EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Improved EViT Network for Semantic Segmentation of High-Resolution Remote Sensing Imagery

Rui Xu, Yihui Yang, Renzhong Mao, Yining Zhang, Yiteng Lin, Weiping Zhang

Image Analysis and Stereology · 06.07.2026 · 45 (2) · 103-122

DOI: 10.5566/ias.3950 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Image Analysis and Stereology, online erschienen am 06.07.2026. Verfasst von Rui Xu und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the issues of blurred building boundaries, small-object omission, and severe background interference in the semantic segmentation of high-resolution remote sensing imagery, this study proposes an improved method based on the Enhanced Vision Transformer Network (EViT). Specifically, this paper introduces a Grouped Cross-Cascaded Multi-Head Self-Attention (GCC-MSA) module to enhance feature diversity while maintaining linear complexity, and a Local-Global Feature Calibration (LGC) module to fuse CNN local details with Transformer global context. Coordinate Attention (CoAt) replaces conventional channel attention to strengthen channel-spatial feature representation. Additionally, Semantic-Guided Spatial Pyramid Pooling (SGSPP) and a GCC-MSA-guided Edge Perception (GEP) module reinforce multi-scale semantic perception and boundary extraction, while a Spatial Perception Gating Mechanism (SPGM) adaptively fuses dual-branch features. On the WHU Aerial, Massachusetts, and GF-7 Building Datasets, the model achieves Intersection-over-Union (IoU) scores of 92.33%, 77.81%, and 78.29%, respectively. These represent improvements of 0.57, 0.67, and 0.62 percentage points over the original EViT. The model demonstrates superior performance in small-building extraction, complex boundary segmentation, and background noise suppression, thereby providing a robust solution for precise surface object information extraction from high-resolution remote sensing imagery.

Zitieren

APA

Xu, R., Yang, Y., Mao, R., Zhang, Y., Lin, Y., & Zhang, W. (2026). An Improved EViT Network for Semantic Segmentation of High-Resolution Remote Sensing Imagery. Image Analysis and Stereology, 45(2), 103-122. https://doi.org/10.5566/ias.3950

Vancouver

Xu R, Yang Y, Mao R, Zhang Y, Lin Y, Zhang W. An Improved EViT Network for Semantic Segmentation of High-Resolution Remote Sensing Imagery. Image Analysis and Stereology. 2026;45(2):103-122. doi:10.5566/ias.3950

BibTeX
@article{Xu2026,
  author = {Xu, Rui and Yang, Yihui and Mao, Renzhong and Zhang, Yining and Lin, Yiteng and Zhang, Weiping},
  title = {An Improved EViT Network for Semantic Segmentation of High-Resolution Remote Sensing Imagery},
  journal = {Image Analysis and Stereology},
  year = {2026},
  volume = {45},
  number = {2},
  pages = {103--122},
  doi = {10.5566/ias.3950}
}
Kostenlos starten →