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

Li, Rui; Zheng, Shunyi; Duan, Chenxi; Wang, Libo; Zhang, Ce ORCID: https://orcid.org/0000-0001-5100-3584. 2022 Land cover classification from remote sensing images based on multi-scale fully convolutional network. Geo-spatial Information Science, 25 (2). 278-294. https://doi.org/10.1080/10095020.2021.2017237

Before downloading, please read NORA policies.

Preview

Text N532770JA.pdf - Published Version Available under License Creative Commons Attribution 4.0. Download (17MB) | Preview

Abstract/Summary

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.

Item Type:	Publication - Article
Digital Object Identifier (DOI):	https://doi.org/10.1080/10095020.2021.2017237
UKCEH and CEH Sections/Science Areas:	Soils and Land Use (Science Area 2017-)
ISSN:	1009-5020
Additional Information. Not used in RCUK Gateway to Research.:	Open Access paper - full text available via Official URL link.
Additional Keywords:	spatio-temporal remote sensing images, multi-scale fully convolutional network, land cover classification
NORA Subject Terms:	Ecology and Environment
Date made live:	17 Jun 2022 15:48 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/532770

Actions (login required)

View Item

Document Downloads

More statistics for this item...