###
:2019,28(11):213-217
←前一篇   |   后一篇→
本文二维码信息
码上扫一扫!
基于聚类与Hough变换的交通标志检测方法
(邢台学院 物理与电子工程学院, 邢台 054000)
Traffic Sign Detection Method Based on Clustering and Hough Transform
(Academy of Physics and Electrical Engineering, Xingtai University, Xingtai 054000, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 17次   下载 14
投稿时间:2019-04-11    修订日期:2019-05-08
中文摘要: 交通标志检测是进行交通标志识别系统的关键技术,提出一种基于图像的颜色和形状进行交通标志检测的方法.首先对图像进行灰度拉伸和噪声滤出的预处理,然后利用改进的K-means聚类算法对彩色图像进行颜色分割,最后采用基于Hough变换的形状检测技术对交通标志中的特殊形状进行定位,从而实现交通标志的检测.实验结果显示,该方法在各种复杂背景条件下检测出结果的平均正确率达到93.0%,优于同条件的算法且具有较高的实时性.
Abstract:The detection of traffic sign is the crucial technology of traffic sign recognition system. A method of traffic sign detection based on image color and shape is proposed. Firstly, the image is pre-processed by gray stretching and noise filtering, and then the color image is segmented by improved K-means clustering algorithm. Finally, the shape detection technology based on Hough transform is used to locate the special shape of traffic signs, so as to realize the detection of traffic signs. The experimental results show that the average accuracy of the detection results under various complex background conditions is 93.0%, which is better than other algorithms under the same conditions and has high real-time performance.
文章编号:     中图分类号:    文献标志码:
基金项目:邢台学院2018年度校级科研项目(XTXYB004)
引用文本:
苗丹,卢伟,高娇娇,李哲.基于聚类与Hough变换的交通标志检测方法.计算机系统应用,2019,28(11):213-217
MIAO Dan,LU Wei,GAO Jiao-Jiao,LI Zhe.Traffic Sign Detection Method Based on Clustering and Hough Transform.COMPUTER SYSTEMS APPLICATIONS,2019,28(11):213-217

用微信扫一扫

用微信扫一扫