摘要
摄像机标定是机器视觉的基本任务之一,首先对开源计算机视觉(OpenCV)库进行介绍,然后给出了摄像机模型和摄像机标定过程中的坐标系转换关系。对图像模板的标定采用基于成像模型的点对应关系和在线实时标定的方法,同时把非线性畸变考虑在内,获得摄像机内外参数。标定结果初步应用于移动机器人平台的视觉伺服实验,对三维目标测量,实验结果表明了标定方法的可行性。
Camera calibration is one of the basic tasks in machine vision. Open source computer vision （OpenCV） library is introduced first, then camera model and coordinates transformation in camera calibration are given. Online real-time calibration and model-based point-objected relationship are used to calibration of the image, with distortion coefficients into consideration to achieve intrinsic and extrinsic parameters of the camera. The calibration result is used to measure the 3D object and experiment in the mobile robots platform. The analysis result validates feasibility of the calibration method.
出处
《计算机工程与设计》
CSCD
北大核心
2009年第16期3856-3858,3862,共4页
Computer Engineering and Design
基金
国家自然科学基金项目(60474009)
上海市曙光计划基金项目(05SG48)
上海市教委科研基金项目(F07zz90)
