EUVIMEDEUVIMED entdecken
Crossref

Edge-Guided Refinement Network With Similarity Perception for Salient Object Detection in Optical Remote Sensing Images

Xin Wang, Xian Fang, Mingfeng Jiang, Jinchao Zhu, Zhigao Li

IEEE Transactions on Geoscience and Remote Sensing · 2025 · 63 · 1-14

DOI: 10.1109/tgrs.2025.3636733 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2025. Verfasst von Xin Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Zhejiang Provincial Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Salient object detection in optical remote sensing image (ORSI-SOD) aims to segment salient regions from high-resolution remote sensing images. However, most existing ORSI-SOD methods primarily rely on feature learning of regions to address the issue of blurred edges, while neglecting the potential advantages of similarity calculation in inferring edge clues. To overcome this issue, we propose a novel network with similarity perception termed the edge-guided refinement network (ERNet), which distinguishes the edge region of salient objects from coarse to fine through two-stage similarity calculation. First, we introduce the adaptive uncertainty calibration module (AUCM), which utilizes the proposed similarity-based edge perception mechanism (SEPM) to adaptively calibrate edge uncertain information. Second, to effectively capture global semantic information, we propose the hierarchical semantic reconstruction module (HSRM), which comprehensively correlates different levels of semantic clues from both internal and external perspectives. Finally, to supplement the local detail of salient objects, we design the dynamic detail interaction module (DDIM), which dynamically extracts detailed information of objects at different scales. Extensive experiments on three challenging benchmark datasets have demonstrated the remarkable superiority of our ERNet compared to 30 state-of-the-art models. The source codes are publicly available at https://github.com/xinwang11/ERNet

Förderung

  • National Natural Science Foundation of China
  • Zhejiang Provincial Natural Science Foundation of China

Zitieren

APA

Wang, X., Fang, X., Jiang, M., Zhu, J., & Li, Z. (2025). Edge-Guided Refinement Network With Similarity Perception for Salient Object Detection in Optical Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 63, 1-14. https://doi.org/10.1109/tgrs.2025.3636733

Vancouver

Wang X, Fang X, Jiang M, Zhu J, Li Z. Edge-Guided Refinement Network With Similarity Perception for Salient Object Detection in Optical Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing. 2025;63:1-14. doi:10.1109/tgrs.2025.3636733

BibTeX
@article{Wang2025,
  author = {Wang, Xin and Fang, Xian and Jiang, Mingfeng and Zhu, Jinchao and Li, Zhigao},
  title = {Edge-Guided Refinement Network With Similarity Perception for Salient Object Detection in Optical Remote Sensing Images},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2025},
  volume = {63},
  pages = {1--14},
  doi = {10.1109/tgrs.2025.3636733}
}
Kostenlos starten →