基于特征点能量的双目立体匹配稳健算法

姚海滨; 翁金平; 崔海华; 程筱胜

doi:doi:10.3788/lop53.021501

激光与光电子学进展, 2016, 53 (2): 021501, 网络出版: 2015-12-25

基于特征点能量的双目立体匹配稳健算法下载： 688次

Binocular Stereo Matching Robust Algorithm Based on Energy of Marked Points

论文大纲

姚海滨 ^1,*翁金平 ²崔海华 ²程筱胜 ²

作者单位

¹ 扬州市职业大学机械工程学院, 江苏扬州 225012

² 南京航空航天大学机电学院, 江苏南京 210016

机器视觉能量双目标志点立体匹配 machine vision energy binocular marked points stereo matching

AI 词云图 AI一句话精读 AI短摘要

注：本部分内容由 AI 自动生成，请您知悉。

摘要

为提高双目立体视觉测量图像精确匹配的稳定性，提出一种基于特征点能量的稳健匹配新算法。该算法基于极线约束获取左右图像中特征点的初始匹配，根据特征点之间极线约束关系定义了一种不受仿射变换影响的能量来描述特征点，通过比对特征点能量值来剔除误匹配。该算法有效降低了误匹配率和误剔除率，从而满足多视角测量数据拼合过程中严格限制误匹配率的要求。实验结果表明，该算法正确匹配率大于95%，误剔除率小于2%，具有较强的稳健性。

Abstract

In order to improve the stability of the binocular stereo vision measuring accuracy image matching. A new robust matching algorithm based on feature point energy is proposed, the algorithm based on epipolar constraint to get the initial matching feature points around image. The energy not affected by affine transformation is defined to describe feature points based on epipolar constraint relationship among feature points, and the error matching is removed by comparing the energy of feature points. The proposed method effectively reduces the false matching rate and the false rejected rate so that it can meet the need of strictly limited false matching rate in the process of multiple angle measurement data. Experimental results show that the correct matching rate of the proposed algorithm is over 95%, and the false rejected rate is less than 2%.The algorithm has better robustness.

参考文献

[1] 燕静杰, 杨庆华, 宋宇鹏, 等. 三维激光扫描技术应用于再造耳廓远期变化的研究[J]. 中华耳科科学杂志, 2013, 11(4): 524-528.

Yan Jingjie, Yang Qinghua, Song Yupeng, et al.. The study of reconstruction auricle long-term changes by 3D laser scan technology[J]. Chinese Journal of Otology, 2013, 11(4): 524-528.

[2] 汤明辉, 程筱胜, 崔海华, 等. 面向结构光三维测量的高稳定映射拼接方法[J]. 光学学报, 2014, 34(11): 1112006.

Tang Minghui, Cheng Xiaosheng, Cui Haihua, et al.. A high stability mapping stitching method for structured light three dimensional measurement[J]. Acta Optica Sinica, 2014, 34(11): 1112006.

[3] 邵杰, 张爱武, 王书民, 等. 三维激光点云与CCD 影像融合的研究[J]. 中国激光, 2013, 40(5): 0514001.

Shao Jie, Zhang Aiwu, Wang Shumin, et al.. Research on fusion of 3D laser point clouds and CCD image[J]. Chinese J Lasers, 2013, 40(5): 0514001.

[4] 车建强, 戴宁, 崔海华, 等. 面向彩色物体的双目三维测量编码新方法[J]. 光学学报, 2014, 34(11): 1115001.

Che Jianqiang, Dai Ning, Cui Haihua, et al.. A novel encoding method for binocular three dimentional mesurement of color objectes[J]. Acta Optica Sinica, 2014, 34(11): 1115001.

[5] 崔艳军, 张文峰, 李建欣, 等. 条纹投影三维测量的Gamma 畸变校正方法[J]. 光学学报, 2015, 35(1): 0112002.

Cui Yanjun, Zhang Wenfeng, Li Jianxin, et al.. A method of Gamma correction in fringe projection measurement[J]. Acta Optica Sinica, 2015, 35(1): 0112002.

[6] Verri A, Trucco E. Introductory Techniques for 3D Computer Vision[M]. Upper Saddle River: Prentice Hall, 1998.

[7] Scharstein D, Szeliski R. A taxonomy and evaluation of dense two frame stereo correspondence algorithms[J]. International Journal of Computer Vision, 2002, 47(13): 7-42.

[8] Maciel J, Costeira J P. A global solution to sparse correspondence problems[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(2): 187-199.

[9] Kolmogorov V, Zabih R. Computing visual correspondence with occlusions using graph cuts[J]. ICCV, 2001, 2: 508-515.

[10] Lowe D G. Distinctive image features from scales-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

[11] Ke Y, Sukthankar R. PCA-SIFT: A more distinctive representation for local image descriptors[J]. Computer Vision and Pattern Recognition, 2004, 2: 506-513.

[12] Pollard S B, Mayhew J, Frisby J. PMF: A stereo correspondence algorithm using a disparity gradient limit[J]. Perception, 1985, 14: 449-470.

[13] Scharstein D, Szeliski R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J]. International Journal of Computer Vision, 2002, 47(1-3): 7-42.

[14] Kanade T, Okutomi M. A stereo matching algorithm with an adaptive window: Theory and experiment[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16(9): 920-932.

[15] 张辉, 张丽艳, 陈鉴富, 等. 基于自适应迭代松弛的立体点对匹配鲁棒算法[J]. 中国图象图形学报, 2009, 14(7): 1378-1385.

Zhang Hui, Zhang Liyan, Chen Jianfu, et al.. A robust stereo matching algorithm based on adaptive relaxation[J]. Chinese Journal of Image and Graphics, 2009, 14(7): 1378-1385.

姚海滨, 翁金平, 崔海华, 程筱胜. 基于特征点能量的双目立体匹配稳健算法[J]. 激光与光电子学进展, 2016, 53(2): 021501. Yao Haibin, Weng Jinping, Cui Haihua, Cheng Xiaosheng. Binocular Stereo Matching Robust Algorithm Based on Energy of Marked Points[J]. Laser & Optoelectronics Progress, 2016, 53(2): 021501.

基于特征点能量的双目立体匹配稳健算法下载： 688次

关于本站 Cookie 的使用提示

全站搜索

基于特征点能量的双目立体匹配稳健算法 下载： 688次

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索

基于特征点能量的双目立体匹配稳健算法下载： 688次