Published May 18, 2021
| Version Submitted
Book Section - Chapter
Open
Mars Image Content Classification: Three Years of NASA Deployment and Recent Advances
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.
Additional Information
© 2021 Association for the Advancement of Artificial Intelligence. Published 2021-05-18. We thank Michael McAuley from the PDS Imaging Node for the continuing support of this work and Anil Natha for assistance with the Google Analytics results. We also thank the numerous volunteers who helped label the Mars images. Part of this research was carried out at the Jet Propulsion Laboratory, California Institute of Technology, under a contract with the National Aeronautics and Space Administration. This publication uses data generated via the Zooniverse.org platform, development of which is funded by generous support, including a Global Impact Award from Google, and by a grant from the Alfred P. Sloan Foundation.Attached Files
Submitted - 2102.05011.pdf
Files
2102.05011.pdf
Additional details
Identifiers
- Eprint ID
- 111573
- Resolver ID
- CaltechAUTHORS:20211021-165421805
Related works
- Describes
- https://arxiv.org/abs/2102.05011 (URL)
Funding
- NASA/JPL/Caltech
- Alfred P. Sloan
Dates
- Created
-
2021-10-22Created from EPrint's datestamp field
- Updated
-
2021-10-26Created from EPrint's last_modified field