EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on Remote Sensing Image Object Segmentation Using a Hybrid Multi-Attention Mechanism

Lei Chen, Changliang Li, Yixuan Gao, Yujie Chang, Siming Jin, Zhipeng Wang, Xiaoping Ma, Limin Jia

Applied Sciences · 09.01.2026 · 16 (2) · 695

DOI: 10.3390/app16020695 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 09.01.2026. Verfasst von Lei Chen und 7 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Program of Safety Assurance Technology for Energy Transport Corridor of Shuohuang Railway Based on Advanced Sensing Technologies.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-resolution remote sensing images are gradually playing an important role in land cover mapping, urban planning, and environmental monitoring tasks. However, current segmentation approaches frequently encounter challenges such as loss of detail and blurred boundaries when processing high-resolution remote sensing imagery, owing to their complex backgrounds and dense semantic content. In response to the aforementioned limitations, this study introduces HMA-UNet, a novel segmentation network built upon the UNet framework and enhanced through a hybrid attention strategy. The architecture’s innovation centers on a composite attention block, where a lightweight split fusion attention (LSFA) mechanism and a lightweight channel-spatial attention (LCSA) mechanism are synergistically integrated within a residual learning structure to replace the stacked convolutional structure in UNet, which can improve the utilization of important shallow features and eliminate redundant information interference. Comprehensive experiments on the WHDLD dataset and the DeepGlobe road extraction dataset show that our proposed method achieves effective segmentation in remote sensing images by fully utilizing shallow features and eliminating redundant information interference. The quantitative evaluation results demonstrate the performance of the proposed method across two benchmark datasets. On the WHDLD dataset, the model attains a mean accuracy, IoU, precision, and recall of 72.40%, 60.71%, 75.46%, and 72.41%, respectively. Correspondingly, on the DeepGlobe road extraction dataset, it achieves a mean accuracy of 57.87%, an mIoU of 49.82%, a mean precision of 78.18%, and a mean recall of 57.87%.

Förderung

  • the Program of Safety Assurance Technology for Energy Transport Corridor of Shuohuang Railway Based on Advanced Sensing Technologies

Zitieren

APA

Chen, L., Li, C., Gao, Y., Chang, Y., Jin, S., Wang, Z., Ma, X., & Jia, L. (2026). Research on Remote Sensing Image Object Segmentation Using a Hybrid Multi-Attention Mechanism. Applied Sciences, 16(2), 695. https://doi.org/10.3390/app16020695

Vancouver

Chen L, Li C, Gao Y, Chang Y, Jin S, Wang Z, et al. Research on Remote Sensing Image Object Segmentation Using a Hybrid Multi-Attention Mechanism. Applied Sciences. 2026;16(2):695. doi:10.3390/app16020695

BibTeX
@article{Chen2026,
  author = {Chen, Lei and Li, Changliang and Gao, Yixuan and Chang, Yujie and Jin, Siming and Wang, Zhipeng and Ma, Xiaoping and Jia, Limin},
  title = {Research on Remote Sensing Image Object Segmentation Using a Hybrid Multi-Attention Mechanism},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {2},
  pages = {695},
  doi = {10.3390/app16020695}
}
Kostenlos starten →