基于Kinect的三维视觉里程计的设计

doi:10.11772/j.issn.1001-9081.2014.08.2371

计算机应用 ›› 2014, Vol. 34 ›› Issue (8): 2371-2374.DOI: 10.11772/j.issn.1001-9081.2014.08.2371

基于Kinect的三维视觉里程计的设计

王亚龙,张奇志,周亚丽

北京信息科技大学自动化学院，北京100192

收稿日期:2014-02-21 修回日期:2014-04-13 出版日期:2014-08-01 发布日期:2014-08-10
通讯作者: 王亚龙
作者简介:王亚龙（1989-），男，河南商丘人，硕士研究生，主要研究方向：机器人SLAM地图创建；张奇志（1963-），男，辽宁阜新人，教授，博士，主要研究方向：机器人；周亚丽（1968-），女，辽宁沈阳人，教授，主要研究方向：运动控制、智能控制。
基金资助:
国家自然科学基金资助项目;北京市属高等学校人才强教深化计划资助项目

Design of 3D visual odometry based on Kinect

WANG Yalong,ZHANG Qizhi,ZHOU Yali

School of Automation, Beijing Information Science and Technology University, Beijing 100192, China

Received:2014-02-21 Revised:2014-04-13 Online:2014-08-01 Published:2014-08-10
Contact: WANG Yalong

摘要/Abstract

摘要：

针对移动服务机器人在未知环境下三维路径估计的问题，设计了一种基于Kinect的实时估计机器人运动轨迹的方法。该方法采用Kinect获取机器人运动过程中连续帧的彩色和深度信息，首先，提取并匹配目标帧和参考帧的SURF的特征点；然后，结合深度信息利用经典P3P问题的方法及改进的随机采样一致性(RANSAC)算法计算机器人的初始6自由度(DOF)位姿；最后，通过非线性最小二乘算法最小化初始位姿内点的双向投影误差来提高位姿精度，进而得到机器人的运动轨迹。同时对比了不同特征点及描述符结合下的里程计精度。实验结果表明，所提方法能够将里程计误差降低到3.1%，且能够满足实时要求，可为机器人同时定位与地图创建提供重要的先验信息。

Abstract:

Aiming at the problem of 3D trajectory estimation for mobile service robots in unknown environments, this thesis proposed a novel framework for using Kinect sensor to estimate the motion trajectory of mobile robots in real time. RGB-D information of successive frames in the environment was captured by a Kinect: firstly, the feature points of Speeded Up Robust Feature (SURF) of the target frame and reference frame were extracted and matched; secondly, initial 6 Degree Of Freedom (DOF) pose estimation was computed by a novel solution for the classical Perspective-3-Point (P3P) problem and an improved Random Sample Consensus (RANSAC) algorithm combining with depth information; lastly, the pose estimation was refined by minimizing the reprojection error of inliers of initial value via a nonlinear least-squares solver, and then the motion trajectory of the robot was gained. The experimental results show that the error of the odometry is reduced to 3.1% by the proposed approach in real time. It can provide important prior information for simultaneous localization and mapping of robots.

中图分类号:

TP242.6
TP18

王亚龙张奇志周亚丽. 基于Kinect的三维视觉里程计的设计[J]. 计算机应用, 2014, 34(8): 2371-2374.

WANG Yalong ZHANG Qizhi ZHOU Yali. Design of 3D visual odometry based on Kinect[J]. Journal of Computer Applications, 2014, 34(8): 2371-2374.

