Abstract
This paper presents 2 improvements to traditional RGB-D SLAM algorithm. One is to build a minimum error function using graph optimization model to estimate camera pose, reduce the number of iterations; another is proposed a intelligent loop detection algorithm which according to camera trajectory curvature, to construct accurate loop closing. We also design the lost recovery system and use GPU in feature extraction. Compared with the tradition RGB-D SLAM, our system is 6.1 times faster, and the best precision increased 30%.
Sign-in/Register to access full text options 
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.
