基于视频分析的车辆排队长度检测

Measurement of vehicle queue length based on video analysis

实现了一个完整的车辆排队长度检测算法,检测算法分为车辆排队检测和队列长度计算两步。对白天和夜晚不同光照条件采用不同的队列检测算法,并实现了白天夜晚检测算法的自动切换。在白天光照条件下,采用移动检测窗来进行车辆排队检测,在每一个检测窗内,通过三帧差法运动检测和形态学边缘检测进行车辆存在检测两步来判断有无车辆排队;针对夜晚场景,提出利用车灯这一显著特征进行车辆排队检测。以图像灰度直方图的相关系数作为距离值,利用KNN分类器进行白天夜晚的识别,实现检测算法的自动切换;队列长度计算通过摄像机标定完成,找到一种仅利用车道线的、简单有效的摄像机标定方法。实验表明该方法可以准确检测出车辆排队并计算出其长度,满足实时性要求。

Real-time measurement of vehicle queue parameters is required in many traffic situations.This paper achieved a complete vehicle queue length measurement system,consisted of vehicle queue detection and queue length measurement.It exploited different processing methods at daytime and nighttime,and used a KNN classification to switch detection methods between daytime and nighttime.At daytime,the queue detection algorithm consisted of vehicle motion detection and vehicle presence detection,and used a profile consisting of small profiles with variable sizes.In the night,achieved a novel queue detection method through detecting vehicle＇s headlights.And found a simple camera calibration method just using the geometry properties of road lane marking,then it could easily calculate the queue length.Experiment results indicate that the system can detect the vehicle queue and measure the queue length effectively.