EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Extracting Alpine Shrub Using Improved Lightweight DeepLabV3+ Network

Wangping Li, Xingling Cao, Zhaoye Zhou, Longlong Shi, Xiaodong Wu, Wenbo Wei, Yanjun Bian, Xiuxia Zhang, Niu Wang, Cong Wang

Remote Sensing · 22.06.2026 · 18 (12) · 2055

DOI: 10.3390/rs18122055 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 22.06.2026. Verfasst von Wangping Li und 9 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, shrubland is an important land cover type in alpine regions, while accurate segmentation of shrubs using remote sensing data remain challenging. To address these issues, this study proposes an alpine shrub segmentation method based on an improved lightweight DeepLabV3+ network, in which MobileNetV2 is used to replace the original backbone to reduce model complexity while maintaining feature representation capability, a channel squeeze-and-excitation (cSE) attention module is introduced to enhance the response to key shrub features and boundary details, and Ghost convolution is incorporated to reduce computational redundancy while preserving segmentation accuracy. Experimental results from both ablation and comparative studies demonstrate that the proposed model achieves a mean intersection over union (MIoU) of 88.47%, mean pixel accuracy (mPA) of 92.93%, F1-score of 91.80%, and overall accuracy of 94.52%, representing improvements of 3.53%, 2.64%, 2.96%, and 1.69%, respectively, over the original DeepLabV3+ model, while also significantly reducing the number of parameters and model size. In addition, independent cross-year validation using unmanned aerial vehicle (UAV) imagery acquired in 2025 suggests that the proposed model has good applicability under similar UAV sensor and acquisition conditions. Overall, this study provides an effective lightweight semantic segmentation approach for alpine shrub segmentation from high-resolution UAV imagery and offers useful technical support for vegetation monitoring in alpine regions such as the Qinghai–Tibet Plateau.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China

Zitieren

APA

Li, W., Cao, X., Zhou, Z., Shi, L., Wu, X., Wei, W., Bian, Y., Zhang, X., Wang, N., & Wang, C. (2026). Extracting Alpine Shrub Using Improved Lightweight DeepLabV3+ Network. Remote Sensing, 18(12), 2055. https://doi.org/10.3390/rs18122055

Vancouver

Li W, Cao X, Zhou Z, Shi L, Wu X, Wei W, et al. Extracting Alpine Shrub Using Improved Lightweight DeepLabV3+ Network. Remote Sensing. 2026;18(12):2055. doi:10.3390/rs18122055

BibTeX
@article{Li2026,
  author = {Li, Wangping and Cao, Xingling and Zhou, Zhaoye and Shi, Longlong and Wu, Xiaodong and Wei, Wenbo and Bian, Yanjun and Zhang, Xiuxia and Wang, Niu and Wang, Cong},
  title = {Extracting Alpine Shrub Using Improved Lightweight DeepLabV3+ Network},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {12},
  pages = {2055},
  doi = {10.3390/rs18122055}
}
Kostenlos starten →