基于ORB-SLAM的室内机器人定位和三维稠密地图构建

doi:10.11772/j.issn.1001-9081.2017.05.1439

计算机应用 ›› 2017, Vol. 37 ›› Issue (5): 1439-1444.DOI: 10.11772/j.issn.1001-9081.2017.05.1439

• 计算机视觉与虚拟现实 • 上一篇下一篇

基于ORB-SLAM的室内机器人定位和三维稠密地图构建

侯荣波, 魏武, 黄婷, 邓超锋

华南理工大学自动化科学与工程学院, 广州 510640

收稿日期:2016-10-14 修回日期:2016-12-21 出版日期:2017-05-10 发布日期:2017-05-16
通讯作者: 魏武
作者简介:侯荣波(1993-),男,广东肇庆人,硕士研究生,主要研究方向:SLAM算法、三维重构、计算机视觉;魏武(1970-),男,湖南益阳人,副教授,博士,主要研究方向:机器人控制、智能控制、模式识别、人工智能;黄婷(1991-),女,湖北孝感人,硕士研究生,主要研究方向:计算机视觉、机器人嵌入式系统;邓超锋(1990-),男,江西鄱阳人,硕士研究生,主要研究方向:机器人控制、智能控制。
基金资助:
国家自然科学基金资助项目（61573148）；广东省科技重大专项（2015B010919007）。

Indoor robot localization and 3D dense mapping based on ORB-SLAM

HOU Rongbo, WEI Wu, HUANG Ting, DENG Chaofeng

School of Automation Science and Engineering, South China University of Technology, Guangzhou Guangdong 510640, China

Received:2016-10-14 Revised:2016-12-21 Online:2017-05-10 Published:2017-05-16
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61573148), the Guangdong Provincial Science and Technology Major Project (2015B010919007).

摘要/Abstract

摘要： 针对在室内机器人定位和三维稠密地图构建系统中，现有方法无法同时满足高精度定位、大范围和快速性要求的问题，应用具有跟踪、地图构建和重定位三平行线程的ORB-SLAM算法估计机器人三维位姿；然后拼接深度摄像头KINECT获得的三维稠密点云，提出空间域上的关键帧提取方法剔除冗余的视频帧；接着提出子地图法进一步减少地图构建的时间，最终提高算法的整体速度。实验结果表明，所提系统能够在大范围环境中准确定位机器人位置，在运动轨迹为50 m的大范围中，机器人的均方根误差为1.04 m，即误差为2%，同时整体速度为11帧/秒，其中定位速度达到17帧/秒，可以满足室内机器人定位和三维稠密地图构建的精度、大范围和快速性的要求。

关键词: 同时定位和地图构建, 室内机器人, ORB-SLAM, 关键帧提取, KINECT, 图优化

Abstract: In the indoor robot localization and 3D dense mapping, the existing methods can not satisfy the requirements of high-precision localization, large-scale and rapid mapping. The ORB-SLAM (Oriented FAST and Rotated BRIEF-Simultaneous Localization And Mapping) algorithm, which has three parallel threads including tracking, map building and relocation, was used to estimate the three-dimensional (3D) pose of the robot. And then 3D dense point cloud was obtained by using the depth camera KINECT. The key frame extraction method in spatial domain was introduced to eliminate redundant frames, and the sub-map method was proposed to reduce the cost of mapping, thereby the whole speed of the algorithm was improved. The experiment results show that the proposed method can locate the robot position accurately in a large range. In the range of 50 meters, the root-mean-square error of the robot is 1.04 m, namely the error is 2%, the overall speed is 11 frame/s, and the localization speed is up to 17 frame/s. The proposed method can meet the requirements of indoor robot localization and 3D dense mapping with high precision, large-scale and rapidity.

Key words: Simultaneous Localization And Mapping (SLAM), indoor robot, Oriented FAST and Rotated BRIEF-Simultaneous Localization And Mapping (ORB-SLAM), key frame extraction, KINECT, graph optimization

中图分类号:

TP242.6

侯荣波, 魏武, 黄婷, 邓超锋. 基于ORB-SLAM的室内机器人定位和三维稠密地图构建[J]. 计算机应用, 2017, 37(5): 1439-1444.

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.

