AstroVision: Towards Autonomous Feature Detection and Description for Missions to Small Bodies Using Deep Learning
arXiv:2208.02053 · doi:10.1016/j.actaastro.2023.01.009
Abstract
Missions to small celestial bodies rely heavily on optical feature tracking for characterization of and relative navigation around the target body. While deep learning has led to great advancements in feature detection and description, training and validating data-driven models for space applications is challenging due to the limited availability of large-scale, annotated datasets. This paper introduces AstroVision, a large-scale dataset comprised of 115,970 densely annotated, real images of 16 different small bodies captured during past and ongoing missions. We leverage AstroVision to develop a set of standardized benchmarks and conduct an exhaustive evaluation of both handcrafted and data-driven feature detection and description methods. Next, we employ AstroVision for end-to-end training of a state-of-the-art, deep feature detection and description network and demonstrate improved performance on multiple benchmarks. The full benchmarking pipeline and the dataset will be made publicly available to facilitate the advancement of computer vision algorithms for space applications.
References in corpus (10)
- Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age
- OSIRIS-REx: Sample Return from Asteroid (101955) Bennu
- TILDE: A Temporally Invariant Learned DEtector
- Lunar Crater Identification via Deep Learning
- The Rosetta mission orbiter Science overview the comet phase
- Deep Learning-based Spacecraft Relative Navigation Methods: A Survey
- How Many Hydrated NEOs Are There?
- GPU4S: Embedded GPUs in Space -- Latest Project Updates
- 3D Visual Tracking Framework with Deep Learning for Asteroid Exploration
- AstroSLAM: Autonomous Monocular Navigation in the Vicinity of a Celestial Small Body -- Theory and Experiments