参考文献

［1］NISTER D, NARODITSKY O, BERGEN J. Visual odometry ［C］// CVPR 2004: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2004: I-652-I-659.
［2］ENGEL J, STURM J, CREMERS D. Semi-dense visual odometry for a monocular camera ［C］// Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 2013: 1449-1456.
［3］YILMAZ O, KARAKUS F. Stereo and Kinect fusion for continuous 3D reconstruction and visual odometry ［C］// Proceedings of the 2013 IEEE International Conference on Electronics Computer and Computation. Piscataway: IEEE Press, 2013: 115-118.
［4］McDONALD J, KAESS M, CADENA C. Real-time 6-DOF multi-session visual SLAM over large scale environment ［J］. Robotics and Autonomous Systems, 2012, 61(10): 1144-1158.
［5］WANG Y. A research on simultaneous localization and mapping of mobile robot with omnidirectional vision ［D］. Harbin: Harbin Engineering University, 2010.（王玉全.基于全景视觉的移动机器人同时定位与地图创建方法研究［D］.哈尔滨：哈尔滨工程大学,2010.）
［6］KNEIP L, CHLI M, SIEGWART R. Robust real-time visual odometry with a single camera and an IMU ［C］// Proceedings of the 2011 British Machine Vision Conference. Durham: BMVC Press, 2011: 16.1-16.11.
［7］WHELAN T, JOHANNSSON H, KAESS M, et al. Robust real-time visual odometry for dense RGB-D mapping ［C］// Proceedings of the 2013 IEEE International Conference on Robotics and Automation. Piscataway: IEEE Press, 2013: 5724-5731.
［8］DRYANOVSKI I, VALENTI R G, XIAO J. Fast visual odometry and mapping from RGB-D data ［C］// Proceedings of the 2013 IEEE International Conference on Robotics and Automation. Piscataway: IEEE Press, 2013: 2305-2310.
［9］KLUSSENDORFF J H, HARTMANN J, FOROUHER D, et al. Graph-based visual SLAM and visual odometry using an RGB-D camera ［C］// Proceedings of the 2013 9th Workshop on Robot Motion and Control. Piscataway: IEEE Press, 2013: 288-293.
［10］SCARAMUZZA D, FRAUNDORFER F. Visual odometry ［J］. Robotics and Automation Magazine, 2011, 18(4): 80-92.
［11］SIEGWART R, NOURBAKHSH I, SCARAMUZZA D. Introduction to autonomous mobile robots ［M］. Cambridge: Massachusetts Institute of Technology Press, 2011: 265-366.
［12］BAY H, ESS A, TUYTELAARS T, et al. SURF: speeded up robust features ［J］. Computer Vision and Image Understanding, 2008, 110(3): 346-359.
［13］KNEIP L, SCARAMUZZA D, SIEGWART R. A novel parametrization of the perspective-three-point problem for a direct computation of absolute camera position and orientation ［C］// Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2011: 2969-2976.
［14］RAGURAM R, FRAHM J M, POLLEFEVS M. A comparative analysis of RANSAC techniques leading to adaptive real-time random sample consensus ［C］// Proceedings of the 10th European Conference on Computer Vision, LNCS 5303. Berlin: Springer, 2008: 500-513.
［15］STRAUB J, HILSENBECK S, SCHROTH G, et al. Fast relocalization for visual odometry using binary features ［C］// Proceedings of the 20th IEEE International Conference on Image Processing. Piscataway: IEEE Press, 2013: 2548-2552.
［16］CHUM O, MATAS J. Optimal randomized RANSAC ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 11(8): 1472-1482.
［17］NISTER D. Preemptive RANSAC for live structure and motion estimation ［J］. Machine Vision and Applications, 2005, 16(5): 321-329.

[1]	卢金燕戚肖克. 基于点线特征的解耦视觉伺服控制方法[J]. 计算机应用, 0, (): 0-0.
[2]	郑思诚, 孔令华, 游通飞, 易定容. 动态环境下基于深度学习的语义SLAM算法[J]. 计算机应用, 2021, 41(10): 2945-2951.
[3]	黄巨挺, 高宏力, 戴志坤. 基于编码解码结构的移动端电力线语义分割方法[J]. 计算机应用, 2021, 41(10): 2952-2958.
[4]	郑李萍, 王建强, 张玉召, 董祚帆. 多时空配送任务驱动的无人车队车辆数优化方法[J]. 计算机应用, 2021, 41(5): 1406-1411.
[5]	栾佳宁, 张伟, 孙伟, 张奥, 韩冬. 基于二维码视觉与激光雷达融合的高精度定位算法[J]. 计算机应用, 2021, 41(5): 1484-1491.
[6]	梁臻, 房体育, 李金屏. 基于虚拟导航线的农业机器人精确视觉导航方法[J]. 计算机应用, 2021, 41(1): 191-198.
[7]	徐小强, 王明勇, 冒燕. 基于改进人工势场法的移动机器人路径规划[J]. 计算机应用, 2020, 40(12): 3508-3512.
[8]	赵宏, 刘向东, 杨永娟. 基于RGB-D图像的室内机器人同时定位与地图构建[J]. 计算机应用, 2020, 40(12): 3637-3643.
[9]	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.
[10]	祁玄玄, 黄家骏, 曹建安. 基于改进A^*算法的无人车路径规划[J]. 计算机应用, 2020, 40(7): 2021-2027.
[11]	罗飞, 刘鹏飞, 罗元, 朱思蒙. 多特征融合的运动想象脑电特征提取方法[J]. 计算机应用, 2020, 40(2): 616-620.
[12]	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.
[13]	付久鹏, 曾国辉, 黄勃, 方志军. 基于双向快速探索随机树的狭窄通道路径规划[J]. 计算机应用, 2019, 39(10): 2865-2869.
[14]	黄超, 梁圣涛, 张毅, 张杰. 基于多目标蝗虫优化算法的移动机器人路径规划[J]. 计算机应用, 2019, 39(10): 2859-2864.
[15]	赵旭浩, 王轶群, 刘健, 徐春晖. 基于能量约束的自主水下航行器任务规划算法[J]. 计算机应用, 2019, 39(9): 2529-2534.

基于Kinect的三维视觉里程计的设计

Design of 3D visual odometry based on Kinect

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics