基于色彩特征的CAMSHIFT视频图像汽车流量检测  

Vehicle flow detection with CAMSHIFT video images based on color feature

作　　者：陈向东[1] 李平[2] 

机构地区：[1]黄淮学院国际学院,河南驻马店463000 [2]黄淮学院信息工程学院,河南驻马店463000

出　　处：《沈阳工业大学学报》2015年第2期183-188,共6页Journal of Shenyang University of Technology

基　　金：河南省科技攻关基金资助项目(122102210549;132102210423)

摘　　要：针对视频图像中目标车辆尾灯及背景色彩在HSV空间分布上的特点,提出了把车辆尾灯作为跟踪目标,恰当选取色彩特征参数,采用CAMSHIFT目标跟踪算法对汽车流量进行检测的技术方案.研究了基于HSV色彩空间的CAMSHIFT目标跟踪算法在视频图像汽车流量检测中的实现,并用实际拍摄的交通视频图像对该检测算法进行了验证.实验结果表明,本文算法具有较高的准确度,能够有效跟踪以各种速度行驶的车辆,可以较好地应用在汽车流量检测领域中.Aiming at the HSV space distribution features of vehicle tail lights and background color in video images,a technological scheme for the detection of vehicle flowwith the CAM SHIFT target tracking algorithm through taking the tail lights as the tracking target and appropriately choosing the color feature parameters was proposed. The realization of CAM SHIFT tracking algorithm for the detection of vehicle flowwith the video images based on the HSV color space was studied. In addition,the proposed detection algorithm was verified by the actual traffic video images. The experimental results showthat the proposed algorithm has higher accuracy,may effectively track the vehicles at any speed and can be well applied in the vehicle flowdetection field.

关 键 词：公路运输 汽车流量检测 自适应均值移动 目标跟踪 色彩空间 色彩直方图 道路背景 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]