首页 | 本学科首页   官方微博 | 高级检索  
     

结合信号配准技术的小波多尺度车辆边缘检测方法
引用本文:连静,王珂,杨兆升. 结合信号配准技术的小波多尺度车辆边缘检测方法[J]. 中国公路学报, 2007, 20(5): 95-100
作者姓名:连静  王珂  杨兆升
作者单位:1. 吉林大学,通信工程学院,吉林,长春,130025
2. 吉林大学,交通学院,吉林,长春,130025
基金项目:国家自然科学基金;吉林省科技发展计划
摘    要:为了在准确检测边缘的同时有效地抑制噪声,提出了结合信号配准技术的小波多尺度边缘检测方法。该方法首先基于小波变换的特点设计小波多尺度边缘检测算法检测图像边缘;而后结合信号配准技术将不连续的边缘连接为完整的边缘轮廓,减弱由噪声或干扰造成的影响。试验结果表明:该方法不仅能准确检测出清晰连续的边缘图像,而且能有效抑制噪声,是边缘检测的实用方法。

关 键 词:交通工程  车辆识别  小波变换  边缘检测  信号配准
文章编号:1001-7372(2007)05-0095-06
收稿时间:2007-01-10
修稿时间:2007-01-10

Method of Wavelet Multi-scale Vehicle Edge Detection Combined with Signal Registration Technology
LIAN Jing,WANG Ke,YANG Zhao-sheng. Method of Wavelet Multi-scale Vehicle Edge Detection Combined with Signal Registration Technology[J]. China Journal of Highway and Transport, 2007, 20(5): 95-100
Authors:LIAN Jing  WANG Ke  YANG Zhao-sheng
Affiliation:1. School of Communication Engineering, Jilin University, Changchun 130025, Jilin, China 2. School of Transportation, Jilin University, Changchun 130025, Jilin, China
Abstract:In order to detect edges correctly while noise can be effectively restrained,wavelet multi-scale edge detection method with signal registration technology was proposed.The method firstly was used to design wavelet multi-scale edge detection algorithm to detect image edges based on the characteristic of wavelet transformation.Then,the discontinuous edges were connected into a contour line with signal registration technology to weaken the influence of noise or disturbance.The experimental results show that the method can not only precisely detect clear and continuous edge images,but also can effectively restrain noise,and is a practical edge detection algorithm.
Keywords:traffic engineering  vehicle recognition  wavelet transformation  edge detection  signal registration
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号