Context-dependent image quality assessment of JPEG compressed Mars Science Laboratory Mastcam images using convolutional neural networks

Hannah R. Kerner, James Bell, Hani Ben Amor

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The Mastcam color imaging system on the Mars Science Laboratory Curiosity rover acquires images that are often JPEG compressed before being downlinked to Earth. Depending on the context of the observation, this compression can result in image artifacts that might introduce problems in the scientific interpretation of the data and might require the image to be retransmitted losslessly. We propose to streamline the tedious process of manually analyzing images using context-dependent image quality assessment, a process wherein the context and intent behind the image observation determine the acceptable image quality threshold. We propose a neural network solution for estimating the probability that a Mastcam user would find the quality of a compressed image acceptable for science analysis. We also propose an automatic labeling method that avoids the need for domain experts to label thousands of training examples. We performed multiple experiments to evaluate the ability of our model to assess context-dependent image quality, the efficiency a user might gain when incorporating our model, and the uncertainty of the model given different types of input images. We compare our approach to the state of the art in no-reference image quality assessment. Our model correlates well with the perceptions of scientists assessing context-dependent image quality and could result in significant time savings when included in the current Mastcam image review process.

Original languageEnglish (US)
Pages (from-to)109-121
Number of pages13
JournalComputers and Geosciences
Volume118
DOIs
StatePublished - Sep 1 2018

Fingerprint

Image quality
Mars
Neural networks
Imaging systems
Labeling
Labels
Earth (planet)
laboratory
science
Color
Experiments
artifact
savings
compression

Keywords

  • Deep learning
  • Image quality
  • Machine learning
  • Planetary science

ASJC Scopus subject areas

  • Information Systems
  • Computers in Earth Sciences

Cite this

@article{5f708a02e5304f2db8ef925d4cdaa31a,
title = "Context-dependent image quality assessment of JPEG compressed Mars Science Laboratory Mastcam images using convolutional neural networks",
abstract = "The Mastcam color imaging system on the Mars Science Laboratory Curiosity rover acquires images that are often JPEG compressed before being downlinked to Earth. Depending on the context of the observation, this compression can result in image artifacts that might introduce problems in the scientific interpretation of the data and might require the image to be retransmitted losslessly. We propose to streamline the tedious process of manually analyzing images using context-dependent image quality assessment, a process wherein the context and intent behind the image observation determine the acceptable image quality threshold. We propose a neural network solution for estimating the probability that a Mastcam user would find the quality of a compressed image acceptable for science analysis. We also propose an automatic labeling method that avoids the need for domain experts to label thousands of training examples. We performed multiple experiments to evaluate the ability of our model to assess context-dependent image quality, the efficiency a user might gain when incorporating our model, and the uncertainty of the model given different types of input images. We compare our approach to the state of the art in no-reference image quality assessment. Our model correlates well with the perceptions of scientists assessing context-dependent image quality and could result in significant time savings when included in the current Mastcam image review process.",
keywords = "Deep learning, Image quality, Machine learning, Planetary science",
author = "Kerner, {Hannah R.} and James Bell and {Ben Amor}, Hani",
year = "2018",
month = "9",
day = "1",
doi = "10.1016/j.cageo.2018.06.001",
language = "English (US)",
volume = "118",
pages = "109--121",
journal = "Computers and Geosciences",
issn = "0098-3004",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Context-dependent image quality assessment of JPEG compressed Mars Science Laboratory Mastcam images using convolutional neural networks

AU - Kerner, Hannah R.

AU - Bell, James

AU - Ben Amor, Hani

PY - 2018/9/1

Y1 - 2018/9/1

N2 - The Mastcam color imaging system on the Mars Science Laboratory Curiosity rover acquires images that are often JPEG compressed before being downlinked to Earth. Depending on the context of the observation, this compression can result in image artifacts that might introduce problems in the scientific interpretation of the data and might require the image to be retransmitted losslessly. We propose to streamline the tedious process of manually analyzing images using context-dependent image quality assessment, a process wherein the context and intent behind the image observation determine the acceptable image quality threshold. We propose a neural network solution for estimating the probability that a Mastcam user would find the quality of a compressed image acceptable for science analysis. We also propose an automatic labeling method that avoids the need for domain experts to label thousands of training examples. We performed multiple experiments to evaluate the ability of our model to assess context-dependent image quality, the efficiency a user might gain when incorporating our model, and the uncertainty of the model given different types of input images. We compare our approach to the state of the art in no-reference image quality assessment. Our model correlates well with the perceptions of scientists assessing context-dependent image quality and could result in significant time savings when included in the current Mastcam image review process.

AB - The Mastcam color imaging system on the Mars Science Laboratory Curiosity rover acquires images that are often JPEG compressed before being downlinked to Earth. Depending on the context of the observation, this compression can result in image artifacts that might introduce problems in the scientific interpretation of the data and might require the image to be retransmitted losslessly. We propose to streamline the tedious process of manually analyzing images using context-dependent image quality assessment, a process wherein the context and intent behind the image observation determine the acceptable image quality threshold. We propose a neural network solution for estimating the probability that a Mastcam user would find the quality of a compressed image acceptable for science analysis. We also propose an automatic labeling method that avoids the need for domain experts to label thousands of training examples. We performed multiple experiments to evaluate the ability of our model to assess context-dependent image quality, the efficiency a user might gain when incorporating our model, and the uncertainty of the model given different types of input images. We compare our approach to the state of the art in no-reference image quality assessment. Our model correlates well with the perceptions of scientists assessing context-dependent image quality and could result in significant time savings when included in the current Mastcam image review process.

KW - Deep learning

KW - Image quality

KW - Machine learning

KW - Planetary science

UR - http://www.scopus.com/inward/record.url?scp=85048642606&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048642606&partnerID=8YFLogxK

U2 - 10.1016/j.cageo.2018.06.001

DO - 10.1016/j.cageo.2018.06.001

M3 - Article

VL - 118

SP - 109

EP - 121

JO - Computers and Geosciences

JF - Computers and Geosciences

SN - 0098-3004

ER -