首页 > 论文 > 激光与光电子学进展 > 55卷 > 5期(pp:51102--1)

基于靶标区域分割的双目定位系统研究与实现

Research and Implementation of Binocular Location System Based on Region of Interest Segmentation

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

摘要

针对传统双目视觉定位系统立体匹配困难、计算量大、效率低的问题,设计了一种基于靶标区域(ROI)提取的双目定位系统,以改善定位精度。首先,利用张氏标定法标定双目摄像机,并通过Bouguet算法对整个系统进行立体校正;然后利用直方图阈值法和投影法分割图像中的ROI,以大幅降低后续特征匹配的计算量;最后采用加速稳健特征算法对左右摄像机图片进行亚像素级角点的提取与匹配,并结合标定结果获得精确的定位。实验结果表明,ROI内特征点的匹配准确度可以达到90%以上,系统的定位时间在700 ms以内,可以满足系统实时性的要求。该方法主要针对ROI进行特征点提取和匹配,避免了不必要的全局图像处理,从而将匹配速度从秒级缩短至毫秒级。

Abstract

Aiming at the problems of difficulty in stereo matching, large computation amount, and low efficiency of the traditional binocular vision positioning system, a binocular positioning system based on the region of interest (ROI) extraction is designed to improve the positioning accuracy. The binocular camera is calibrated by calibration method of Zhang, and the system is calibrated by Bouguet algorithm. The ROI in image is divided by the histogram thresholding method and projection method, and the computation amount of the feature matching is reduced greatly. The speed up robust features algorithm is used to extract and match the camera image subpixel corners, and accurate positioning results are obtained when the calibration results are combined. Experimental results show that the matching accuracy of feature points in ROI can reach more than 90%, and the positioning time of the proposed system is less than 700 ms, which can meet the real-time requirements of the system. This proposed method is mainly used for ROI feature point detection and matching. The global image processing is avoided, and the feature points matching speed can be reduced from seconds to milliseconds magnitude.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TH741

DOI:10.3788/lop55.051102

所属栏目:成像系统

基金项目:国家自然科学基金(61401049)、军工专项(JG2015068)、国家大学生创新创业计划(201710611038)

收稿日期:2017-10-26

修改稿日期:2017-11-10

网络出版日期:--

作者单位    点击查看

刘远远:重庆大学光电技术及系统教育部重点实验室, 重庆 400044
冯鹏:重庆大学光电技术及系统教育部重点实验室, 重庆 400044
龙邹荣:重庆大学光电技术及系统教育部重点实验室, 重庆 400044
俞鹏炜:重庆大学光电技术及系统教育部重点实验室, 重庆 400044
李鑫韬:重庆大学光电技术及系统教育部重点实验室, 重庆 400044
魏彪:重庆大学光电技术及系统教育部重点实验室, 重庆 400044

联系人作者:刘远远(15922776016@163.com)

备注:刘远远(1994—),女,硕士研究生,主要从事机器视觉及图像处理方面的研究。E-mail: 15922776016@163.com

【1】Tang X X. Target identification and positioning research based on binocular stereo vision[D]. Harbin: Harbin University of Science and Technology, 2017.
唐献献. 基于双目立体视觉的目标识别与定位研究[D]. 哈尔滨: 哈尔滨理工大学, 2017.

【2】Chen D M. Research on vision stereo matching algorithm based on computer[J]. Wireless Internet Technology, 2017(4): 61-62.
陈冬梅. 基于计算机的视觉立体匹配算法研究[J]. 无线互联科技, 2017(4): 61-62.

【3】Ma X W, Gan Y, Sun F J. Research on extraction of bottom of shoe pattern based on binocular stereo vision[J]. International Journal of Plant Engineering and Management, 2016, 21(1): 20-34.

【4】Gu Y Z, Sato M, Zhang X L. An active stereo vision system based on neural pathways of human binocular motor system[J]. Journal of Bionic Engineering, 2007, 4(4): 185-192.

