EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

STar-DETR: A Lightweight Real-Time Detection Transformer for Space Targets in Optical Sensor Systems

Yao Xiao iD, Yang Guo, Qinghao Pang, Xu Yang, Zhengxu Zhao, Xianlong Yin iD

Sensors · 13.02.2025 · 25 (4) · 1146

DOI: 10.3390/s25041146 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.02.2025. Verfasst von Yao Xiao und 5 weiteren Autor:innen. Beteiligte Einrichtung: Shandong Key Laboratory of Space Debris Monitoring and Low-Orbit Satellite Networking, Qingdao University of Technology, Qingdao 266520, China. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Open Fund Project of Shandong Key Laboratory of Space Debris Monitoring and Low-orbit Satellite Networking, the Open Fund Project of Key Laboratory of Intelligent Space TTC&O (Space Engineering University), Ministry of Education, Shandong Key Laboratory of Space Debris Monitoring and Low-orbit Satellite Networking.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Optical sensor systems are essential for space target detection. However, previous studies have prioritized detection accuracy over model efficiency, limiting their deployment on resource-constrained sensors. To address this issue, we propose the lightweight space target real-time detection transformer (STar-DETR), which achieves a balance between model efficiency and detection accuracy. First, the improved MobileNetv4 (IMNv4) backbone network is developed to significantly reduce the model’s parameters and computational complexity. Second, group shuffle convolution (GSConv) is incorporated into the efficient hybrid encoder, which reduces convolution parameters while facilitating information exchange between channels. Subsequently, the dynamic depthwise shuffle transformer (DDST) feature fusion module is introduced to emphasize the trajectory formed by space target exposure. Finally, the minimum points distance scylla intersection over union (MPDSIoU) loss function is developed to enhance regression accuracy and expedite model convergence. A space target dataset is constructed, integrating offline and online data augmentation techniques to improve robustness under diverse sensing conditions. The proposed STar-DETR model achieves an AP0.5:0.95 of 89.9%, successfully detecting dim and discontinuous streak space targets. Its parameter count and computational complexity are reduced by 64.8% and 41.8%, respectively, highlighting its lightweight design and providing a valuable reference for space target detection in resource-constrained optical sensors.

Schlagwörter

Stichwörter der Autor:innen

RT-DETRdata augmentationlightweightobject detectionspace targets

Autor:innen und Institutionen

  • Shandong Key Laboratory of Space Debris Monitoring and Low-Orbit Satellite Networking, Qingdao University of Technology, Qingdao 266520, China.
  • National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100101, China.

ORCID-Profile: Yao Xiao, Xianlong Yin

Förderung

  • the Open Fund Project of Shandong Key Laboratory of Space Debris Monitoring and Low-orbit Satellite Networking
  • the Open Fund Project of Key Laboratory of Intelligent Space TTC&O (Space Engineering University), Ministry of Education
  • Shandong Key Laboratory of Space Debris Monitoring and Low-orbit Satellite Networking

Zitieren

APA

Xiao, Y., Guo, Y., Pang, Q., Yang, X., Zhao, Z., & Yin, X. (2025). STar-DETR: A Lightweight Real-Time Detection Transformer for Space Targets in Optical Sensor Systems. Sensors, 25(4), 1146. https://doi.org/10.3390/s25041146

Vancouver

Xiao Y, Guo Y, Pang Q, Yang X, Zhao Z, Yin X. STar-DETR: A Lightweight Real-Time Detection Transformer for Space Targets in Optical Sensor Systems. Sensors. 2025;25(4):1146. doi:10.3390/s25041146

BibTeX
@article{Xiao2025,
  author = {Xiao, Yao and Guo, Yang and Pang, Qinghao and Yang, Xu and Zhao, Zhengxu and Yin, Xianlong},
  title = {STar-DETR: A Lightweight Real-Time Detection Transformer for Space Targets in Optical Sensor Systems},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {4},
  pages = {1146},
  doi = {10.3390/s25041146}
}
Kostenlos starten →