EUVIMEDEUVIMED entdecken
Crossref

Real-Time Oriented Object Detection Transformer in Remote Sensing Images

Zeyu Ding, Yong Zhou, Jiaqi Zhao, Wen-Liang Du, Xixi Li, Rui Yao, Abdulmotaleb El Saddik

IEEE Transactions on Geoscience and Remote Sensing · 2026 · 64 · 1-14

DOI: 10.1109/tgrs.2026.3671683 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2026. Verfasst von Zeyu Ding und 6 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Double FirstClass Project of China University of Mining and Technology for Independent Innovation and Social Service, Six Talent Peaks Project in Jiangsu Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent real-time detection transformers (DETRs) have gained popularity due to their simplicity and efficiency. However, these detectors do not explicitly model object rotation, especially in remote sensing imagery where objects appear at arbitrary angles, leading to challenges in angle representation, matching cost, and training stability. In this article, we propose a real-time oriented object DETR, the first real-time end-to-end oriented object detector to the best of our knowledge, that addresses the above issues. Specifically, angle distribution refinement (ADR) is proposed to reformulate angle regression as an iterative refinement of probability distributions, thereby capturing the uncertainty of object rotation and providing a more fine-grained angle representation. Then, we incorporate a Chamfer distance cost into bipartite matching, measuring box distance via vertex sets, enabling more accurate geometric alignment and eliminating ambiguous matches. Moreover, we propose oriented contrastive denoising (OCD) to stabilize training and analyze four noise modes. We observe that a ground truth can be assigned to different index queries across different decoder layers, and analyze this issue using the proposed instability metric. We design a series of model variants and experiments to validate the proposed method. Notably, our O2-DFINE-L, O2-RTDETR-R50 and O2-DEIM-R50 achieve 77.73%/78.45%/80.15% AP50 on DOTA1.0 and 132/119/119 FPS on the 2080ti GPU.

Förderung

  • National Natural Science Foundation of China
  • Double FirstClass Project of China University of Mining and Technology for Independent Innovation and Social Service
  • Six Talent Peaks Project in Jiangsu Province

Zitieren

APA

Ding, Z., Zhou, Y., Zhao, J., Du, W., Li, X., Yao, R., & Saddik, A. E. (2026). Real-Time Oriented Object Detection Transformer in Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 64, 1-14. https://doi.org/10.1109/tgrs.2026.3671683

Vancouver

Ding Z, Zhou Y, Zhao J, Du W, Li X, Yao R, et al. Real-Time Oriented Object Detection Transformer in Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing. 2026;64:1-14. doi:10.1109/tgrs.2026.3671683

BibTeX
@article{Ding2026,
  author = {Ding, Zeyu and Zhou, Yong and Zhao, Jiaqi and Du, Wen-Liang and Li, Xixi and Yao, Rui and Saddik, Abdulmotaleb El},
  title = {Real-Time Oriented Object Detection Transformer in Remote Sensing Images},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2026},
  volume = {64},
  pages = {1--14},
  doi = {10.1109/tgrs.2026.3671683}
}
Kostenlos starten →