基于DeepLabv3+语义分割模型的GF-2影像城市绿地提取  

Urban green space extraction from GF-2 remote sensing image based on DeepLabv3+ semantic segmentation model

作　　者：刘文雅 岳安志 季珏[4] 师卫华[4] 邓孺孺[1,5,6] 梁业恒 熊龙海[1] LIU Wenya;YUE Anzhi;JI Jue;SHI Weihua;DENG Ruru;LIANG Yeheng;XIONG Longhai(School of Geography and Planning, Sun Yat-sen University, Guangzhou 510275, China;National Engineering Laboratory for Integrated Air-Space-Ground-Ocean Big Data Application Technology, Beijing 100101, China;Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China;Ministry of Housing and Urban-Rural Development of the People’s Republic of China, Beijing 100101, China;Guangdong Engineering Research Center of Water Environment Remote Sensing Monitoring, Guangzhou 510275, China;Guangdong Provincial Key Laboratory of Urbanization and Geo-Simulation, Guangzhou 510275, China)

机构地区：[1]中山大学地理科学与规划学院,广州510275 [2]空天地海一体化大数据应用技术国家工程实验室,北京100101 [3]中国科学院空天信息创新研究院,北京100101 [4]中国住房和城乡建设部城乡规划管理中心,北京100101 [5]广东省城市化与地理环境空间模拟重点实验室,广州510275 [6]广东省水环境遥感监测工程技术研究中心,广州510275

出　　处：《国土资源遥感》2020年第2期120-129,共10页Remote Sensing for Land & Resources

基　　金：国家科技重大专项项目“GF-6卫星宽视场影像林地/非林地类型快速识别”(编号:21-Y20A06-9001-17/18-3);国家重点研发计划项目“城镇生态资源高分遥感与地面协同监测关键技术研究”(编号:2017YFB0503903);国家科技重大专项项目“高分辨率对地观测重大专项”(编号:03-Y20A04-9001-17/18)、广东省省级科技计划项目“珠江三角洲大气污染高分遥感监测及预警”(编号:2017B020216001);中央高校基本科研业务费专项资金“裸土区浅层地下水埋深遥感反演研究”(编号:19lgpy45)共同资助。

摘　　要：高效准确地提取城市绿地对国土规划建设意义重大,将深度学习语义分割算法应用于遥感图像分类是近年研究的新探索。提出一种基于DeepLabv3+深度学习语义分割网络的GF-2遥感影像城市绿地自动化提取架构,通过网络的多孔空间金字塔池化(atrous spatial pyramid pooling,ASPP)等模块,提取高层特征,并依托架构完成数据集创建,模型训练,城市绿地提取以及精度评估。研究表明,本文架构分类的总体精度达到91.02%,F值为0.86,优于最大似然法(maximum likelihood,ML)、支持向量机(support vector machine,SVM)和随机森林法(random forest,RF)3种传统方法及另外4种语义分割网络(PspNet,SegNet,U-Net和DeepLabv2),可以准确提取城市绿地,排除农田像元干扰;此外,对另一地区的提取试验也证实了本架构具有一定的迁移能力。所提出的GF-2遥感影像城市绿地自动化提取架构,可实现更精确、效率更高的城市绿地提取,为城市规划管理提供参考。The efficient and accurate extraction of urban green space(UGS)is of great significance to land planning and construction.The application of deep learning semantic segmentation algorithm to remote sensing image classification is a new exploration in recent years.This paper describes a multilevel architecture which targets UGS extraction from GF-2 imagery based on DeepLabv3plus semantic segmentation network.Through Atrous Spatial Pyramid Pooling(ASPP)and other modules of the network,high-level features are extracted,and data set creation,model training,urban green space extraction and accuracy evaluation are completed relying on the architecture.The accuracy evaluation shows that DeepLabv3plus outperforms the traditional machine learning methods,such as maximum likelihood(ML),support vector machine(SVM),random forest(RF)and other four semantic segmentation networks(PspNet,SegNet,U-Net and DeepLabv2),allowing us to better extract UGS,especially exclude interference of farmland.Through accuracy evaluation,the proposed architecture reaches an acceptable accuracy,with overall accuracy being 91.02%and F Score being 0.86.Furthermore,the authors also explored the portability of the method by applying the model to another city.Overall,the automatic architecture in this paper is capable of excluding farmland pixels'interference and extracting UGS accurately from RGB high spatial RS images,which provides reference for urban planning and managements.

关 键 词：城市绿地 DeepLab 深度学习 语义分割 GF-2 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]