摘要
车辆或道路的边缘是灰度视频交通图像的重要特征,文章采用细胞神经网络技术,合理地选择了网络参数,并编制了基于Matlab5.3平台的程序,将其用于检测灰度交通图像的边缘。经算例与传统的Sobel方法进行比较,证明采用该方法提取交通图像边缘是有效的,实用的,并通过分析推荐了网络参数。
The edges of vehicles or roads are important characteristics of grayscale video traffic images. Cellular neural network (CNN) is a large-scale nonlinear analog circuit suitable for realtime signal and image processing. In this paper, the CNN technology is applied in order to detect the edges of traffic images, Programs are composed based on MATLAB 5. 3 and applied to accomplishing the purpose. A comparative processing using the classical Sobel method is conducted in order to validate the effect of this method. The results show that the CNN method is effective. In addition, appropriate network parameters are proposed.
出处
《交通与计算机》
2005年第4期28-31,共4页
Computer and Communications
关键词
边缘检测
细胞神经网络
灰度
交通图像
模板
edge detection
cellular neural network
grayscale
traffic image
template