利用梯度方向信息的随机Hough变换  

A RANDOMIZED HOUGH TRANSFORM USING GRADIENT DIRECTION INFORMATION

作　　者：陈燕新[1] 戚飞虎[1] 

机构地区：[1]上海交通大学计算机科学与工程系

出　　处：《红外与毫米波学报》1998年第5期375-380,共6页Journal of Infrared and Millimeter Waves

基　　金：国防预研基金

摘　　要：针对随机Ｈｏｕｇｈ变换（ＲＨＴ）在处理复杂图像时随机采样造成的大量无效累积提出一种改进的用于直线检测的ＲＨＴ，较好地解决了无效累积问题，并使改进后的算法具有计算速度更快。To solve the problem of a large amount of useless accumulations yielded by random sampling by means of the randomized Hough transform (RHT)in handling complex images,an improved RHT used to detect lines was proposed. It uses gradient direction information, not only can well solve the problem of useless accumulations, but also has higher speed ,smaller storage and better detection performance.

关 键 词：随机HOUGH变换 直线检测 梯度方向信息 RHT 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]