首页 > 论文 > 激光与光电子学进展 > 56卷 > 21期(pp:211507--1)

基于ORB特征的视觉里程计算法优化

Optimization of Visual Odometry Algorithm Based on ORB Feature

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对在动态环境下受运动物体影响而不能准确进行机器人运动估计的问题,提出一种基于ORB特征区域分割的视觉里程计算法。利用相邻区域特征点三维空间距离不变性,对提取的特征点进行区域分割,将图像中运动物体产生的特征点与静态背景的特征点分割开,去除动态物体特征点的影响,再进行相机的位姿估计,从而去除场景中动态物体的干扰。实验结果表明,基于ORB特征区域分割的视觉里程计算法能够实时地在动态和静态环境中进行相机的位姿估计,具有很高的稳健性和精度。

Abstract

Robot movement cannot be accurately estimated because of the impact of moving objects in a dynamic environment. Therefore, this study proposes a visual odometry algorithm based on ORB (Oriented FAST and Rotated BRIEF) feature regional segmentation. Further, using the distance invariance of the feature points in the adjacent regions in a three-dimensional space, the extracted feature points are segmented and the feature points generated by the moving objects in the image are separated from the feature points in the static background, and influences of dynamic object feature points are removed. Subsequently, the position of the camera can be estimated, thereby removing the interference caused by the dynamic objects in a scene. The experimental results show that the visual odometry algorithm based on ORB feature regional segmentation can perform real-time pose estimation in both dynamic and static environments with good robustness and high precision.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391.4

DOI:10.3788/LOP56.211507

所属栏目:机器视觉

基金项目:贵州省科技计划、贵州省科技计划;

收稿日期:2019-04-03

修改稿日期:2019-05-06

网络出版日期:2019-11-01

作者单位    点击查看

林付春:贵州大学大数据与信息工程学院, 贵州 贵阳 550025
刘宇红:贵州大学大数据与信息工程学院, 贵州 贵阳 550025
周进凡:贵州大学大数据与信息工程学院, 贵州 贵阳 550025
马治楠:贵州大学大数据与信息工程学院, 贵州 贵阳 550025
何倩倩:贵州大学大数据与信息工程学院, 贵州 贵阳 550025
王曼曼:贵州大学大数据与信息工程学院, 贵州 贵阳 550025
张荣芬:贵州大学大数据与信息工程学院, 贵州 贵阳 550025

联系人作者:张荣芬(rfzhang@gzu.edu.cn)

备注:贵州省科技计划、贵州省科技计划;

【1】Xiong W, Xu Y L, Cui Y Q et al. Geometric feature extraction of ship in high-resolution synthetic aperture radar images. Acta Photonica Sinica. 47(1), (2018).
熊伟, 徐永力, 崔亚奇 等. 高分辨率合成孔径雷达图像舰船目标几何特征提取方法. 光子学报. 47(1), (2018).

【2】Huo J, Li Y H and Yang M. Measurement and error analysis of moving target pose based on laser projection imaging. Acta Photonica Sinica. 46(9), (2017).
霍炬, 李云辉, 杨明. 激光投影成像式运动目标位姿测量与误差分析. 光子学报. 46(9), (2017).

【3】Li M. Research on visual odometer method of outdoor mobile robot based on stereo camera. Nanjing: Southeast University. (2015).
李孟. 基于立体相机的室外移动机器人视觉里程计方法研究. 南京: 东南大学. (2015).

【4】Gao X and Zhang T. Visual SLAM XIV: from theory to practice. (2017).
高翔, 张涛. 视觉SLAM十四讲:从理论到实践. (2017).

【5】Nikoohemat S, Peter M, Elberink S O, Remote Sensing, Spatial Information Sciences et al. Wuhan, China. New York: IEEE, 2017, IV-. 2/W4, 355-362(2017).

【6】Charles R Q, Su H, Mo K C et al. PointNet: deep learning on point sets for 3D classification and segmentation. [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 77-85(2017).

【7】Cao J. Research on laser SLAM sensing method based on visual semantics in dynamic scene. Guangzhou: Guangdong University of Technology GDUT. (2018).
曹军. 动态场景下融合视觉语义的激光SLAM感知方法研究. 广州: 广东工业大学. (2018).

【8】Wang Z D and Guo C. An improved ORB_SLAM2 in dynamic scene with semantic segmentation. Journal of Dalian Maritime University. 44(4), 121-126(2018).
王召东, 郭晨. 一种动态场景下语义分割优化的ORB_SLAM2. 大连海事大学学报. 44(4), 121-126(2018).

