基于双目视觉的铝合金件三维点云重建研究  

Aluminum Alloy Parts Based on Binocular Vision 3D Point Cloud Reconstruction Method

作　　者：吕钦 周诗洋 万波为[1,2,3] 刘怀广 LYU Qin;ZHOU Shiyang;WAN Bowei;LIU Huaiguang(Key Laboratory of Metallurgical Equipment and Control Technology,Ministry of Education,Wuhan University of Science and Technology,Wuhan 430081,China;Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering,Wuhan University of Science and Technology,Wuhan 430081,China;Precision Manufacturing Institute,Wuhan University of Science and Technology,Wuhan 430081,China)

机构地区：[1]武汉科技大学冶金装备及其控制教育部重点实验室,武汉430081 [2]武汉科技大学机械传动与制造工程湖北省重点实验室,武汉430081 [3]武汉科技大学精密制造研究院,武汉430081

出　　处：《组合机床与自动化加工技术》2025年第2期63-68,共6页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家自然科学基金项目(51805386)。

摘　　要：针对传统三维立体匹配算法对光照不均、弱纹理图像误匹配率高导致三维重建点云误差大的问题,提出一种基于改进十字交叉域聚合的加强边缘梯度的立体匹配算法对表面易反光、纹理弱的铝合金件进行三维重建。首先,搭建双目立体视觉实验平台,并通过张正友标定法对测量系统进行标定;再根据提出的改进十字交叉区域代价聚合的立体匹配算法获取视差图和深度图;最后,将深度图转换为点云信息,并采用Open3D开源库重构铝合金件的三维信息。实验结果表明,提出的立体匹配算法能有效地降低误匹配率,重建出的铝合金件的三维点云孔径直径平均误差小于5%,可以为机械零件尺寸的快速测量提供参考。To solve the problem of a high mismatching rate for uneven illumination and weak texture images,large error in the three-dimensional reconstructed point cloud in the traditional three-dimensional stereo matching algorithm,a stereo matching algorithm based on enhanced cross-based cost aggregation with strengthened edge gradient is proposed for three-dimensional reconstruction of aluminum alloy parts with reflective surfaces and weak textures.Firstly,the experiment platform of binocular stereo vision is built and the measurement system is calibrated by Zhang calibration method.Then,the parallax map and depth map are obtained according to the proposed stereo matching algorithm with enhanced cross-based cost aggregation.Finally,the depth map is converted into the three-dimensional point cloud.The three-dimensional structure of aluminum alloy parts is reconstructed by using Open3D software.The experimental results show that the proposed stereo matching algorithm can effectively reduce the mis-matching rate,and the average error of aperture diameters for reconstructed 3D point cloud of aluminum alloy parts is less than 5%.The proposed method can be used as a reference for the rapid measurement of industrial machine parts.

关 键 词：双目视觉 铝合金件 立体匹配 三维点云重建 

分 类 号：TH165[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]