Abstract | ||
---|---|---|
Place recognition plays a vital role in eliminating accumulated drift from visual odometry in SLAM system. Bag- of-Words (BoW) -based approach is the most popular solution due to its efficiency and robustness. We propose to use Line- Junction-Line (LJL) to build a BoW for place recognition in urban environments. LJL is a simple structure of two lines with their intersection. Different from point features which are detected based on pixel intensity patterns, it represents structure with physical existence, which is more robust to challenging scenarios. Moreover, its descriptor is distinctive and encodes the relationship between the two lines. Experiments on KITTI dataset show the effectiveness of the proposed method compared to loop detection using BoW trained with either point or line features. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CIS-RAM47153.2019.9095776 | 2019 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM) |
Keywords | DocType | ISSN |
LJL,BoW,place recognition,Line-Junction-lines,urban environments,KITTI dataset,Bag-of-Words,loop detection,SLAM system | Conference | 2326-8123 |
ISBN | Citations | PageRank |
978-1-7281-3459-8 | 0 | 0.34 |
References | Authors | |
20 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaoyu Tang | 1 | 0 | 1.01 |
Wenhao Fu | 2 | 0 | 0.34 |
Muyun Jiang | 3 | 0 | 0.34 |
Guohao Peng | 4 | 2 | 2.06 |
Wu Zhenyu | 5 | 1 | 3.39 |
Yufeng Yue | 6 | 1 | 4.40 |
Danwei Wang | 7 | 1529 | 175.13 |