EUVIMEDEUVIMED entdecken
Crossref

UBPT: Unidirectional and Bidirectional Prompts for RGBD Tracking

Zhou Ou, Dawei Zhang, Ge Ying, Zhonglong Zheng

IEEE Sensors Journal · 15.11.2024 · 24 (22) · 37503-37513

DOI: 10.1109/jsen.2024.3470852 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 15.11.2024. Verfasst von Zhou Ou und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Zhejiang Provincial Natural Science Foundation of China, Open Project of Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RGBD tracking addresses the limitations of single RGB modality tracking in complex environments by incorporating depth images. In recent years, the widespread use of depth sensors has made RGBD data available, greatly promoting the development of RGBD tracking. However, existing RGBD datasets still suffer from small scale and scarcity, as well as the dominance of modalities in the tracking process often fluctuates with changes in the open environments. Most existing RGBD trackers struggle to adaptively extract information from both modalities, hindering the models’ capacity to leverage the combined strengths of RGB and depth data. To address this issue, we propose a novel prompt-based RGBD tracking framework named unidirectional and bidirectional prompts for RGBD tracking (UBPT). UBPT employs a dual-stream transformer architecture and implements both unidirectional and bidirectional prompt learning to extract RGB and depth modality information, fully achieving cross-modality feature interaction. It can dynamically perform unidirectional intramodality feature enhancement and bidirectional intermodality feature fusion. This approach can dynamically and adaptively enhance dominant features while suppressing nondominant features. Experimental findings reveal that our proposed tracker achieves advanced results compared to recent state-of-the-art methods on various RGBD tracking benchmarks, demonstrating its superior tracking performance.

Förderung

  • National Natural Science Foundation of China
  • Zhejiang Provincial Natural Science Foundation of China
  • Open Project of Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University

Zitieren

APA

Ou, Z., Zhang, D., Ying, G., & Zheng, Z. (2024). UBPT: Unidirectional and Bidirectional Prompts for RGBD Tracking. IEEE Sensors Journal, 24(22), 37503-37513. https://doi.org/10.1109/jsen.2024.3470852

Vancouver

Ou Z, Zhang D, Ying G, Zheng Z. UBPT: Unidirectional and Bidirectional Prompts for RGBD Tracking. IEEE Sensors Journal. 2024;24(22):37503-37513. doi:10.1109/jsen.2024.3470852

BibTeX
@article{Ou2024,
  author = {Ou, Zhou and Zhang, Dawei and Ying, Ge and Zheng, Zhonglong},
  title = {UBPT: Unidirectional and Bidirectional Prompts for RGBD Tracking},
  journal = {IEEE Sensors Journal},
  year = {2024},
  volume = {24},
  number = {22},
  pages = {37503--37513},
  doi = {10.1109/jsen.2024.3470852}
}
Kostenlos starten →