With the development of computer technology and the increasing data processing capability and speed, the robot vision-based SLAM problem is gradually emerging. In this paper, based on the traditional vision odometry implementation scheme, the ORB feature extraction algorithm is used to extract the feature points of the image and calculate the BRIEF descriptors, and then a combination of PnP and improved ICP is used to solve the bit pose of the camera. In order to improve the accuracy and stability of the algorithm, the PROSAC algorithm is used to reject the mis-match in this paper. Finally, the algorithm is tested using the public dataset of TUM, which proves that the algorithm has faster computational speed and stability.
Study on visual odometry and optimization of SLAM system
12.10.2022
1965616 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
CoVOR-SLAM: Cooperative SLAM Using Visual Odometry and Ranges for Multi-Robot Systems
IEEE | 2025
|British Library Conference Proceedings | 2004
|IEEE | 2004
|TIBKAT | 2018
|