EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Positive-Guided Local Supervision for Robust Road Extraction from Remote Sensing Imagery

Hao He, Shuyang Wang, Lei Huang, Xiaohu Fan, Yongfei Li, Dongfang Yang

Remote Sensing · 15.05.2026 · 18 (10) · 1589

DOI: 10.3390/rs18101589 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 15.05.2026. Verfasst von Hao He und 5 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Science and Technology of Shandong Province, China Postdoctoral Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Road extraction from high-resolution remote sensing imagery is fundamental to numerous practical applications, yet still faces notable challenges caused by label noise, particularly the underlabeling of rural roads within training datasets. End-to-end dense prediction networks deliver high efficiency and strong global context capture capability, yet they are highly vulnerable to such label noise. In contrast, patch-based methods achieve better robustness but sacrifice global reasoning ability and computational efficiency. This paper proposes a novel training strategy named Positive-guided Local Supervision (PLS), which integrates the strengths of the two aforementioned paradigms. PLS preserves the full end-to-end forward pass to leverage global context, while restricting loss computation to local patches centered on reliably annotated road pixels (positive samples) via a standard dense segmentation loss. By isolating the model from misleading gradients generated in underlabeled regions, PLS effectively mitigates the negative impact of underlabeling without compromising computational efficiency and prediction quality. We evaluate the proposed PLS on two datasets: the public DeepGlobe benchmark and a newly constructed challenging dataset, namely China Four Provinces (CH4P). CH4P includes 13,498 high-resolution images of rural China, which suffers from severe underlabeling inherited from public web maps. Extensive quantitative evaluations on DeepGlobe and the newly built CH4P dataset validate that our PLS strategy surpasses conventional end-to-end baselines and competitive state-of-the-art methods under both noisy original labels and manually refined annotations. On the refined DeepGlobe-mini-test and CH4P-mini-test subsets, PLS obtains prominent absolute IoU improvements of 0.127 and 0.104 over baseline models, respectively, showing distinct superiority in handling severe real-world underlabeling. Qualitative visualizations and cross-dataset generalization tests further demonstrate that PLS can effectively retrieve road segments omitted in raw annotations, delivers strong robustness against practical label noise, and introduces no extra computational burden in the inference stage.

Förderung

  • Department of Science and Technology of Shandong Province
  • China Postdoctoral Science Foundation

Zitieren

APA

He, H., Wang, S., Huang, L., Fan, X., Li, Y., & Yang, D. (2026). Positive-Guided Local Supervision for Robust Road Extraction from Remote Sensing Imagery. Remote Sensing, 18(10), 1589. https://doi.org/10.3390/rs18101589

Vancouver

He H, Wang S, Huang L, Fan X, Li Y, Yang D. Positive-Guided Local Supervision for Robust Road Extraction from Remote Sensing Imagery. Remote Sensing. 2026;18(10):1589. doi:10.3390/rs18101589

BibTeX
@article{He2026,
  author = {He, Hao and Wang, Shuyang and Huang, Lei and Fan, Xiaohu and Li, Yongfei and Yang, Dongfang},
  title = {Positive-Guided Local Supervision for Robust Road Extraction from Remote Sensing Imagery},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {10},
  pages = {1589},
  doi = {10.3390/rs18101589}
}
Kostenlos starten →