EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HWANet: A Haar Wavelet-based Attention Network for remote sensing object detection

Baohua Jin, Fukang Yin, Wenpeng Cai, Hongchan Li, Haodong Zhu, Wei Huang, Qinggang Wu, Hui Chen, Zhongchuan Sun iD

PLOS One · 04.09.2025 · 20 (9) · e0330759

DOI: 10.1371/journal.pone.0330759 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 04.09.2025. Verfasst von Baohua Jin und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou, China. Hauptthemen laut MEDLINE: Wavelet Analysis, Remote Sensing Technology, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing object detection (RSOD) is highly challenging due to large variations in object scales. Existing deep learning-based methods still face limitations in addressing this challenge. Specifically, reliance on stride convolutions during downsampling leads to the loss of object information, and insufficient context-aware modeling capability hampers full utilization of object information at different scales. To address these issues, this paper proposes a Haar wavelet-based Attention Network (HWANet). The model includes a Low-frequency Enhanced Downsampling Module (LEM), a Haar Frequency Domain Self-attention Module (HFDSA), and a Spatial Information Interaction Module (SIIM). Specifically, LEM employs the Haar wavelet transform to downsample feature maps and enhances low-frequency components, mitigating the loss of object information at different scales. The HFDSA module integrates Haar wavelet transform and explicit spatial priors, reducing computational complexity while enhancing the capture of image spatial structures. Meanwhile, the SIIM module facilitates interactions among information at different levels, enabling multi-level feature integration. Together, SIIM and HFDSA strengthen the model’s context-aware modeling capability, allowing full utilization of multi-scale information. Experimental results show that HWANet achieves 93.1% mAP50 on the NWPU VHR-10 dataset and 99.1% mAP50 on the SAR-Airport-1.0 dataset, with only 2.75M parameters, outperforming existing methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Wavelet AnalysisRemote Sensing TechnologyImage Processing, Computer-AssistedDeep LearningAlgorithmsNeural Networks, ComputerHumans

Autor:innen und Institutionen

  • School of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou, China.
  • Engineering Training Centre, Zhengzhou University of Light Industry, Zhengzhou, China.

ORCID-Profile: Zhongchuan Sun

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Jin, B., Yin, F., Cai, W., Li, H., Zhu, H., Huang, W., Wu, Q., Chen, H., & Sun, Z. (2025). HWANet: A Haar Wavelet-based Attention Network for remote sensing object detection. PLOS One, 20(9), e0330759. https://doi.org/10.1371/journal.pone.0330759

Vancouver

Jin B, Yin F, Cai W, Li H, Zhu H, Huang W, et al. HWANet: A Haar Wavelet-based Attention Network for remote sensing object detection. PLOS One. 2025;20(9):e0330759. doi:10.1371/journal.pone.0330759

BibTeX
@article{Jin2025,
  author = {Jin, Baohua and Yin, Fukang and Cai, Wenpeng and Li, Hongchan and Zhu, Haodong and Huang, Wei and Wu, Qinggang and Chen, Hui and Sun, Zhongchuan},
  title = {HWANet: A Haar Wavelet-based Attention Network for remote sensing object detection},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {9},
  pages = {e0330759},
  doi = {10.1371/journal.pone.0330759}
}
Kostenlos starten →