基于改进D-UNet模型的典型洪泛湿地信息提取  

Mapping typical floodplain wetlands using an improved D-UNet model

作　　者：张久丹 王浩宇 李均力[1,3] 包安明 吴浩儒[1,2,3] 李爽爽 沈占锋 ZHANG Jiudan;WANG Haoyu;LI Junli;BAO Anming;WU Haoru;LI Shuangshuang;SHEN Zhanfeng(Xinjiang Institute of Ecology and Geography,Chinese Academy of Sciences,Urumqi 830011,China;University of Chinese Academy of Sciences,Beijing 100049,China;Key Laboratory of GIS&RS Application Xinjiang Uygur Autonomous Region,Urumqi 830011,China;State Key Laboratory of Remote Sensing Science,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100101,China;School of Surveying and Land Information Engineering,Henan Polytechnic University,Jiaozuo 454003,China)

机构地区：[1]中国科学院新疆生态与地理研究所荒漠与绿洲生态国家重点实验室,乌鲁木齐830011 [2]中国科学院大学,北京100049 [3]新疆遥感与地理信息系统应用重点实验室,乌鲁木齐830011 [4]中国科学院空天信息创新研究院遥感科学国家重点实验室,北京100101 [5]河南理工大学测绘与国土信息工程学院,焦作454003

出　　处：《遥感学报》2025年第1期300-313,共14页NATIONAL REMOTE SENSING BULLETIN

基　　金：国家自然科学基金(编号:U2003201);第三次新疆综合科学考察(编号:2021XJKK1403);天山英才科技创新团队(编号:2022TSYCTD0006)。

摘　　要：洪泛湿地的季节性变化剧烈,湿地水体和植被交替变化频繁,传统的信息提取方法存在光谱混淆和误分的问题。本研究以Sentinel-2多时相影像为数据源,利用多尺度膨胀卷积模块改进D-UNet(Deformable U-Net)网络卷积感受野较小的缺点,以提高模型对高分辨率遥感影像复杂湿地结构的多尺度学习能力。并基于小样本数据库训练和提取不同季节洪泛湿地的结构信息,并以新疆维吾尔自治区台特玛湖湿地为例,分析改进D-UNet网络、5种经典语义分割模型(D-UNet、FCN8s、DABNet、Segfomer及D-LinkNet34)和传统的指数阈值法在洪泛湿地时序制图的适用性。结果表明:改进的D-UNet模型在单时相影像湿地结构提取的总体精度高达96.3%,Kappa系数为0.839,且在时序影像上具有良好的时相可迁移性和稳定性,其多时相总体精度也能达到92.3%;与其他模型及指数阈值法相比,改进D-UNet模型在多变的洪泛湿地结构提取中表现出更好的应用潜力,对湿地水体与湿地植被的错分及漏分现象较指数阈值法分别减少了7.2%和48.9%;较改进前D-UNet分别减少了0.6%和5.4%。本研究可为湿地精细化结构提取研究提供技术参考。Wetland is an important ecosystem and plays a vital role in maintaining regional ecological security.Wetland structure changes respond sensitively to natural and human activities,and flood wetlands experience drastic seasonal water and vegetation changes due to intermittent flood inundations.Mapping high-accuracy wetland structures is challenging because of frequent water and vegetation alternations,which cause spectral confusion and misclassification in optical satellite images.Several wetland extraction methods are available today,including object-oriented methods,whose parameters need to be decided subjectively,and machine learning methods,which have relatively low accuracy.With the continuous development of deep learning in image semantic segmentation,a precise and automatic remote sensing image binary classification becomes possible.Recent studies have suggested that deep learning semantic segmentation methods show great potential for mapping wetland changes in high-resolution images.However,the extraction of wetland structures in complex floodplain scenarios places high demands on models in terms of mining deep spatial information.The deformable U-Net(D-UNet)semantic segmentation model is improved to enhance the accuracy of the extraction of floodplain wetland structure.In this study,the Taitema Lake in Xinjiang,China was selected as the study area because it is a typical floodplain wetland in the arid zone.A multiscene and multitemporal wetland sample dataset was collected using Sentinel-2 remote sensing images in the study area.The DUNet for wetland structure extraction used VGG16 to build the encoding/decoding network and focused on improving the convolutional layer in the network.D-UNet was improved by replacing the convolution block before dimensionality reduction with multiscale dilated convolutions to enhance the network’s receptive field,fuse features of different scales,and avoid loss of detailed information in highresolution remote sensing images.After pretraining D-UNet,we determined that a mul

关 键 词：遥感 语义分割 D-UNet 多尺度膨胀卷积 Sentinel-2 遥感影像 洪泛湿地 湿地结构提取 塔里木河流域 

分 类 号：X87[环境科学与工程—环境工程] P941.78[天文地球—自然地理学] TP79[自动化与计算机技术—检测技术与自动化装置] P2[自动化与计算机技术—控制科学与工程]