参考文献

[1] DARDARI D, CLOSAS P, DJURIC P M. Indoor tracking theory, methods, and technologies[J]. IEEE Transactions on Vehicular Technology, 2015, 64(4):1263-1278.
[2] CHOI H, YANG K W, KIM E. Simultaneous global localization and mapping[J]. IEEE/ASME Transactions on Mechatronics, 2014, 19(4):1160-1170.
[3] CHEN Z, SAMARABANDU J, RODRIGO R. Recent advances in simultaneous localization and map-building using computer vision[J]. Advanced Robotics, 2007, 21(3/4):233-265.
[4] SMITH R, SELF M, CHEESEMAN P. Estimating uncertain spatial relationships in robotics[C]//Autonomous Robot Vehicles. New York:Springer, 1990:167-193.
[5] JULIER S J, UHLMANN J K. Unscented filtering and nonlinear estimation[J]. Proceedings of the IEEE, 2004, 92(3):401-422.
[6] 张毅,汪龙峰,余佳航. 基于深度信息的移动机器人室内环境三维地图创建[J]. 计算机应用,2014,34(12):3438-3445.(ZHANG Y,WANG L F, YU J H. Depth-image based 3D map reconstruction of indoor environment for mobile robots[J]. Journal of Computer Applications, 2014, 34(12):3438-3445.)
[7] SCHMIDT A. The EKF-based visual SLAM system with relative map orientation measurements[C]//Proceedings of the 2014 International Conference on Computer Vision and Graphics. Berlin:Springer, 2014:570-577.
[8] SIM R, ELINAS P, LITTLE J. A study of the Rao-Blackwellised particle filter for efficient and accurate vision-based SLAM[J]. International Journal of Computer Vision, 2007, 74(3):303-318.
[9] BLANCO J L, GONZALEZ J, FERNANDEZ-MADRIGAL J A. An optimal filtering algorithm for non-parametric observation models in robot localization[C]//Proceedings of the 2008 IEEE International Conference on Robotics and Automation. Piscataway, NJ:IEEE, 2008:461-466.
[10] SIBLEY G. Relative bundle adjustment[J]. Electronic Notes in Theoretical Computer Science, 2009, 220(3):976-982.
[11] 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. Washington, DC:IEEE Computer Society, 2007:225-234.
[12] MUR-ARTAL R, MONTIEL J M M, TARDÓS J D. ORB-SLAM:a versatile and accurate monocular SLAM system[J]. IEEE Transactions on Robotics, 2015, 31(5):1147-1163.
[13] STURM J, ENGELHARD N, ENDRES F, et al. A benchmark for the evaluation of RGB-D SLAM systems[C]//Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, NJ:IEEE, 2012:573-580.
[14] GALVEZ-LÓPEZ D, TARDOS J D. Bags of binary words for fast place recognition in image sequences[J]. IEEE Transactions on Robotics, 2012, 28(5):1188-1197.
[15] STRASDAT H, DAVISON A J, MONTIEL J M M, et al. Double window optimization for constant time visual SLAM[C]//Proceedings of the 2011 International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2011:2352-2359.
[16] KUEMMERLE R, GRISETTI G, STRASDAT H, et al. G2o:a general framework for graph optimization[C]//Proceedings of the 2011 IEEE International Conference on Robotics and Automation. Piscataway, NJ:IEEE, 2011:3607-3613.
[17] LUCAS B, KANADE T. An iterative image registration technique with an application to stereo vision[C]//Proceedings of 7th International Joint Conference on Artificial Intelligence. San Francisco:Morgan Kaufmann, 1981:674-679.

基于ORB-SLAM的室内机器人定位和三维稠密地图构建

Indoor robot localization and 3D dense mapping based on ORB-SLAM

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 14

编辑推荐

Metrics

[1]	喻露, 胡剑锋, 姚磊岳. 基于人体骨架的非标准深蹲姿势检测方法[J]. 计算机应用, 2019, 39(5): 1448-1452.
[2]	陈田, 汪加伟, 安鑫, 任福继. 三维芯片多层与多核并行测试调度优化方法[J]. 计算机应用, 2018, 38(6): 1795-1800.
[3]	张全贵, 蔡丰, 李志强. 基于耦合多隐马尔可夫模型和深度图像数据的人体动作识别[J]. 计算机应用, 2018, 38(2): 454-457.
[4]	石念峰, 侯小静, 张平. 时空特征局部保持的运动视频关键帧提取[J]. 计算机应用, 2017, 37(9): 2605-2609.
[5]	俞璜悦, 王晗, 郭梦婷. 基于用户兴趣语义的视频关键帧提取[J]. 计算机应用, 2017, 37(11): 3139-3144.
[6]	王红霞, 王坤. 基于加锁机制的静态手势识别方法[J]. 计算机应用, 2016, 36(7): 1959-1964.
[7]	王梅, 于远芳, 屠大维, 周华. 基于Kinect的环境平面特征提取与重构[J]. 计算机应用, 2016, 36(5): 1366-1370.
[8]	蒋穗峰, 李艳春, 肖南峰. 基于手势识别的工业机器人操作控制方法[J]. 计算机应用, 2016, 36(12): 3486-3491.
[9]	谈家谱, 徐文胜. 基于Kinect的指尖检测与手势识别方法[J]. 计算机应用, 2015, 35(6): 1795-1800.
[10]	张毅黄聪罗元. 基于改进朴素贝叶斯分类器的康复训练行为识别方法[J]. 计算机应用, 2013, 33(11): 3187-3189.
[11]	杨全彭进业. 基于深度图像信息的手语识别算法[J]. 计算机应用, 2013, 33(10): 2882-2885.
[12]	王松韩永国吴亚东张赛楠. 基于图像主色彩的视频关键帧提取方法[J]. 计算机应用, 2013, 33(09): 2631-2635.
[13]	张建明蒋兴杰李广翠姜靓. 基于粒子群的关键帧提取算法[J]. 计算机应用, 2011, 31(02): 358-361.
[14]	吴渝贾学鹏李红波. 基于多特征相似度曲线曲率检测的关键帧提取[J]. 计算机应用, 2008, 28(12): 3084-3088.