摘要
设计了一种基于DM642的嵌入式车辆检测系统.系统主要由CCD摄像头、TMS320DM642开发板和PC组成.对输入图像采用帧间差分法检测出运动区域,然后对运动区域进行Otsu阈值化、边缘检测及形态学滤波,准确提取运动车辆,利用交通参数提取算法计算车速和车流量.实验结果表明:该系统能实时提取道路交通信息,具有一定的实用性和推广价值.
A DM642-based embedded vehicle detection system has been designed and the system consists of CCD camera,TMS320DM642 development board and PC.Inter-frame difference method is used to detect the vehicle movement areas from input images,then,with the adoption of other algorithms such as Otsu,Edge detection and Morphological filtering,the movement of vehicles can be extracted exactly.Finally,the system can compute speed and traffic flow with the algorithm of traffic parameters extraction.Experimental results show that the system can real-timely obtain the information of the traffic flow,suggesting that this technique is worthy of consieration for practical application.
出处
《中南民族大学学报（自然科学版）》
CAS
2012年第1期84-87,共4页
Journal of South-Central University for Nationalities：Natural Science Edition
基金
湖北省自然科学基金资助项目(2010CDZ057)
关键词
帧间差法
边缘检测
形态学滤波
交通参数提取
inter-frame difference method
edge detection
morphological filtering
traffic parameters extraction
