Prompt-Driven Temporal Domain Adaptation for Nighttime UAV Tracking
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914958514585600 |
|---|---|
| author | Fu, Changhong Wang, Yiheng Yao, Liangliang Zheng, Guangze Zuo, Haobo Pan, Jia |
| author_facet | Fu, Changhong Wang, Yiheng Yao, Liangliang Zheng, Guangze Zuo, Haobo Pan, Jia |
| contents | Nighttime UAV tracking under low-illuminated scenarios has achieved great progress by domain adaptation (DA). However, previous DA training-based works are deficient in narrowing the discrepancy of temporal contexts for UAV trackers. To address the issue, this work proposes a prompt-driven temporal domain adaptation training framework to fully utilize temporal contexts for challenging nighttime UAV tracking, i.e., TDA. Specifically, the proposed framework aligns the distribution of temporal contexts from daytime and nighttime domains by training the temporal feature generator against the discriminator. The temporal-consistent discriminator progressively extracts shared domain-specific features to generate coherent domain discrimination results in the time series. Additionally, to obtain high-quality training samples, a prompt-driven object miner is employed to precisely locate objects in unannotated nighttime videos. Moreover, a new benchmark for long-term nighttime UAV tracking is constructed. Exhaustive evaluations on both public and self-constructed nighttime benchmarks demonstrate the remarkable performance of the tracker trained in TDA framework, i.e., TDA-Track. Real-world tests at nighttime also show its practicality. The code and demo videos are available at https://github.com/vision4robotics/TDA-Track. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18533 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Prompt-Driven Temporal Domain Adaptation for Nighttime UAV Tracking Fu, Changhong Wang, Yiheng Yao, Liangliang Zheng, Guangze Zuo, Haobo Pan, Jia Computer Vision and Pattern Recognition Nighttime UAV tracking under low-illuminated scenarios has achieved great progress by domain adaptation (DA). However, previous DA training-based works are deficient in narrowing the discrepancy of temporal contexts for UAV trackers. To address the issue, this work proposes a prompt-driven temporal domain adaptation training framework to fully utilize temporal contexts for challenging nighttime UAV tracking, i.e., TDA. Specifically, the proposed framework aligns the distribution of temporal contexts from daytime and nighttime domains by training the temporal feature generator against the discriminator. The temporal-consistent discriminator progressively extracts shared domain-specific features to generate coherent domain discrimination results in the time series. Additionally, to obtain high-quality training samples, a prompt-driven object miner is employed to precisely locate objects in unannotated nighttime videos. Moreover, a new benchmark for long-term nighttime UAV tracking is constructed. Exhaustive evaluations on both public and self-constructed nighttime benchmarks demonstrate the remarkable performance of the tracker trained in TDA framework, i.e., TDA-Track. Real-world tests at nighttime also show its practicality. The code and demo videos are available at https://github.com/vision4robotics/TDA-Track. |
| title | Prompt-Driven Temporal Domain Adaptation for Nighttime UAV Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.18533 |