EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Hybrid CNN–Transformer Model for Terrace Extraction from Remote Sensing Imagery

Fengying Jin, Zhihui Wang, Yinan Wang, Jintao Zhao, Chunjing Zhao, Qingfeng Xu, Kai Guo

Remote Sensing · 09.07.2026 · 18 (14) · 2291

DOI: 10.3390/rs18142291 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 09.07.2026. Verfasst von Fengying Jin und 6 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Henan Province, Central Nonprofit Research Institutions Basic Scientific Research Special Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Terraces constitute a critical form of land surface modification, serving both as essential agricultural resources and effective soil and water conservation measures. However, their morphological diversity, pronounced scale variation, and ambiguous geometric boundaries pose substantial challenges for automated extraction from high-resolution remote sensing imagery. Existing CNN- and Transformer-based methods still face difficulties in simultaneously preserving fine spatial details and modeling long-range contextual information. To address these limitations, this study proposes TerraceNet, a hybrid CNN–Transformer architecture with an encoder–dual-decoder design. The framework employs a ConvNeXt encoder to extract multi-scale features, which are subsequently aggregated by a dynamic fusion feature pyramid network (DF-FPN) and fed into two parallel decoders: a boundary decoder dedicated to fine-grained edge localization and a multi-scale Transformer decoder that incorporates boundary priors for global context modeling and final segmentation. Experimental results on a 2 m resolution GF-1 satellite imagery dataset from the Wuding River Basin in the Loess Plateau demonstrate that TerraceNet an IoU of 77.61% and an F1-Score of 87.39%. These results validate the effectiveness of the proposed architecture for extracting morphologically diverse terraces in complex terrain.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Henan Province
  • Central Nonprofit Research Institutions Basic Scientific Research Special Fund

Zitieren

APA

Jin, F., Wang, Z., Wang, Y., Zhao, J., Zhao, C., Xu, Q., & Guo, K. (2026). A Hybrid CNN–Transformer Model for Terrace Extraction from Remote Sensing Imagery. Remote Sensing, 18(14), 2291. https://doi.org/10.3390/rs18142291

Vancouver

Jin F, Wang Z, Wang Y, Zhao J, Zhao C, Xu Q, et al. A Hybrid CNN–Transformer Model for Terrace Extraction from Remote Sensing Imagery. Remote Sensing. 2026;18(14):2291. doi:10.3390/rs18142291

BibTeX
@article{Jin2026,
  author = {Jin, Fengying and Wang, Zhihui and Wang, Yinan and Zhao, Jintao and Zhao, Chunjing and Xu, Qingfeng and Guo, Kai},
  title = {A Hybrid CNN–Transformer Model for Terrace Extraction from Remote Sensing Imagery},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {14},
  pages = {2291},
  doi = {10.3390/rs18142291}
}
Kostenlos starten →