Skip to main navigation Skip to search Skip to main content

Spatial resolution enhancement for large-scale land cover mapping via weakly supervised deep learning

  • Qiutong Yu
  • , Wei Liu
  • , Wesley Nunes Gonçalves
  • , José Marcato Junior
  • , Jonathan Li*
  • *Corresponding author for this work
  • University of Waterloo
  • Universidade Federal de Mato Grosso do Sul

Research output: Contribution to journal › Article › peer-review

Abstract

Multispectral satellite imagery is the primary data source for monitoring land cover change and characterizing land cover globally. However, the consistency of land cover monitoring is limited by the spatial and temporal resolutions of the ac-quired resolution satellite images. The public availability of daily high-images is still scarce. This paper aims to fill this gap by proposing a novel spatiotemporal fusion method to enhance daily low spatial resolution land cover mapping using a weakly supervised deep convolutional neural network. We merge Sentinel images and moderate resolution imaging spectroradiometer (MODIS)-derived thematic land cover maps under the application background of massive remote sensing data and the large spatial resolution gaps between MODIS data and Sentinel images. The neural network training was conducted on the public data set SEN12MS, while the valida-tion and testing used ground truth data from the 2020 IEEE Geoscience and Remote Sensing Society data fusion contest. The proposed data fusion method shows that the synthesized land cover map has significantly higher spatial resolution than the corresponding MODIS-derived land cover map.DeliveredThe bensemble approach can be implementedIP: 125.17.16.94for

Original languageEnglish
Pages (from-to)405-412
Number of pages8
JournalPhotogrammetric Engineering and Remote Sensing
Volume87
Issue number6
DOIs
StatePublished - Jun 2021
Externally publishedYes

Fingerprint

Dive into the research topics of 'Spatial resolution enhancement for large-scale land cover mapping via weakly supervised deep learning'. Together they form a unique fingerprint.

Cite this