基于距离约束的随机Hough变换直线检测算法  

Random Hough Transform Lines Detection Based on the Distance Constraint

作　　者：曾接贤[1] 王斌斌[1] 陈志良[1] 

机构地区：[1]南昌航空大学,江西南昌330063

出　　处：《南昌航空大学学报（自然科学版）》2011年第3期7-11,共5页Journal of Nanchang Hangkong University(Natural Sciences)

基　　金：国家自然科学基金(61165011);江西省自然科学基金(2008GZS0034);航空科学基金(20085556017&2010ZC56006)

摘　　要：从图像中提取直线是图像处理中基本而又重要的任务。Hough变换是提取直线的经典算法。针对随机Hough变换(RHT)存在无效采样和无效累积等问题,提出了一种基于距离约束的随机Hough变换直线检测算法。该算法在随机Hough变换选择点对时,先判断这两点是否满足某一距离约束条件,从而确定是否将其变换到参数空间;然后在参数空间中判断直线的存在性。通过理论分析和实验表明,本算法具有低内存、速度快等优点。Lines detection is the basic and important task for the image processing.Hough transform is the classical algorithm of the lines detection.Aiming at invalid sampling and cumulative problems of the random Hough transform（RHT）,a method for random Hough transform lines detection based on the distance constraint is presented.The method is as follows： when selecting two points with the random Hough transform,we judge whether the two points meet a distance constraint,and determine whether to convert the two points to the parameter space;and then judge the existence of straight line in the parameter space.The theoretical analysis and experiment results demonstrate that the algorithm has low memory and fast speed.

关 键 词：图像处理 距离约束 随机霍夫变换 直线检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]