智能视觉在交通流量监测的应用  

Application of Intelligent Vision in Traffic Flow Monitoring

作　　者：董大明[1] DONG Daming(Shanxi Jiaotong Vocational and Technical College,Shanxi 030031,China)

机构地区：[1]山西交通职业技术学院,山西030031

出　　处：《集成电路应用》2020年第8期150-151,共2页Application of IC

摘　　要：针对运动车辆图像中存在的车辆与路面色差问题,提出了一种基于视觉检测技术的在线交通状态监测分析方法。首先对视频进行10帧/s的采样。利用相邻两幅图像在同一区域的差分运算,在测量带上快速检测运动车辆。然后对差分结果进行灰度化处理,采用直方图均衡化和二值化方法对运动车辆和车辆类型进行统计识别。结果表明,该系统非常方便、准确、快速,正确识别率达96%。与相位控制相结合的道路控制,可以通过在线智能引导交通,满足实际应用的要求。Aiming at the problem of color difference between vehicle and road in moving vehicle image,this paper proposes an online traffic condition monitoring and analysis method based on visual detection technology.It samples the video at 10 frames per second.By using the difference operation of two adjacent images in the same region,the moving vehicle can be quickly detected on the measurement band.The difference results are grayed out,and the moving vehicles and vehicle types are identified by histogram equalization and binarization.The results show that the system is very convenient,accurate and fast,and the correct recognition rate is 96%.The road control combined with phase control can guide the traffic on line intelligently to meet the requirements of practical application.

关 键 词：智能交通系统 在线测量系统 视觉检测 交通流 城市高速公路 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] U495[自动化与计算机技术—计算机科学与技术]