Fast mismatch elimination algorithm and map-building based on ORB-SLAM2 system

doi:10.11772/j.issn.1001-9081.2020010092

Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (11): 3289-3294.DOI: 10.11772/j.issn.1001-9081.2020010092

• Virtual reality and multimedia computing • Previous Articles Next Articles

Fast mismatch elimination algorithm and map-building based on ORB-SLAM2 system

XI Zhihong, WANG Hongxu, HAN Shuangquan

College of Information and Communication Engineering, Harbin Engineering University, Harbin Heilongjiang 150001, China

Received:2020-02-03 Revised:2020-03-18 Online:2020-11-10 Published:2020-03-24
Supported by:
This work is partially supported by the National Natural Science Foundation of China (60875025).

基于ORB-SLAM2系统的快速误匹配剔除算法与地图构建

席志红, 王洪旭, 韩双全

哈尔滨工程大学信息与通信工程学院, 哈尔滨 150001

通讯作者: 王洪旭(1994-),男,吉林松原人,硕士研究生,主要研究方向:视觉SLAM、图像理解;504715799@qq.com
作者简介:席志红(1965-),女,黑龙江哈尔滨人,教授,博士,主要研究方向:图像处理、室内定位;韩双全(1993-),男,山东潍坊人,硕士研究生,主要研究方向:视觉SLAM、图像理解
基金资助:
国家自然科学基金资助项目（60875025）。

Abstract

Abstract: To address the problem that the RANdom SAmple Consensus (RANSAC) algorithm in the ORB-SLAM2 system has a low efficiency due to the randomness of the algorithm when eliminating mismatches and fails to build dense point cloud map in ORB-SLAM2 system, a PROgressive SAmple Consensus (PROSAC) algorithm was adopted to improve the mismatch elimination in the ORB-SLAM2 system and the dense point cloud map and the octree map building threads were added in this system. Firstly, compared with RANSAC algorithm, in PROSAC algorithm, the feature points were preordered according to the evaluation function, and the feature points with high evaluation quality were selected to solve the homography matrix. According to the solution of the homography matrix and the matching error threshold, the mismatches were eliminated. Secondly, the pose estimation and relocation of the camera were carried out according to the ORB-SLAM2 system. Finally, the dense point cloud map and the octree map were constructed according to the selected key frames. According to the experimental results on TUM dataset, PROSAC algorithm took about 50% time to perform the mismatch elimination of the same images compared to RANSAC algorithm, and the proposed system had the absolute trajectory error and relative pose error basically consistent with the ORB-SLAM2 system, showing good robustness. Besides, compared with the sparse point cloud map, the proposed new maps could be directly used for robot navigation and path planning.

Key words: Simultaneous Localization And Mapping (SLAM), RANdom SAmple Consensus (RANSAC) algorithm, PROgressive SAmple Consensus (PROSAC) algorithm, dense point cloud map, octree map

摘要： 针对ORB-SLAM2系统中随机抽样一致（RANSAC）算法在误匹配剔除时因其算法本身的随机性而导致效率较低的问题和在ORB-SLAM2系统里未能构建稠密点云地图的问题，采用渐进一致采样（PROSAC）算法来改进ORB-SLAM2系统中的误匹配剔除，并在系统中添加稠密点云地图和八叉树地图构建线程。首先，与RANSAC算法相比，PROSAC算法依据评价函数对特征点进行预排序，并选取评价质量较高的特征点求解单应性矩阵，根据单应性矩阵的解与匹配误差阈值进行误匹配剔除；然后，根据ORB-SLAM2系统进行相机的位姿估计与重定位；最后，根据所选关键帧进行稠密点云地图与八叉树地图的构建。根据TUM数据集上的实验结果，PROSAC算法在进行相同图像的误匹配剔除时所用时间是RANSAC算法的50%左右，并且所提系统的绝对轨迹误差与相对位姿误差与ORB-SLAM2系统基本一致，表现出良好的鲁棒性；另外，与稀疏点云地图相比，提出的新构建地图可以直接用于机器人的导航与路径规划。

关键词: 同步定位与地图构建, 随机抽样一致算法, 渐进一致采样算法, 稠密点云地图, 八叉树地图

CLC Number:

TP242.6

XI Zhihong, WANG Hongxu, HAN Shuangquan. Fast mismatch elimination algorithm and map-building based on ORB-SLAM2 system[J]. Journal of Computer Applications, 2020, 40(11): 3289-3294.

