基于Hough变换的车轮定位方法  

A Localization Method of Vehicle Wheels Based on Hough Transform

作　　者：王红亮[1] 黄洋文[1] 李健楠[2] 

机构地区：[1]中北大学电子测试技术国家重点实验室仪器科学与动态测试教育部重点实验室,太原030051 [2]东南大学仪器科学与工程学院,南京210096

出　　处：《火力与指挥控制》2011年第11期25-27,共3页Fire Control & Command Control

基　　金：国家自然科学基金资助项目(60871041)

摘　　要：提出了一种基于Hough变换的车轮定位方法,主要针对道路上车辆目标侧面图像进行车轮检测定位,为车型识别提供重要的几何特征参数。首先通过中值滤波、Sobel边缘检测、阈值分割和边缘细化等算法进行图像预处理,然后使用两步Hough变换圆检测算法对两车轮分别进行检测定位。实验结果表明,本方法能准确地定位出车辆目标的两车轮位置,且具有较强的鲁棒性,并成功应用于某车辆识别系统。In this paper,a localization method of vehicle wheels is proposed,and this method is based on the Hough transform of the vehicle＇s sideway images,providing some important parameters for vehicle calssification.First,some image pre-processing techniques are applied,such as median filtering,Sobel edge detecting,thresholding and edge detecting.Then the localization is implemented by the method of two-steps Hough transform to decide whether the input figure is a circle.Experimental results show that this method can accurately locate the two wheels of the vehicle with strong robustness.This method has been successfully applied in a vehicle identification system.

关 键 词：车轮定位 HOUGH变换 边缘细化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]