双目立体视觉非接触式测量研究  

Non-Contact Measurement with Binocular Stereo Vision

作　　者：黄松梅 毕远伟 刘殿通 程志宏 HUANG Song-mei BI Yuan-wei LIU Dian-tong CHENG Zhi-hong(School of Computer and Control Engineering, Yantai University, Yantai 264005, China School of Communication and Electronic Engineering,Qingdao Technological University, Qingdao 266520, China)

机构地区：[1]烟台大学计算机与控制工程学院,山东烟台264005 [2]青岛理工大学通信与电子工程学院,山东青岛266520

出　　处：《烟台大学学报（自然科学与工程版）》2017年第4期323-327,共5页Journal of Yantai University(Natural Science and Engineering Edition)

基　　金：国家自然科学基金资助项目(61602399)

摘　　要：为了实现距离和物体尺寸的非接触式测量,通过摄像机标定、图像的采集和预处理、立体校正、立体匹配、三维重建等关键技术,实现了物体点三维坐标的求解.采用图割法和块匹配2种算法分别进行立体匹配,建立了原图像与视差图之间的对应关系,实现了物体与相机距离测量,在此基础上实现了物体外观尺寸的测量.并对2种匹配算法的精度和速度进行了对比,实验结果表明:图割法测量结果更加精确,块匹配算法测量速度更快.In order to realize the non-contact measurement of distance and object size, the three-dimensional coor- dinates of the object point are solved through camera calibration, image acquisition and pretreatment, stereo correc- tion, stereo matching and three-dimensional reconstruction. The stereo matching is realized by two algorithms, graph cut method and block matching algorithm, and the correspondence relationship between the original image and the disparity map is established. Based on the measurement of the distance between the object amt the camera, the external dimensions of the object are measured. The accuracy and speed of the two matching algorithms are compared, and the experimental results show that the measurement result of graph cut is more accurate and the block matching algorithm is faster.

关 键 词：立体视觉 摄像机标定 立体匹配 三维重建 图割法 视差图 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]