Land cover classification from remote sensing images based on multi-scale fully convolutional network

作     者：Rui Li Shunyi Zheng Chenxi Duan Libo Wang Ce Zhang Rui Li;Shunyi Zheng;Chenxi Duan;Libo Wang;Ce Zhang

作者机构：School of Remote Sensing and Information EngineeringWuhan UniversityWuhanChina Faculty of Geo-Information Science and Earth Observation(ITC)University of TwenteEnschedeThe Netherlands The State Key Laboratory of Information Engineering in SurveyingMapping and Remote SensingWuhan UniversityWuhanChina Lancaster Environment CentreLancaster UniversityLancasterUK UK Centre for Ecology&HydrologyLancasterUK 

出 版 物：《Geo-Spatial Information Science》 (地球空间信息科学学报（英文）)

年 卷 期：2022年第25卷第2期

页      面：278-294页

核心收录：

学科分类：0810[工学-信息与通信工程] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 081002[工学-信号与信息处理] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China[grant number 41671452] 

主　　题：Spatio-temporal remote sensing images Multi-Scale Fully Convolutional Network land cover classification 

摘      要：Although the Convolutional Neural Network(CNN)has shown great potential for land cover classification,the frequently used single-scale convolution kernel limits the scope of informa-tion ***,we propose a Multi-Scale Fully Convolutional Network(MSFCN)with a multi-scale convolutional kernel as well as a Channel Attention Block(CAB)and a Global Pooling Module(GPM)in this paper to exploit discriminative representations from two-dimensional(2D)satellite ***,to explore the ability of the proposed MSFCN for spatio-temporal images,we expand our MSFCN to three-dimension using three-dimensional(3D)CNN,capable of harnessing each land cover category’s time series interac-tion from the reshaped spatio-temporal remote sensing *** verify the effectiveness of the proposed MSFCN,we conduct experiments on two spatial datasets and two spatio-temporal *** proposed MSFCN achieves 60.366%on the WHDLD dataset and 75.127%on the GID dataset in terms of mIoU index while the figures for two spatio-temporal datasets are 87.753%and 77.156%.Extensive comparative experiments and abla-tion studies demonstrate the effectiveness of the proposed MSFCN.