激光切割视觉系统单目摄像机快速标定方法  

Monocular camera fast calibration method for laser cutting vision system

作　　者：杨煜俊[1] 陈洵凛 许征波 YANGYu-jun;CHEN Xun - lin;XU Zhenn - bo(School of Electromechanic Engineering,Guangdong University of Technology,Guangzhou 510006,China)

机构地区：[1]广东工业大学机电工程学院,广东广州510006

出　　处：《激光与红外》2018年第7期880-884,共5页Laser & Infrared

摘　　要：针对目前激光切割机结合视觉切割行业中现有的张正友一般圆点标定算法中存在计算量大、结果不稳定的问题。提出一种基于九圆点的摄像机自标定算法。算法首先计算出图像和定义在世界坐标系X-Y平面上的模板之间的单应性矩阵,利用该单应性矩阵线性求解出摄像机内参,然后考虑非线性畸变因素,求解出畸变系数。最后在矫正后的模板中求出内外共八个仿射投影矩阵,并取其均值做为最终投影矩阵来求解出世界坐标。实验结果表明:该算法比现有的基于圆点的摄像机自标定算法更快速、更稳定,达到精度更高。As the existing Zhang Zhengyou general dot calibration algorithm has a large amount of calculation and the unstable results in the current visual cutting industry with laser cutting machine,a self-calibration algorithm based on nine-dotted camera is proposed.The homography matrix between the image and the template defined on the X-Y plane of the world coordinate system is calculated.The homography matrix is used to linearly solve the internal parameters of the camera,and then the distortion coefficient is solved considering the nonlinear distortion factor.Finally,eight affine projection matrices are obtained in the corrected template,and the mean value is taken as the final projection matrix to solve the world coordinates.The experimental results show that the algorithm is faster and more stable than the existing dot-based camera self-calibration algorithm.

关 键 词：九圆点 摄像机自标定 单应性矩阵 仿射投影矩阵 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]