Optical Navigation Dataset for Solar System Small Bodies from Four Space Missions

Four distinct space missions provide images for this dataset: NEAR Shoemaker (Eros), Hayabusa (Itokawa), Rosetta (67P/Churyumov-Gerasimenko), and OSIRIS-REx (Bennu). It also incorporates synthetic data generated using a Bennu shape model and OpenGL-based rendering software. The dataset was curated by Olli Knuuttila of Aalto University for training and evaluating local feature extractors for optical navigation near asteroids.

Use Cases

• Training local feature extractors for optical navigation based on real and synthetic asteroid surface imagery.
• Evaluating feature matching algorithms using pre-rotated image subsets with pixel correspondences.
• Testing depth estimation techniques using subsets that include depth information stored as scaled grayscale arrays.
• Benchmarking navigation algorithms against imagery from multiple historical small body missions.

Strengths

• Includes imagery from four distinct space missions: NEAR Shoemaker, Hayabusa, Rosetta, and OSIRIS-REx.
• Contains both real mission data and synthetic data generated with a Bennu shape model.
• Provides specialized subsets with pre-rotated images and pixel correspondences for training, and subsets with depth information for evaluation.

Limitations

• Row count and total dataset size are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

NASA Planetary Data System (PDS), ESA Planetary Science Archive, and synthetic generation.

Collection Method

Compilation of mission images and generation of synthetic data using a shape model and OpenGL rendering.

Geography

Solar System small bodies (asteroids Eros, Itokawa, 67P/Churyumov-Gerasimenko, and Bennu).