棋盘格模板角点的自动识别与定位  

Auto-recognition and Auto-location of the Checkerboard Pattern Corners

作　　者：王忠石[1] 徐心和[2] 

机构地区：[1]沈阳大学信息工程学院,沈阳110044 [2]东北大学人工智能与机器人研究所,沈阳110004

出　　处：《中国图象图形学报》2007年第4期618-622,共5页Journal of Image and Graphics

摘　　要：棋盘格模板角点的识别与定位是摄像机定标过程中的关键环节,而自动识别与定位则是实现定标过程自动化的前提条件。为了实现定标过程自动化,提出了一种有效的方法,即利用棋盘格模板图像内部角点的局部灰度特征和由栅格线构成的结构特征,实现了内部角点的自动识别与定位。实验结果表明,该方法是有效和实用的,其能明显地加快定标速度,缩短定标时间,从而为基于多幅棋盘格模板图像的摄像机定标过程自动化创造了条件。Recognizing and locating the internal corners of a planar checkerboard pattern image is very important in camera calibration. An effective approach is proposed to automatically recognize and locate the internal target corners of the planar checkerboard pattern image based on the characteristics of the local intensity and the grid line. architecture. Experiments show that the approach obviously reduces the time cost for camera calibration, improves the speed of calibration process and is especially adapted for automatic calibration based on multiple images.

关 键 词：棋盘格模板 摄像机定标 角点检测 目标识别 

分 类 号：TP242.62[自动化与计算机技术—检测技术与自动化装置] TP391.41[自动化与计算机技术—控制科学与工程]