EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PS-YOLO: A Lighter and Faster Network for UAV Object Detection

Han Zhong, Yan Zhang, Zhiguang Shi, Yu Zhang, Liang Zhao

Remote Sensing · 06.05.2025 · 17 (9) · 1641

DOI: 10.3390/rs17091641 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 06.05.2025. Verfasst von Han Zhong und 4 weiteren Autor:innen. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The operational environment of UAVs poses unique challenges for object detection compared to conventional methods. When UAVs capture remote sensing images from elevated altitudes, objects often appear minuscule and can be easily obscured by complex backgrounds. This increases the likelihood of false positives and missed detections, thereby complicating the detection process. Furthermore, the hardware resources available on UAV platforms are typically highly constrained. To meet deployment requirements, researchers often must compromise some detection accuracy in favor of a more lightweight model. To address these challenges, we propose PS-YOLO, a fast and precise network specifically designed for UAV-based object detection. In the proposed network, we first design a lightweight backbone based on partial convolution. Then, we introduce a more efficient neck network called FasterBIFFPN to replace the original PAFPN, enabling more effective multi-scale feature fusion. Finally, we propose the GSCD head. GSCD employs shared convolutions to enhance the network’s ability to learn common features across objects of different scales and introduces Normalized Gaussian Wasserstein Distance Loss (NWDLoss) to improve detection accuracy. This detection head effectively increases inference speed without significantly increasing parameter counts. The proposed PS-YOLO is validated on the Visdrone2019 dataset, and the results demonstrate that PS-YOLO provides a 2% improvement in precision, 0.5% improvement in recall, 1.3% improvement in mean average precision (mAP), 41.3% reduction in parameter counts, 6.1% reduction in computational cost, and 26.73 FPS improvement in inference speed compared to the benchmark model YOLOv11-s.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhong, H., Zhang, Y., Shi, Z., Zhang, Y., & Zhao, L. (2025). PS-YOLO: A Lighter and Faster Network for UAV Object Detection. Remote Sensing, 17(9), 1641. https://doi.org/10.3390/rs17091641

Vancouver

Zhong H, Zhang Y, Shi Z, Zhang Y, Zhao L. PS-YOLO: A Lighter and Faster Network for UAV Object Detection. Remote Sensing. 2025;17(9):1641. doi:10.3390/rs17091641

BibTeX
@article{Zhong2025,
  author = {Zhong, Han and Zhang, Yan and Shi, Zhiguang and Zhang, Yu and Zhao, Liang},
  title = {PS-YOLO: A Lighter and Faster Network for UAV Object Detection},
  journal = {Remote Sensing},
  year = {2025},
  volume = {17},
  number = {9},
  pages = {1641},
  doi = {10.3390/rs17091641}
}
Kostenlos starten →