基于支持向量机的视频交通信息采集研究

Video Detection of Traffic Information Based on Support Vector Machines

提出一种基于支持向量机的视频交通信息采集的设计方案。通过对视频交通流的采集、处理和分析,获取所需样本数据,采用导师训练方法训练支持向量机识别器。最后利用获得的识别器判断检测区域内交通流图像的类别,从而动态跟踪车辆,实现交通流量、车速、车型信息的采集。

A new method to detect video traffic information based on the theory of support vector machines is presented. Through processing and analyzing the traffic flow images, sample data are gathered. Then the SVM （support vector machines） classifiers are used to classify the traffic flow images in detection area and traces vehicles to get the information of passing vehicle count, vehicle speed and vehicle types.