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 extraction. Therefore, 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 images. Meanwhile, 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 images. To verify the effectiveness of the proposed MSFCN, we conduct experiments on two spatial datasets and two spatio-temporal datasets. The 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. Code will be available at .

Rui Li;Shunyi Zheng;Chenxi Duan;Libo Wang;Ce Zhang

School of Remote Sensing and Information Engineering,Wuhan University,Wuhan,China;Faculty of Geo-Information Science and Earth Observation(ITC),University of Twente,Enschede,The Netherlands;The State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,Wuhan,China;Lancaster Environment Centre,Lancaster University,Lancaster,UK;UK Centre for Ecology&Hydrology,Lancaster,UK

地球空间信息科学学报（英文版）

[1]Rui Li;Shunyi Zheng;Chenxi Duan;Libo Wang;Ce Zhang-.Land cover classification from remote sensing images based on multi-scale fully convolutional network)[J].地球空间信息科学学报（英文版）,2022(02):278-294

MSFCN,WHDLD

Land,cover,classification,from,remote,sensing,images,multi,scale,fully,convolutional,network,Although,Convolutional,Neural,Network,has,shown,great,potential,land,frequently,used,single,kernel,limits,scope,informa,extraction,Therefore,Multi,Scale,Fully,well,Channel,Attention,Block,CAB,Global,Pooling,Module,GPM,this,paper,exploit,discriminative,representations,dimensional,2D,satellite,Meanwhile,explore,ability,proposed,spatio,temporal,expand,our,three,using,capable,harnessing,each,category,series,interac,reshaped,To,verify,effectiveness,conduct,experiments,spatial,datasets,achieves,GID,terms,mIoU,figures,are,Extensive,comparative,abla,studies,demonstrate,Code,will,be,available

0.524844