Satellite Articulation Tracking Using Computer Vision
Autonomous on-orbit satellite servicing benefits from an inspector satellite that can gain as much information as possible about the primary satellite. This includes performance of articulated objects such as solar arrays, antennas, and sensors. A method is developed for tracking the articulation of the primary satellite in real time, given an articulated model using silhouettes extracted from inspection imagery. Additionally, a physical satellite model is built and used to collect stop-motion images of simulated articulated motion over an inspection route in a simulated space illumination environment. The images are used as measurements for the silhouette articulation tracking method, and successful tracking is demonstrated qualitatively. Finally, a human pose tracking algorithm is modified for tracking satellite articulation, demonstrating the applicability of human tracking methods to satellite articulation tracking when an articulated model is available. The presented methods have all been demonstrated to be capable of tracking articulated motion.
Journal of Spacecraft and Rockets
Curtis, D. H., & Cobb, R. G. (2019). Satellite Articulation Tracking Using Computer Vision. Journal of Spacecraft and Rockets, 56(5), 1478–1491. https://doi.org/10.2514/1.A34343