基于ICP算法的双目标定改进方法研究
郭清达; 全燕鸣; 于广平; 武彦林
刊名光学学报
2016
卷号36期号:12页码:1-8
关键词机器视觉 双目标定改进 点云匹配 ICP算法
ISSN号0253-2239
其他题名Improved Binocular Stereo Vision Calibration Based on ICP Algorithm
通讯作者全燕鸣
产权排序2
中文摘要双目视觉作为一种非接触三维测量技术,其位姿标定结果的好坏将直接影响三维物体测量的精度,本文基于 ICP 算法(Iterative Closest Point,简称 ICP)的获得两组点集之间平移和旋转参数的原理,提出了一种在传统双目位姿标定结果的基础上补偿双目标定矩阵改善精度的方法。首先,介绍了摄像机模型、双目视觉测量模型和 ICP 算法的基本思想。然后,用双目摄像机标定的外参数和相同的靶标坐标系获得双目视觉作为一种非接触三维测量技术,其位姿标定结果的好坏将直接影响三维物体测量的精度,本文基于 ICP 算法(Iterative Closest Point,简称 ICP)的获得两组点集之间平移和旋转参数的原理,提出了一种在传统双目位姿标定结果的基础上补偿双目标定矩阵改善精度的方法。首先,介绍了摄像机模型、双目视觉测量模型和 ICP 算法的基本思想。然后,用双目摄像机标定的外参数和相同的靶标坐标系获得双目视觉位姿矩阵,在此提出基于 ICP 算法获得两组点集的旋转平移矩阵补偿双目位姿矩阵的方法,以及相应的靶标角点坐标投影误差分析模型。最后,双目摄像机采集 9 组 5*7 个角点的靶标标定图像,应用 ICP 算法的补偿双目位姿矩阵,并采用误差模型对 9 组标定结果进行了分析,双目结构光标定改进实验表明,应用ICP 算法补偿双目标定模型能显著地提高双目标定的精度。
英文摘要Binocular vision is a new kind of non-contact 3-D measurement technology, and that the calibration result is good or bad will directly lead to the precision of the 3-D object measurement. This paper is based on ICP algorithm principle to obtain translation and rotation parameters between two point sets, and then compensate binocular stereo calibration matrix to improve the precision. Firstly, the camera model and binocular vision measurement model in Cartesian space and the basic steps of the ICP algorithm were introduced. Then, the external parameters of binocular vision and the same target plane were used for obtaining binocular vision pose matrix, which would be compensated by using the rotation and translation matrix of the two groups of point set based on ICP algorithm. Furthermore, the analysis model of corresponding target point coordinates projection error was established. Finally, 9 sets of calibration images including 5*7 points were collected, the binocular vision calibration parameters were obtained, the pose matrix using the ICP algorithm was compensated and 9 sets of calibration error by using points coordinates projection error model were got. The results showed that the application of ICP algorithm which is used to compensate the binocular calibration model could significantly improve the accuracy of binocular calibration.
收录类别EI ; CSCD
语种中文
CSCD记录号CSCD:5887174
内容类型期刊论文
源URL[http://ir.sia.cn/handle/173321/18847]  
专题沈阳自动化研究所_广州中国科学院沈阳自动化研究所分所
推荐引用方式
GB/T 7714
郭清达,全燕鸣,于广平,等. 基于ICP算法的双目标定改进方法研究[J]. 光学学报,2016,36(12):1-8.
APA 郭清达,全燕鸣,于广平,&武彦林.(2016).基于ICP算法的双目标定改进方法研究.光学学报,36(12),1-8.
MLA 郭清达,et al."基于ICP算法的双目标定改进方法研究".光学学报 36.12(2016):1-8.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace