摘要： 系统利用视频检测线上的ＲＧＢ灰度变化识别车辆，从而完成对车辆流量的检测。由于引入了动态投影技术，并由动态投影图得到特征值的波形，因此特征提取中灰度差阈值的确定变得直观而可靠。为了保证背景信号的真实性，系统采用了和背景变化相对应的背景刷新技术。系统的识别正确率可达９０％以上，能满足实际应用要求。

关键词: 智能交通系统, 车辆流量检测, 动态投影, 特征提取

Abstract: In this paper, we propose a new scheme for vehicle flow measuring which recognizes the vehicle by the RGB gray scale variation on the video measuring lines. Because of the adopting of the dynamic projecting technology, we can get the feature curves from the dynamic projection picture, which make the determination of the gray scale difference threshold illustratively and reliably. For the validity of the background values, we adopt a new background refresh strategy corresponding to the background changing. The recognition rate of the system can reach over 90%. The measuring system can meet the demand of the practical application.

中图分类号: 

• TP274.2