基于双目立体匹配的三维重建系统研究  

Research on 3D reconstruction system based on binocular stereo matching

作　　者：吴昊[1] 李成斌 陈彦良 金亨 刘亚涛 Wu Hao;Li Chengbin;Chen Yanliang;Jin Heng;Liu Yatao(School of Computer and Control Engineering,Northeast Forestry University,Harbin 150040,China)

机构地区：[1]东北林业大学计算机与控制工程学院,哈尔滨150040

出　　处：《现代计算机》2024年第13期78-81,共4页Modern Computer

基　　金：东北林业大学大学生创新创业训练计划项目(202310225531)。

摘　　要：在计算机视觉领域,基于双目立体匹配的三维重建系统是一个研究热点。首先进行双目相机标定,获取标定参数。而后采用立体校正方法,使成像平面对准共面行,借助SGBM(semi-globalblock matching)立体匹配算法可以计算出视差。得到视差图后,计算像素深度,获取像素点的三维坐标。恢复三维坐标后使用Open3D恢复并显示点云图。In the field of computer vision,the 3D reconstruction system based on binocular stereo matching is a research hotspot.First,the binocular camera calibration was carried out to obtain the calibration parameters.Then,the stereo correction method is used to align the imaging plane with the coplanar row,and the disparity can be calculated with the help of the SGBM(Semi-Global Block Matching)stereo matching algorithm.After obtaining the disparity map,the pixel depth is calculated to obtain the 3D coordinates of the pixels.After recovering the 3D coordinates,use Open3D to recover and display the point cloud map.

关 键 词：三维重建 立体匹配算法 Open3D 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]