三维信息提取中摄像机标定技术的的研究论文.docx

南京航空航天大学硕士学位论文摘要摄像机标定是计算机视觉中的一个重要研究方向，它在机器人视觉导航、军事科学、机械制造、虚拟现实等领域得到了广泛的应用。本文以 Marr 视觉理论为基础，重点研究了摄像机标定问题，并成功构造了基于双目立体视觉的三维信息提取系统，进而得到了特征点的三维坐标。本文的主要工作如下：提出了一种新的基于消失点的摄像机标定方法。充分利用了射影几何中交比和调和共轭的知识以及正方形模板对角线相互垂直的性质，根据一幅模板图像可以得到两组相互正交的消失点连线，在至少三个不同方向拍摄的图像上线性求解出摄像机的所有内部参数。该方法无须图像匹配，避免了边缘检测和直线拟合带来的误差，降低了计算复杂度，同时大大提高了标定精度。提出了一种改进的基于圆环点的摄像机自标定方法。利用模板图像的Harris 角点分别计算四条直径方向上的消失点，再根据消失点和圆环点之间的约束关系求取圆环点的图像坐标，最后高精度地求解出摄像机的所有内部参数。该算法的优点是不需要拟合椭圆和直径，也不需要利用椭圆和消失线繁琐地求取圆环点坐标。在左右图像特征点匹配完成的基础上，将摄像机标定技术应用于三维信息提取，成功地获得了特征点的三维坐标。计算出的特征点三维坐标和标准值之间误差很小，三维信息提取系统取得了很好的效果。实验结果表明，本文采取的算法鲁棒性强。关键词：摄像机标定，自标定，射影几何，消失点，基本矩阵，三维信息提取i三维信息提取中的摄像机标定技术研究ABSTRACTCamera calibration is a significant field of computer vision and it has beenwidely applied in many fields, such as robot vision navigation, militaryapplication, mechanical manufacture, virtual reality and so on. By the theory ofMarr vision, research on camera calibration is emphasized. A system of 3Dinformation extraction based on binocular stereo vision is designed successfully toextract 3D coordinates of feature points. The main job of the thesis can bedescribed as follows:A new approach for camera calibration based on vanishing points is proposed.Two pairs of vanishing points of orthogonal directions from each image areobtained by using the concept of cross ratio and harmonic conjugate in projectivegeometry and the orthogonal property of the two diagonals on a square. Allintrinsic parameters are calculated linearly after capturing the template from atleast three shooting angles. Errors of edge detection and line fitting are avoidedbecause the method does not require image matching. Thus the proposed methodcan reduce the calculation complexity and improve the precision of calibrationgreatly.An improved method for camera calibration based on circular points is alsoproposed. The vanishing points on four diametric directions are determined viaHarris corners on the template images. The image coordinates of circular pointsare calculated by the special r