[1]付鹏辉,闫晓磊,余捷,等.激光雷达与RGB-D相机融合的SLAM建图[J].福建理工大学学报,2024,22(01):58-64.[doi:10.3969/j.issn.2097-3853.2024.01.009]
　FU Penghui,YAN Xiaolei,YU Jie,et al.SLAM mapping based on fusion of LiDAR and RGB-D camera[J].Journal of Fujian University of Technology;,2024,22(01):58-64.[doi:10.3969/j.issn.2097-3853.2024.01.009]
点击复制

激光雷达与RGB-D相机融合的SLAM建图()
分享到：

《福建理工大学学报》[ISSN:2097-3853/CN:35-1351/Z]

卷:
第22卷
期数:
2024年01期
页码:
58-64
栏目:
出版日期:
2024-02-25

文章信息/Info

Title:
SLAM mapping based on fusion of LiDAR and RGB-D camera
作者:
付鹏辉; 闫晓磊; 余捷; 于廷海; 叶盛
（福建理工大学）福建省汽车电子与电驱动技术重点实验室
Author(s):
FU Penghui;  YAN Xiaolei;  YU Jie;  YU Tinghai;  YE Sheng
Fujian Provincial Key Laboratory of Automotive Electronics and Electric Drive Technology
关键词:
激光雷达; RGB-D相机; ORB-SLAM2算法; 同步定位与建图; 多传感器融合
Keywords:
LiDAR;  RGB-D camera; ORB-SLAM2 algorithm;  SLAM;  multi-sensor fusion
分类号:
TP242.6
DOI:
10.3969/j.issn.2097-3853.2024.01.009
文献标志码:
A
摘要:
对二维激光雷达与RGB?D 相机联合标定,采用改进的ORB?SLAM2 算法实现稠密的点云地图、八叉树地图、栅格地图的构建。提出了一种将Cartographer 算法与改进的ORB?SLAM2 算法融合建图的改进算法。实验结果表明,相比传统的ORB?SLAM2 算法,改进的融合算法在建图过程中障碍物的识别率达到了96.8%,绝对位姿误差减小了53.2%,提高了建图的精确性和鲁棒性。
Abstract:
For the joint calibration of 2D LiDAR and RGB-D camera, the improved ORB-SLAM2 algorithm was used to construct dense point cloud map, octree map and raster map. An improved mapping algorithm combining Cartographer algorithm with improved ORB-SLAM2 algorithm is proposed. The experimental results show that compared with the traditional ORB-SLAM2 algorithm, the new fusion algorithm can achieve 96.8% obstacle recognition rate and reduce the absolute pose error by 53.2%, which improves the accuracy and robustness of map construction.

参考文献/References:

［1］ QUERALTA J P，YUHONG F，SALOMA A L. FPGA-based architecture for a low-cost 3D lidar design and implementation from multiple rotating 2D lidars with ROS［C］∥2019 IEEE SENSORS. Montreal，QC，Canada: IEEE，2019：1-4.［2］ XIA T，SHEN X. Research on parameter adjustment method of cartographer algorithm［C］∥2022 IEEE 6th Advanced Information Technology，Electronic and Automation Control Conference （IAEAC）. Beijing，China: IEEE，2022：1292-1297.［3］ ZHANG S S，ZHENG L Y，TAO W B. Survey and evaluation of RGBD SLAM［J］. IEEE Access，2021，9：21367-21387.［4］ MUR-ARTAL R，TARDOS J D. ORBSLAM2：an open-source SLAM system for monocular，stereo，and RGBD cameras［J］. IEEE Transactions on Robotics，2017，33（5）：1255-1262.［5］ LIU C，ZHANG G J，RONG Y M，et al. Hybrid metric-feature mapping based on camera and Lidar sensor fusion［J］. Measurement，2023，207：112411.［6］ HOU X，SHI H，QU Y H，et al. A fusion method for 2D LiDAR and RGBD camera depth image without calibration［C］∥SUN F，LI J，LIU H，et al. International Conference on Cognitive Computation and Systems. Singapore：Springer，2023：89-101.［7］ PARK K，KIM S，SOHN K. High-precision depth estimation using uncalibrated LiDAR and stereo fusion［J］. IEEE Transactions on Intelligent Transportation Systems，2020，21（1）：321-335.［8］ GRISETTI G，STACHNISS C，BURGARD W. Improved techniques for grid mapping with Rao-blackwellized particle filters［J］. IEEE Transactions on Robotics，2022，23（1）：34-46.［9］ 韩彦峰，唐超超，肖科. 基于改进ORBSLAM2算法的RGBD稠密地图构建［J］. 湖南大学学报（自然科学版），2023，50（2）：52-62.［10］ 罗亮，谈莉斌，余晓流，等. 一种融合二维激光雷达和RGBD相机的移动机器人建图方法研究［J］. 制造业自动化，2023，45（4）：137-140，190.

更新日期/Last Update: 2024-02-25