Making Good Features Track Better
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Real-Time 2-D Feature Detection on a Reconfigurable Computer
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Hi-index | 0.00 |
Computer vision based autonomous navigation scheme for pin-point landing of robotic spacecraft on asteroids is considered. Due to the long communication delay and complicated dynamic environment close to asteroids, traditional spacecraft navigation and control using the deep space network (DSN) is not suitable for the precise and safe landing of robotic spacecraft on asteroids. It is necessary to develop new generation autonomous navigation algorithms for future asteroid landing missions. To meet this requirement, this paper presents computer vision based autonomous relative navigation (VARN) algorithm. Firstly, architecture and function of VARN is introduced; secondly, feature detection and tracking algorithm is given out; then, VARN basing on Levenberg-Marquardt (LM) iteration is defined in detail. Finally, the validity of the proposed navigation scheme is confirmed by computer simulation.