摘要
针对标定物存在的自遮挡问题,提出了一种应用于多摄像机的利用投影特征点进行标定的方法。在投影平面幕中投影标定图案,统一投影平面坐标系与世界坐标系。特征提取后,分别对每个摄像机标定,根据立体视觉特性求取摄像机间的相对位姿关系,并计算重投影误差。该方法对标定物自遮挡有一定的鲁棒性,同时有效地降低了计算量。
A Calibration approach to multiple cameras is put forward in terms of projective feature points in order to solve the problem of calibration target self-occlusion.A coordinate system is unified between world coordinates and projective plane ones after feature patterns are projected onto a planar screen.Then corners are extracted for calibration images and each camera is calibrated separately,from which it can obtain internal parameters and relative poses among cameras.Re-projection error is analyzed by feature points.Experimental results indicate that the method is robust to calibration object self-occlusion and also can reduce computational complexity.
出处
《北京信息科技大学学报（自然科学版）》
2012年第2期88-91,96,共5页
Journal of Beijing Information Science and Technology University
基金
北京市教育委员会科技计划面上项目(KM201010772021)
关键词
多摄像机
投影特征点
投影标定
multiple cameras
projective feature points
projective calibration
作者简介
刘亚辉（1974-），女，河北任丘人，博士，讲师，主要从事计算机视觉，图像处理方面的研究。