席志红, 王洪旭, 韩双全. 基于ORB-SLAM2系统的快速误匹配剔除算法与地图构建[J]. 计算机应用, 2020, 40(11): 3289-3294.

References

[1] ENGEL J,SCHÖPS K,CREMERS D. LSD-SLAM:large-scale direct monocular SLAM[C]//Proceedings of the 2014 European Conference on Computer Vision,LNCS 8690. Cham:Springer, 2014:834-849.
[2] ENGEL J,STÜCKLER J,CREMERS D. Large-scale direct SLAM with stereo cameras[C]//Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway:IEEE,2015:1935-1942.
[3] ENGEL J,KOLTUN V,CREMERS D. Direct sparse odometry[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,40(3):611-625.
[4] KLEIN G,MURRAY D. Parallel tracking and mapping for small AR workspaces[C]//Proceedings of the 6th IEEE and ACM International Symposium on Mixed and Augmented Reality. Piscataway:IEEE,2007:225-234.
[5] MUR-ARTAL R,TARDÓS 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.
[6] FISCHLER M A,BOLLES R C. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM,1981,24(6):381-395.
[7] BENNASAR M,HICKS Y,SETCHI R. Feature selection using joint mutual information maximisation[J]. Expert Systems with Applications,2015,42(22):8520-8532.
[8] 张美玉, 王洋洋, 侯向辉, 等. 基于ORB和改进的RANSAC图像拼接算法[J]. 计算机科学,2019,46(S2):294-298.(ZHANG M Y,WANG Y Y,HOU X H,et al. Image stitching algorithm based on ORB and Improved RANSAC[J]. Computer Science,2019,46(S2):294-298.)
[9] 段勋军, 刘美爽. 基于PROSAC算法的TLS林分树干提取研究[J]. 西北林学院学报,2020,35(1):226-231,256.(DUAN X J, LIU M S. Tree trunk extraction of the stand based on TLS of PROSAC algorithm[J]. Journal of Northwest Forestry University, 2020,35(1):226-231,256.)
[10] CHUM O,MATAS J. Matching with PROSAC-progressive sample consensus[C]//Proceedings of the 2005 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2005:220-226.
[11] 徐子锋, 石超, 王永锋, 等. 基于ORB+PROSAC误匹配剔除算法的视觉SLAM研究[J]. 软件工程,2019,22(5):9-14.(XU Z F,SHI C,WANG Y F,et al. A study of visual SLAM based on ORB+SLAM mismatch elimination algorithm[J]. Software Engineering,2019,22(5):9-14.)
[12] 陆建伟. 基于视觉的ORB-ISM室内同时定位与建图研究[D]. 太原:太原理工大学,2019:37-48.(LU J W. Research on visionbased indoor ORB-ISM simultaneous localization and mapping[D]. Taiyuan:Taiyuan University of Technology,2019:37-48.)
[13] 李雅芳. 基于RGB-D的稠密ORB-SLAM研究[D]. 湘潭:湘潭大学,2018:22-50.(LI Y F. Research of dense ORB-SLAM based on RGB-D[D]. Xiangtan:Xiangtan University,2018:22-50.)
[14] 席志红, 韩双全, 王洪旭. 基于语义分割的室内动态场景同步定位与语义建图[J]. 计算机应用,2019,39(10):2847-2851. (XI Z H,HAN S Q,WANG H X. Simultaneous location and semantic mapping of indoor dynamic scene based on semantic segmentation[J]. Journal of Computer Applications,2019,39(10):2847-2851.)
[15] 周明超. 基于ORB-slam2改进的八叉树地图构建[J]. 电脑知识与技术,2018,14(34):236-237.(ZHOU M C. Improved octree map construction based on ORB-slam2[J]. Computer Knowledge and Technology,2018,14(34):236-237.)

