Abstract: Checkerboard images are widely used in camera calibration and vision measurement，so a novel fast algorithm for detecting checkerboard corners is proposed to solve the problems of present corner detection algorithms.The algorithm is based on the characters of transition region and gray level distribution；and it uses loop detection method.Simulation and real teat results show that the algorithm is real-time and robust to rotation，intensity change and edge blur.In comparison with Harris，the algorithm is easier to realize，and the computation is smaller.

Key words: checkerboard image, corners, fast detection, Harris algorithm

摘要： 棋盘格图像在摄像机标定及视觉检测中有着广泛的应用。针对目前棋盘格图像角点检测的局限性，提出了一种棋盘格图像角点快速检测方法。该方法是利用存在过渡区和角点处灰度分布的独特性质，设计了环形检测方法。仿真及实测实验结果表明：该方法实时性强，对棋盘格图像的旋转变换、亮度变换和边缘模糊具有良好的适应性；与经典Harris角点检测算法相比，易于实现、计算量小。

关键词: 棋盘格, 角点, 快速检测, Harris算法