Li Guangchen, Li Kefeng, Zhang Guangyuan, Pan Ke, Ding Yuxuan, Wang Zhenfei, Fu Chen, Zhu Zhenfang
Shandong Jiaotong University, Haitang Road 5001, Jinan, 250357, China.
Shandong Zhengyuan Yeda Environmental Technology Co., Ltd, Jinan, 250101, China.
Sci Rep. 2025 Apr 7;15(1):11852. doi: 10.1038/s41598-025-94039-5.
As remote sensing technology matures, landslide target segmentation has become increasingly important in disaster prevention, control, and urban construction, playing a crucial role in disaster loss assessment and post-disaster rescue. Therefore, this paper proposes an improved UNet-based landslide segmentation algorithm. Firstly, the feature extraction structure of the model was redesigned by integrating dilated convolution and EMA attention mechanism to enhance the model's ability to extract image features. Additionally, this study introduces the Pag module to replace the original skip connection method, thereby enhancing information fusion between feature maps, reducing pixel information loss, and further improving the model's overall performance. Experimental results show that compared to the original model, our model improves mIoU, Precision, Recall, and F1-score by approximately 2.4%, 2.4%, 3.2%, and 2.8%, respectively. This study not only provides an effective method for landslide segmentation tasks but also offers new perspectives for further research in related fields.
随着遥感技术的成熟，滑坡目标分割在防灾、减灾和城市建设中变得越来越重要，在灾害损失评估和灾后救援中发挥着关键作用。因此，本文提出了一种基于改进U-Net的滑坡分割算法。首先，通过集成空洞卷积和EMA注意力机制对模型的特征提取结构进行重新设计，以增强模型提取图像特征的能力。此外，本研究引入Pag模块来取代原来的跳跃连接方法，从而增强特征图之间的信息融合，减少像素信息损失，并进一步提高模型的整体性能。实验结果表明，与原始模型相比，我们的模型的mIoU、Precision、Recall和F1分数分别提高了约2.4%、2.4%、3.2%和2.8%。本研究不仅为滑坡分割任务提供了一种有效的方法，也为相关领域的进一步研究提供了新的视角。
