ConeQuest: A Benchmark for Cone Segmentation on Mars

We are releasing a novel dataset called ConeQuest, which has been annotated by experts, enabling ML methods to identify cones on Mars. This dataset comprises more than 13k samples from the Isidis Planitia, Acidalia Planitia, and Hypanis regions of the Martian surface. Additionally, we provide metadata for every data sample, such as latitude-longitude, area, and bounding box.

To read more about this dataset and how it is prepared, used, or to cite this dataset in your own work, please see the following citation:

Purohit, Mirali, Jacob Adler, and Hannah Kerner. "ConeQuest: A Benchmark for Cone Segmentation on Mars." In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 6026-6035. 2024.

To explore visualizations, data preparation scripts, and related code, visit our GitHub repository:

https://github.com/kerner-lab/ConeQuest