A SR-Context Loop-Closure Detection Algorithm of Lidar Point Clouds

被引：0

作者：

Li J. ^{[1
]}

Shao J. ^{[2
]}

Wang R. ^{[3
]}

Zhao K. ^{[3
]}

Liang Z. ^{[1
]}

机构：

[1] 95848 Army of P.L.A., Xiaogan

[2] School of Transportation and Vehicle Engineering, Shandong University of Technology, Zibo

[3] Institute of Military Transportation, Army Military Transportation University, Tianjin

来源：

Guangxue Xuebao/Acta Optica Sinica | 2021年 / 41卷 / 22期

关键词：

Intelligent vehicle; Lidar; Loop-closure detection; Sensors; Simultaneous localization and mapping;

D O I：

10.3788/AOS202141.2228002

中图分类号：

学科分类号：

摘要：

Traditional light detection and ranging (lidar) loop-closure detection algorithms are greatly interfered with by dynamic obstacles, and key-frame search and feature matching take a long time. In response, this paper proposed a less time-consuming SR-Context lidar loop-closure detection algorithm with stronger robustness based on the multiple-features random sample consensus (MF-RANSAC) algorithm and an improved ScanContext algorithm. Firstly, the region growing algorithm was used to cluster the point clouds that had undergone fan-shaped rasterization. Then, an MF-RANSAC algorithm was proposed to eliminate dynamic targets quickly. This algorithm was based on multi-point selection in a dynamic region and query of corresponding points with multiple attributes rather than target recognition and tracking. Finally, the ScanContext algorithm was improved by simplifying the feature matching calculation and deleting the loop-closure historical matching frames. Loop-closure detection of the point clouds of the current frame after elimination of dynamic targets was thus achieved. Tests were carried out on a KITTI dataset and a real vehicle dataset. The experimental results show that the proposed method delivers quick and accurate loop-closure detection in dynamic urban environments and thereby improves lidar mapping accuracy. The average time it takes is only 40% of that of the ScanContext algorithm. © 2021, Chinese Lasers Press. All right reserved.

引用

共 18 条

[1]

Lu S D, Tu M Y, Luo X Y, Et al., Laser SLAM pose optimization algorithm based on graph optimization theory and GNSS, Laser & Optoelectronics Progress, 57, 8, (2020)

[2]

Jaud M, Rouveure R, Faure P, Et al., Method for orthorectification of terrestrial radar maps, ISPRS Journal of Photogrammetry and Remote Sensing, 97, pp. 185-194, (2014)

[3]

Wang R D, Li H, Zhao K, Et al., Robust localization based on kernel density estimation in dynamic diverse city scenes using lidar, Acta Optica Sinica, 39, 5, (2019)

[4]

Ma J, Bajracharya M, Susca S, Et al., Real-time pose estimation of a dynamic quadruped in GPS-denied environments for 24-hour operation, The International Journal of Robotics Research, 35, 6, pp. 631-653, (2016)

[5]

Zou B, Lin S Y, Yin Z S., Semantic mapping based on YOLOv3 and visual SLAM, Laser & Optoelectronics Progress, 57, 20, (2020)

[6]

Wang R D, Xu Y C, Qi Y, Et al., A robust point cloud registration method in urban dynamic environment, Robot, 40, 3, pp. 257-265, (2018)

[7]

Im J H, Im S H, Jee G I., Vertical corner feature based precise vehicle localization using 3D LIDAR in urban area, Sensors, 16, 8, (2016)

[8]

Tang Z R, Liu M Z, Jiang Y, Et al., Point cloud registration algorithm based on canonical correlation analysis, Chinese Journal of Lasers, 46, 4, (2019)

[9]

Leutenegger S, Lynen S, Bosse M, Et al., Keyframe-based visual-inertial odometry using nonlinear optimization, The International Journal of Robotics Research, 34, 3, pp. 314-334, (2015)

[10]

Qiu C L, Huang D Z, Liu H W, Et al., Loop closure detection algorithm based on convolutional autoencoder fused with Gist feature, Laser & Optoelectronics Progress, 56, 18, (2019)

← 1 2 →