一种新的白点定位图像处理算法  

A New Image Processing Algorithm of White Points Location

作　　者：吴晓[1] 曹其新[1] 

机构地区：[1]上海交通大学机器人研究所,上海200030

出　　处：《西南科技大学学报》2008年第3期71-75,共5页Journal of Southwest University of Science and Technology

基　　金：国家自然科学基金资助项目(60443007)

摘　　要：白点定位是求解足球机器人坐标的关键步骤。通过分析以往的定位方法的优缺点,提出了一种基于沿预定义径向线求梯度亚像素定白点的新方法,并在足球机器人视觉系统中进行了实验。实验结果表明该方法既在一定的程度上降低了噪声干扰的影响,又避免了逐个像素求解边界及中点,降低了计算量,从而提高了系统的实时性和可靠性。The white points localization is a key step to solve soccer robot serf-localization. A new method was proposed, in which white lines＇ gradient information based on search along predefined radial scanlines and subpixel were applied simultaneously, and this method was also used in the experiment of the soccer robot. The experiments show that the new method reduces not only the noise interference but also the amount of calculation by avoiding computation of the boundary and middle point pixel by pixel, which can considerably enhance the real-time performance and the reliability of the vision system of soccer robot for MSRL.

关 键 词：白点定位 图像处理 亚像素边缘检测 足球机器人 

分 类 号：TP242[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]