Fast mismatch elimination algorithm and map-building based on ORB-SLAM2 system

基于ORB-SLAM2系统的快速误匹配剔除算法与地图构建

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	ZHENG Sicheng, KONG Linghua, YOU Tongfei, YI Dingrong. Semantic SLAM algorithm based on deep learning in dynamic environment [J]. Journal of Computer Applications, 2021, 41(10): 2945-2951.
[2]	WEI Wenle, JIN Guodong, TAN Lining, LU Libin, CHEN Danqi. Real-time SLAM algorithm with keyframes determined by inertial measurement unit [J]. Journal of Computer Applications, 2020, 40(4): 1157-1163.
[3]	ZHAO Hong, LIU Xiangdong, YANG Yongjuan. Indoor robot simultaneous localization and mapping based on RGB-D image [J]. Journal of Computer Applications, 2020, 40(12): 3637-3643.
[4]	HUANG Shuai, FU Guangyuan, WU Ming, YUE Min. Multi-mode filtering object tracking algorithm based on monocular suboptimal parallax under unknown environment [J]. Journal of Computer Applications, 2019, 39(3): 864-868.
[5]	XI Zhihong, HAN Shuangquan, WANG Hongxu. Simultaneous localization and semantic mapping of indoor dynamic scene based on semantic segmentation [J]. Journal of Computer Applications, 2019, 39(10): 2847-2851.
[6]	HOU Rongbo, WEI Wu, HUANG Ting, DENG Chaofeng. Indoor robot localization and 3D dense mapping based on ORB-SLAM [J]. Journal of Computer Applications, 2017, 37(5): 1439-1444.
[7]	LIN Huican, LYU Qiang, WANG Guosheng, ZHANG Yang, LIANG Bing. 3D simultaneous localization and mapping for mobile robot based on VSLAM [J]. Journal of Computer Applications, 2017, 37(10): 2884-2887.
[8]	YIN Jun, DONG Lida, CHI Tianyang. Mobile robot motion estimation based on classified feature points [J]. Journal of Computer Applications, 2015, 35(2): 590-594.
[9]	ZHAO Wei, TIAN Zheng, YANG Lijuan, YAN Weidong, WEN Jinhuan. Scale invariant feature transform mismatches removal based on canonical correlation analysis [J]. Journal of Computer Applications, 2015, 35(11): 3308-3311.
[10]	LIU Jin. Adaptive approach for point cloud based CAD model reconstruction [J]. Journal of Computer Applications, 2013, 33(09): 2617-2622.
[11]	YAN Wei-dong TIAN Zheng WEN Jin-huan PAN Lu-lu. SIFT mismatching correction based on partial least squares [J]. Journal of Computer Applications, 2012, 32(05): 1255-1257.
[12]	TIAN Ke-chun WEI Li DING Meng. Improved linear fitting algorithm of modulated signal carrier frequency estimation [J]. Journal of Computer Applications, 2012, 32(02): 374-380.
[13]	Bo ZHOU Jian YANG Dong-ping WANG. Matching method of plane image based on random sample consensus algorithm [J]. Journal of Computer Applications, 2011, 31(04): 1053-1056.
[14]	. Edge-based adaptive real-time 3D tracking [J]. Journal of Computer Applications, 2011, 31(01): 20-24.
[15]	. Ball velocity estimation method based on RANSAC and Kalman filter for soccer robots [J]. Journal of Computer Applications, 2010, 30(9): 2305-2309.