Mars Image Content Classification: Three Years of NASA Deployment and Recent Advances
Kiri L. Wagstaff, Steven Lu, Emily Dunkel, Kevin Grimes, Brandon Zhao, Jesse Cai, S. Cole, Gary Doran, Raymond Francis, Jake Lee, Lukas Mandrake
Abstract
The NASA Planetary Data System hosts millions of images acquired from the planet Mars. To help users quickly find images of interest, we have developed and deployed content-based classification and search capabilities for Mars orbital and surface images. The deployed systems are publicly accessible using the PDS Image Atlas. We describe the process of training, evaluating, calibrating, and deploying updates to two CNN classifiers for images collected by Mars missions. We also report on three years of deployment including usage statistics, lessons learned, and plans for the future.
Topics & Concepts
Mars Exploration ProgramSoftware deploymentComputer scienceExploration of MarsRemote sensingArtificial intelligenceInformation retrievalAstrobiologyGeographyOperating systemPhysicsImage Processing and 3D ReconstructionPlanetary Science and ExplorationGeochemistry and Geologic Mapping