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

Rui Li, Shunyi Zheng, Chenxi Duan*, Libo Wang, Ce Zhang

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

57 Citations (Scopus)
344 Downloads (Pure)

Abstract

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 information 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 interaction 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 ablation studies demonstrate the effectiveness of the proposed MSFCN. Code will be available at https://github.com/lironui/MSFCN.

Original languageEnglish
Pages (from-to)278-294
Number of pages17
JournalGeo-spatial information science
Volume25
Issue number2
Early online date7 Jan 2022
DOIs
Publication statusPublished - 3 Apr 2022

Keywords

  • Land cover classification
  • Multi-Scale Fully Convolutional Network
  • Spatio-temporal remote sensing images
  • ITC-GOLD
  • ITC-ISI-JOURNAL-ARTICLE
  • UT-Gold-D

Fingerprint

Dive into the research topics of 'Land cover classification from remote sensing images based on multi-scale fully convolutional network'. Together they form a unique fingerprint.

Cite this