The time complexity.

Landslide segmentation from remote sensing imagery is crucial for rapid disaster assessment and risk mitigation. Owing to the pronounced heterogeneity of landslide scales and the subtle visual contrast between some landslide bodies and their background, this task remains highly challenging. Although Transformers surpass convolutional neural networks in modeling long-range contextual dependencies, channel-level or feature-level fusion strategies provide only intermittent terrain cues, leading models to underutilize digital elevation model (DEM) information and to lack fine-grained adaptability to terrain variability. To address this, We propose a Swin-Transformer–based framework, Dual-Stage DEM-guided Fusion Transformer for landslide segmentation (D2FLS-Net), which embeds terrain features via two modules: (1) The Dual-Stage DEM-Guided Fusion (DSDF) module that injects DEM cues twice, where the early stage emphasizes DEM related discontinuities before feature extraction, and the late stage coordinates high-level RGB and DEM semantics through a cross-attention mechanism. (2) The Terrain-aware Pixel-wise Adaptive Context Enhancement (T-PACE) module that optimizes intermediate features using a DEM-gated, pixel-adaptive hybrid of multi-dilation atrous convolutions, enabling broader context aggregation within homogeneous landslide interiors and more precise discrimination at boundaries. We evaluate D2FLS-Net on the Bijie and Landslide4Sense 2022 datasets. On Bijie, the mean Intersection over Union (mIoU) reaches 88.77%, Recall 95.27%, and Precision 94.60%, exceeding the best competing model SegFormer by 7.96%, 7.90%, and 4.05%, respectively. On Landslide4Sense2022, mIoU 72.86%, Recall 82.55%, and Precision 93.30%, surpassing SegFormer by 7.06%, 6.56%, and 5.02%, respectively. Ablation studies indicate that DSDF primarily reduces missed detections of landslide traces, whereas T-PACE refines pixel level context selection. Injecting DEM at the Swin-1 and Swin-4 stages consistently outperforms other stage combinations. In summary, the model shows good detection performance and is suitable for fusing DEM and remote sensing imagery for landslide recognition.

基于遥感影像的滑坡分割对于快速灾害评估与风险防控至关重要。由于滑坡规模存在显著异质性，且部分滑坡体与背景间视觉对比度较弱，该任务仍极具挑战性。尽管Transformer在建模长距离上下文依赖关系上优于卷积神经网络，但通道级或特征级融合策略仅能提供间断性的地形线索，导致模型未能充分利用数字高程模型（DEM）信息，且对地形变化缺乏细粒度适应性。为此，我们提出了一种基于Swin Transformer的框架——滑坡分割双阶段DEM引导融合Transformer（D2FLS-Net），该框架通过两个模块嵌入地形特征：（1）双阶段DEM引导融合（DSDF）模块：该模块两次注入DEM线索，早期阶段在特征提取前侧重与DEM相关的不连续性信息，晚期阶段则通过跨注意力机制协调高层RGB与DEM语义特征；（2）地形感知像素级自适应上下文增强（T-PACE）模块：该模块采用DEM门控、像素自适应的多扩张率空洞卷积混合结构优化中间特征，能够在均质滑坡区域内实现更广泛的上下文聚合，并在边界处实现更精准的区分。我们在毕节（Bijie）数据集与Landslide4Sense 2022数据集上对D2FLS-Net进行了评估。在毕节数据集上，其平均交并比（mIoU）达到88.77%，召回率为95.27%，精确率为94.60%，分别优于最优竞品模型SegFormer 7.96%、7.90%与4.05%；在Landslide4Sense 2022数据集上，其mIoU为72.86%，召回率为82.55%，精确率为93.30%，分别超越SegFormer 7.06%、6.56%与5.02%。消融实验表明，DSDF模块主要减少滑坡痕迹的漏检情况，而T-PACE模块则优化像素级上下文选择。在Swin-1与Swin-4阶段注入DEM的策略，始终优于其他阶段组合方案。综上，该模型具备优异的检测性能，适用于融合DEM与遥感影像以实现滑坡识别。