Efficient and Accurate Tightly-Coupled Visual-Lidar SLAM

Autor:	Chih-Chung Chou, Cheng-Fu Chou
Rok vydání:	2022
Předmět:	Lidar Odometry business.industry Computer science Mechanical Engineering Automotive Engineering Computer vision Artificial intelligence Visual odometry Focus (optics) business Residual Computer Science Applications
Zdroj:	IEEE Transactions on Intelligent Transportation Systems. 23:14509-14523
ISSN:	1558-0016 1524-9050
DOI:	10.1109/tits.2021.3130089
Popis:	We investigate a novel way to integrate visual SLAM and lidar SLAM. Instead of enhancing visual odometry via lidar depths or using visual odometry as the motion initial guess of lidar odometry, we propose tightly-coupled visual-lidar SLAM (TVL-SLAM), in which the visual and lidar frontend are run independently and which incorporates all of the visual and lidar measurements in the backend optimizations. To achieve large-scale bundle adjustments in TVL-SLAM, we focus on accurate and efficient lidar residual compression. The visual-lidar SLAM system implemented in this work is based on the open-source ORB-SLAM2 and a lidar SLAM method with average performance, whereas the resulting visual-lidar SLAM clearly outperforms existing visual/lidar SLAM approaches, achieving 0.52% error on KITTI training sequences and 0.56% error on testing sequences.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::6c7c81666fc4a1d8e33b425e7bbd3f67 https://doi.org/10.1109/tits.2021.3130089 Zobrazit plný text záznamu