【9】Rublee E, Rabaud V, Konolige K et al. ORB: an efficient alternative to SIFT or SURF. [C]∥2011 International Conference on Computer Vision, November 6-13, 2011, Barcelona, Spain. New York: IEEE. 2564-2571(2011).

【10】Lin Z L, Zhang G L, Yao E L et al. Stereo visual odometry based on motion object detection in the dynamic scene. Acta Optica Sinica. 37(11), (2017).
林志林, 张国良, 姚二亮 等. 动态场景下基于运动物体检测的立体视觉里程计. 光学学报. 37(11), (2017).

【11】Li Z, Zhou W H and Liu J L. Stereo visual odometry from disparity space in dynamic environments. Journal of Zhejiang University(Engineering Science). 42(10), 1661-1665(2008).
李智, 周文晖, 刘济林. 动态场景下基于视差空间的立体视觉里程计. 浙江大学学报(工学版). 42(10), 1661-1665(2008).

【12】Bay H. Tuytelaars T, van Gool L. SURF: speeded up robust features. ∥Leonardis A, Bischof H, Pinz A. European conference on computer vision-ECCV 2006. Lecture notes in computer science. Berlin, Heidelberg: Springer. 3951, 404-417(2006).

【13】Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision. 60(2), 91-110(2004).

【14】Li J, Cao Y P, Chen C et al. On-line three-dimension measurement method based on SURF algorithm. Acta Photonica Sinica. 46(9), (2017).
李建, 曹益平, 陈澄 等. 基于SURF算法的在线三维测量方法. 光子学报. 46(9), (2017).

【15】Li Y D, Xu X P and Wang J Q. Feature extraction based on pyramid match kernel algorithm with adaptive partitioning. Acta Photonica Sinica. 46(12), (2017).
李艳荻, 徐熙平, 王佳琪. 基于自适应分块金字塔匹配核的特征提取算法. 光子学报. 46(12), (2017).

【16】Calonder M, Lepetit V, Strecha C et al. BRIEF: binary robust independent elementary features. ∥Daniilidis K, Maragos P, Paragios N. European conference on computer vision-ECCV 2010. Lecture notes in computer science. Berlin, Heidelberg: Springer. 6314, 778-792(2010).

【17】Lee D T and Schachter B J. Two algorithms for constructing a Delaunay triangulation. International Journal of Computer & Information Sciences. 9(3), 219-242(1980).

【18】Peng Z. Research on vision-based self-motion estimation and environment modeling method in dynamic environment. Zhejiang: Zhejiang University. (2017).
彭真. 动态环境下基于视觉的自运动估计与环境建模方法研究. 浙江: 浙江大学. (2017).

【19】Gong J H. Depth priority algorithm and its improvement. Modern Electronics Technique. 30(22), 90-92(2007).
龚建华. 深度优先搜索算法及其改进. 现代电子技术. 30(22), 90-92(2007).

【20】Zhu D M and Wang Z Q. Extraction of keyframe from motion capture data based on motion sequence segmentation. Journal of Computer-Aided Design & Computer Graphics. 20(6), 787-792(2008).
朱登明, 王兆其. 基于运动序列分割的运动捕获数据关键帧提取. 计算机辅助设计与图形学学报. 20(6), 787-792(2008).

【21】Gargallo P, Prados E and Sturm P. Minimizing the reprojection error in surface reconstruction from images. [C]∥2007 IEEE 11th International Conference on Computer Vision, October 14-21, 2007, Rio de Janeiro, Brazil. New York: IEEE. 9849037, (2007).

【22】Mur-Artal R. Montiel J M M, Tardós J D. ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Transactions on Robotics. 31(5), 1147-1163(2015).

引用该论文

Lin Fuchun,Liu Yuhong,Zhou Jinfan,Ma Zhinan,He Qianqian,Wang Manman,Zhang Rongfen. Optimization of Visual Odometry Algorithm Based on ORB Feature[J]. Laser & Optoelectronics Progress, 2019, 56(21): 211507

林付春,刘宇红,周进凡,马治楠,何倩倩,王曼曼,张荣芬. 基于ORB特征的视觉里程计算法优化[J]. 激光与光电子学进展, 2019, 56(21): 211507

被引情况

【1】许广富,曾继超,刘锡祥. 融合光流法和特征匹配的视觉里程计. 激光与光电子学进展, 2020, 57(20): 201501--1

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF