EUVIMEDEUVIMED entdecken
Crossref

Highly Efficient and Unsupervised Framework for Moving Object Detection in Satellite Videos

Chao Xiao, Wei An, Yifan Zhang, Zhuo Su, Miao Li, Weidong Sheng, Matti Pietikainen, Li Liu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 11532-11539

DOI: 10.1109/tpami.2024.3409824 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Chao Xiao und 7 weiteren Autor:innen. Die Arbeit wurde bisher 55-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, National University of Defense Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Moving object detection in satellite videos (SVMOD) is a challenging task due to the extremely dim and small target characteristics. Current learning-based methods extract spatio-temporal information from multi-frame dense representation with labor-intensive manual labels to tackle SVMOD, which needs high annotation costs and contains tremendous computational redundancy due to the severe imbalance between foreground and background regions. In this paper, we propose a highly efficient unsupervised framework for SVMOD. Specifically, we propose a generic unsupervised framework for SVMOD, in which pseudo labels generated by a traditional method can evolve with the training process to promote detection performance. Furthermore, we propose a highly efficient and effective sparse convolutional anchor-free detection network by sampling the dense multi-frame image form into a sparse spatio-temporal point cloud representation and skipping the redundant computation on background regions. Coping these two designs, we can achieve both high efficiency (label and computation efficiency) and effectiveness. Extensive experiments demonstrate that our method can not only process 98.8 frames per second on 1024 ×1024 images but also achieve state-of-the-art performance.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • National University of Defense Technology

Zitieren

APA

Xiao, C., An, W., Zhang, Y., Su, Z., Li, M., Sheng, W., Pietikainen, M., & Liu, L. (2024). Highly Efficient and Unsupervised Framework for Moving Object Detection in Satellite Videos. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 11532-11539. https://doi.org/10.1109/tpami.2024.3409824

Vancouver

Xiao C, An W, Zhang Y, Su Z, Li M, Sheng W, et al. Highly Efficient and Unsupervised Framework for Moving Object Detection in Satellite Videos. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):11532-11539. doi:10.1109/tpami.2024.3409824

BibTeX
@article{Xiao2024,
  author = {Xiao, Chao and An, Wei and Zhang, Yifan and Su, Zhuo and Li, Miao and Sheng, Weidong and Pietikainen, Matti and Liu, Li},
  title = {Highly Efficient and Unsupervised Framework for Moving Object Detection in Satellite Videos},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {12},
  pages = {11532--11539},
  doi = {10.1109/tpami.2024.3409824}
}
Kostenlos starten →