基于高分辨率遥感影像和改进U-Net模型的滑坡提取——以汶川地区为例  

Information extraction of landslides based on high-resolution remote sensing images and an improved U-Net model:A case study of Wenchuan,Sichuan

作　　者：白石 唐攀攀 苗朝[2] 金彩凤 赵博 万昊明 BAI Shi;TANG Panpan;MIAO Zhao;JIN Caifeng;ZHAO Bo;WAN Haoming(Research Center of Big Data Technology,Nanhu Laboratory,Jiaxing 314002,China;Institute of Exploration Technology Chinese Academy of Geological Sciences,Chengdu 611734,China;School of Architectural Engineering,Jiaxing Nanhu University,Jiaxing 314001,China)

机构地区：[1]南湖实验室大数据技术研究中心,嘉兴314002 [2]中国地质调查局探矿工艺研究所,成都611734 [3]嘉兴南湖学院建筑工程学院,嘉兴314001

出　　处：《自然资源遥感》2024年第3期96-107,共12页Remote Sensing for Natural Resources

基　　金：南湖实验室自研项目“大数据一体化互操作系统研发”(编号:NSS2021C102004)资助。

摘　　要：滑坡快速识别检测可以满足滑坡灾害的高时效性要求,对灾害损失评估和灾后救援具有重要意义。研究提出一种基于深度学习的滑坡自动提取方法提高滑坡检测的精度。该方法使用目标区遥感影像、数字高程模型数据和面向对象多特征变化向量分析法(robust change vector analysis,RCVA)提取的变化特征作为模型输入,设计结合密集上采样和非对称卷积的U-Net模型提高滑坡识别精度。以四川省汶川地区作为研究区,设计试验测试了不同数据组合和不同方法得到的像素级滑坡分割精度,结果表明该研究提出的改进的U-Net模型可以取得更好的分割结果。Rapid identification and detection of landslides can both meet the requirement of timely responses to disasters and hold great significance for loss assessment and rescue post-disaster.This study proposed a deep learning-based automatic information extraction method for landslides to improve their detection accuracy.Specifically,the model input of this method includes the remote sensing images of the target areas,data from digital elevation models,and variation characteristics extracted using robust change vector analysis(RCVA).Furthermore,a U-Net model integrating dense upsampling and asymmetric convolution is designed to improve the identification accuracy.Taking Wenchuan,Sichuan Province as the study area,this study designed experiments to test the pixel-level image segmentation accuracy of landslides using different data combinations and methods.The results indicate that the improved U-Net model proposed in the study can produce the optimal image segmentation results of landslides.

关 键 词：深度学习 滑坡 语义分割 U-Net 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]