Mars Image Content Classification: Three Years of NASA Deployment and Recent Advances
Kiri Wagstaff (1), Steven Lu (1), Emily Dunkel (1), Kevin Grimes (1),, Brandon Zhao (2), Jesse Cai (3), Shoshanna B. Cole (4), Gary Doran (1),, Raymond Francis (1), Jake Lee (1), and Lukas Mandrake (1) ((1) Jet Propulsion, Laboratory, California Institute of Technology

TL;DR
This paper discusses the development, deployment, and evaluation of CNN-based classifiers for Mars images over three years, enhancing search capabilities in NASA's PDS Image Atlas.
Contribution
It introduces CNN classifiers tailored for Mars images, detailing their training, deployment, and real-world usage over an extended period.
Findings
CNN classifiers improved image search efficiency
Three years of deployment provided valuable usage insights
Lessons learned inform future Mars image classification efforts
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Processing and 3D Reconstruction
