EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

STAR-Net: Dual-Encoder Network with Global-Local Fusion for Agricultural Land Cover Parsing

Boya Yang, Peigang Xu, Hongtao Han, Chongpei Wu, Jian Tang, Zhejun Feng, Changqing Cao, Lei Qiao

Remote Sensing · 24.04.2026 · 18 (9) · 1314

DOI: 10.3390/rs18091314 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 24.04.2026. Verfasst von Boya Yang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Farmland Protection Monitoring and Supervision Engineering Technology Center Innovation Foundation of Shaanxi Province, Natural Science Basis Research Program in Shaanxi Province of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cultivated land, as a vital resource for human sustenance, requires region-specific protection strategies worldwide. Semantic segmentation technology for agricultural land remote sensing imagery offers a scientific foundation and decision-making support for cultivated land protection through accurate identification and dynamic monitoring. In China, the fragmented distribution, small parcel sizes, complex terrain, and indistinct boundaries of cultivated land pose challenges to the intelligent interpretation of high-resolution remote sensing (HRRS) imagery. Conventional semantic segmentation methods often struggle to address these complexities. To address this issue, we propose a hybrid network called STAR-Net (Swin Transformer Auxiliary Residual Structure) for semantic segmentation of agricultural land in HRRS imagery whose encoder integrates a Global-Local Feature Fusion Module to effectively merge complementary information from both branches. A Multi-Scale Aggregation Module within the decoder facilitates the fusion of shallow spatial details and deep semantic cues, enhancing the model’s ability to discriminate objects at varying scales. Using the LoveDA dataset, we show that STAR-Net generates the highest Intersection over Union (IoU) on the “Barren” and “Forest”, achieving the improvement of 9.88% and 7.05% respectively, while delivering comparable IoU performance on other categories. Overall performance improved by 0.46% in mIoU compared to state-of-the-art models. Across all target categories, the method also achieves the greatest count of leading segmentation metrics.

Förderung

  • Farmland Protection Monitoring and Supervision Engineering Technology Center Innovation Foundation of Shaanxi Province
  • Natural Science Basis Research Program in Shaanxi Province of China

Zitieren

APA

Yang, B., Xu, P., Han, H., Wu, C., Tang, J., Feng, Z., Cao, C., & Qiao, L. (2026). STAR-Net: Dual-Encoder Network with Global-Local Fusion for Agricultural Land Cover Parsing. Remote Sensing, 18(9), 1314. https://doi.org/10.3390/rs18091314

Vancouver

Yang B, Xu P, Han H, Wu C, Tang J, Feng Z, et al. STAR-Net: Dual-Encoder Network with Global-Local Fusion for Agricultural Land Cover Parsing. Remote Sensing. 2026;18(9):1314. doi:10.3390/rs18091314

BibTeX
@article{Yang2026,
  author = {Yang, Boya and Xu, Peigang and Han, Hongtao and Wu, Chongpei and Tang, Jian and Feng, Zhejun and Cao, Changqing and Qiao, Lei},
  title = {STAR-Net: Dual-Encoder Network with Global-Local Fusion for Agricultural Land Cover Parsing},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {9},
  pages = {1314},
  doi = {10.3390/rs18091314}
}
Kostenlos starten →