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.

Cite

Text

Wagstaff et al. "Mars Image Content Classification: Three Years of NASA Deployment and Recent Advances." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I17.17784

Markdown

[Wagstaff et al. "Mars Image Content Classification: Three Years of NASA Deployment and Recent Advances." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/wagstaff2021aaai-mars/) doi:10.1609/AAAI.V35I17.17784

BibTeX

@inproceedings{wagstaff2021aaai-mars,
  title     = {{Mars Image Content Classification: Three Years of NASA Deployment and Recent Advances}},
  author    = {Wagstaff, Kiri and Lu, Steven and Dunkel, Emily and Grimes, Kevin and Zhao, Brandon and Cai, Jesse and Cole, Shoshanna B. and Doran, Gary and Francis, Raymond and Lee, Jake H. and Mandrake, Lukas},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15204-15213},
  doi       = {10.1609/AAAI.V35I17.17784},
  url       = {https://mlanthology.org/aaai/2021/wagstaff2021aaai-mars/}
}