A Hybrid CNN–Transformer Model for Terrace Extraction from Remote Sensing Imagery
TL;DR
Experimental results validate the effectiveness of the proposed architecture for extracting morphologically diverse terraces in complex terrain, with an IoU of 77.61% and an F1-Score of 87.39%.
Abstract
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.