Lossy compression of multichannel remote sensing images with quality control

Vladimir Lukin, Irina Vasilyeva, Sergey Krivenko, Fangfang Li, Sergey Abramov, Oleksii Rubel, Benoit Vozel, Kacem Chehdi, Karen Egiazarian

Research output: Contribution to journalArticleScientificpeer-review

24 Citations (Scopus)
6 Downloads (Pure)

Abstract

Lossy compression is widely used to decrease the size of multichannel remote sensing data. Alongside this positive effect, lossy compression may lead to a negative outcome as making worse image classification. Thus, if possible, lossy compression should be carried out carefully, controlling the quality of compressed images. In this paper, a dependence between classification accuracy of maximum likelihood and neural network classifiers applied to three-channel test and real-life images and quality of compressed images characterized by standard and visual quality metrics is studied. The following is demonstrated. First, a classification accuracy starts to decrease faster when image quality due to compression ratio increasing reaches a distortion visibility threshold. Second, the classes with a wider distribution of features start to “take pixels” from classes with narrower distributions of features. Third, a classification accuracy might depend essentially on the training methodology, i.e., whether features are determined from original data or compressed images. Finally, the drawbacks of pixel-wise classification are shown and some recommendations on how to improve classification accuracy are given.

Original languageEnglish
Article number3840
Pages (from-to)1-35
Number of pages35
JournalRemote Sensing
Volume12
Issue number22
DOIs
Publication statusPublished - 23 Nov 2020
Publication typeA1 Journal article-refereed

Keywords

  • Image classification
  • Image quality
  • Lossy compression
  • Remote sensing
  • Visual quality metrics

Publication forum classification

  • Publication forum level 1

ASJC Scopus subject areas

  • General Earth and Planetary Sciences

Fingerprint

Dive into the research topics of 'Lossy compression of multichannel remote sensing images with quality control'. Together they form a unique fingerprint.

Cite this