【5】Wang X J, Xing F, Liu F. Stereo matching of objects with same features based on Delaunay triangulation and affine constraint[J]. Acta Optica Sinica, 2016, 36(11): 1115004.
王向军, 邢峰, 刘峰. Delaunay三角剖分和仿射约束的特征相同多物体同名点立体匹配[J]. 光学学报, 2016, 36(11): 1115004.

【6】Zhu S P, Yan L N, Li Z. Stereo matching algorithm based on improved Census transform and dynamic programming[J]. Acta Optica Sinica, 2016, 36(4): 0415001.
祝世平, 闫利那, 李政. 基于改进Census变换和动态规划的立体匹配算法[J]. 光学学报, 2016, 36(4): 0415001.

【7】Duan H B, Li H, Luo Q N, et al. A binocular vision-based UAVs autonomous aerial refueling platform[J]. Science China Information Sciences, 2016, 59(5): 232-238.

【8】Ma X W, Gan Y, Sun F J. Research on extraction of bottom of shoe pattern based on binocular stereo vision[J]. International Journal of Plant Engineering and Management, 2016, 1: 20-34.

【9】Zhang Z Y. Aflexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2000, 22(11): 1330-1334.

【10】Dai S J, Shao M, Wu J N, et al. Internal corner detection of chessboard image for camera calibration based on 12 pixels symmetrical template[J]. Infrared and Laser Engineering, 2014, 43(4): 1306-1311.
戴士杰, 邵猛, 吴佳宁, 等. 使用12像素对称模板的棋盘格内角点检测[J]. 红外与激光工程, 2014, 43(4): 1306-1311.

【11】Zhang H C. Research of color image segmentation based on the combination of OTSU and region growing method[D]. Jinan: Shandong Normal University, 2016.
张洪超. 基于大津法和区域生长法结合的彩色图像分割方法研究[D]. 济南: 山东师范大学, 2016.

【12】Tuo Q. Research on image threshold segmentation algorithm based on maximum entropy and genetic algorithm[D]. Kunming: Kunming University of Science and Technology, 2016.
庹谦. 最大熵结合遗传算法的图像阈值分割算法研究[D]. 昆明: 昆明理工大学, 2016.

【13】Mo S H, Yu N N, Dai J S. Application of iterative in the weld seam image threshold segmentation[J]. Electric Welding Machine, 2015, 45(2): 53-56.
莫胜撼, 喻宁娜, 戴建树. 迭代法在焊缝图像阈值分割中的应用[J]. 电焊机, 2015, 45(2): 53-56.

【14】Bay H, Ess A, Tuytelaars T, et al. Speeded-up robust features (SURF)[J]. Computer Vision & Image Understanding, 2008, 110(3): 346-359.

【15】Ke Y, Sukthankar R. PCA-SIFT: a more distinctive representation for local image descriptors[C]. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004: 506-513.

【16】Jin J J, Lu W L, Guo X T, et al. Position registration method of simultaneous phase-shifting interferograms based on SURF and RANSAC algorithms[J]. Acta Optica Sinica, 2017, 37(10): 1012002.
靳京京, 卢文龙, 郭小庭, 等. 基于SURF和RANSAC算法的同步相移干涉图位置配准方法[J]. 光学学报, 2017, 37(10): 1012002.

引用该论文

Liu Yuanyuan,Feng Peng,Long Zourong,Yu Pengwei,Li Xintao,Wei Biao. Research and Implementation of Binocular Location System Based on Region of Interest Segmentation[J]. Laser & Optoelectronics Progress, 2018, 55(5): 051102

刘远远,冯鹏,龙邹荣,俞鹏炜,李鑫韬,魏彪. 基于靶标区域分割的双目定位系统研究与实现[J]. 激光与光电子学进展, 2018, 55(5): 051102

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