Context-dependent image quality assessment of JPEG compressed Mars Science Laboratory Mastcam images using convolutional neural networks. (September 2018)

• Record Type: Journal Article
• Authors: Kerner, Hannah R.; Bell, James F.; Ben Amor, Heni
• Is Part Of: Computers & geosciences. Volume 118(2018)
• Page Start: 109
• Page End: 121
• Publication Date: 2018-09
• Subjects: Deep learning -- Machine learning -- Planetary science -- Image quality; Environmental policy -- Periodicals; 550.5
• DOI: 10.1016/j.cageo.2018.06.001
• Languages: English
• ISSNs: 0098-3004

Abstract

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. Highlights: Convolutional neural network used to predict image quality given scientific context. Method for automatically labeling images based on joint entropy information loss. Stochastic pass experiments show model uncertainty reflects human uncertainty. Automatic image quality analysis can save significant time for instrument P.I.s.