen, Chenglizhao Liang, Shaofeng Guan, Runwei Sun, Xiaolou Zhao, Haocheng Jiang, Haiyun Huang, Tao Ding, Henghui Han, Qing-Long |
| author_facet | Chen, Chenglizhao Liang, Shaofeng Guan, Runwei Sun, Xiaolou Zhao, Haocheng Jiang, Haiyun Huang, Tao Ding, Henghui Han, Qing-Long |
| contents | Referring Multi-Object Tracking (RMOT) aims to achieve precise object detection and tracking through natural language instructions, representing a fundamental capability for intelligent robotic systems. However, current RMOT research remains mostly confined to ground-level scenarios, which constrains their ability to capture broad-scale scene contexts and perform comprehensive tracking and path planning. In contrast, Unmanned Aerial Vehicles (UAVs) leverage their expansive aerial perspectives and superior maneuverability to enable wide-area surveillance. Moreover, UAVs have emerged as critical platforms for Embodied Intelligence, which has given rise to an unprecedented demand for intelligent aerial systems capable of natural language interaction. To this end, we introduce AerialMind, the first large-scale RMOT benchmark in UAV scenarios, which aims to bridge this research gap. To facilitate its construction, we develop an innovative semi-automated collaborative agent-based labeling assistant (COALA) framework that significantly reduces labor costs while maintaining annotation quality. Furthermore, we propose HawkEyeTrack (HETrack), a novel method that collaboratively enhances vision-language representation learning and improves the perception of UAV scenarios. Comprehensive experiments validated the challenging nature of our dataset and the effectiveness of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_21053 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AerialMind: Towards Referring Multi-Object Tracking in UAV Scenarios Chen, Chenglizhao Liang, Shaofeng Guan, Runwei Sun, Xiaolou Zhao, Haocheng Jiang, Haiyun Huang, Tao Ding, Henghui Han, Qing-Long Robotics Computer Vision and Pattern Recognition Referring Multi-Object Tracking (RMOT) aims to achieve precise object detection and tracking through natural language instructions, representing a fundamental capability for intelligent robotic systems. However, current RMOT research remains mostly confined to ground-level scenarios, which constrains their ability to capture broad-scale scene contexts and perform comprehensive tracking and path planning. In contrast, Unmanned Aerial Vehicles (UAVs) leverage their expansive aerial perspectives and superior maneuverability to enable wide-area surveillance. Moreover, UAVs have emerged as critical platforms for Embodied Intelligence, which has given rise to an unprecedented demand for intelligent aerial systems capable of natural language interaction. To this end, we introduce AerialMind, the first large-scale RMOT benchmark in UAV scenarios, which aims to bridge this research gap. To facilitate its construction, we develop an innovative semi-automated collaborative agent-based labeling assistant (COALA) framework that significantly reduces labor costs while maintaining annotation quality. Furthermore, we propose HawkEyeTrack (HETrack), a novel method that collaboratively enhances vision-language representation learning and improves the perception of UAV scenarios. Comprehensive experiments validated the challenging nature of our dataset and the effectiveness of our method. |
| title | AerialMind: Towards Referring Multi-Object Tracking in UAV Scenarios |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.21053 |