Abstract
For autonomous navigation systems used in robots and self-driving vehicles, the usage of sequence images captured from single or multiple cameras for localization has been widely adopted due to both the low cost and high accuracy. The approach using essential matrix estimation for calculating the transformation is so popular that the essential matrix is estimated from five points which is the minimum number of points for pose estimation. However, each five pairs of points provides up to ten solutions for the essential matrix. In this paper, we propose an approach to improve the computation speed of the essential matrix by selecting the number of solutions based on a comparison with the previous essential vector of the two consecutive frames. The proposed method evaluated on the KITTI dataset shows at least 15% reduction in computation speed compared to the conventional method.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
