轿车局部区域特征提取与车型识别

Feature Extraction of Car Local Aera and Vehicle Recognition

车型识别技术是智能交通管理系统的关键技术之一。目前车型识别多基于车牌及整体外形的识别技术。基于此提出从轿车图像提取局部信息,从而快速、准确的识别出轿车车型。主要研究轿车尾灯特征提取,并在此基础上进行轿车分类识别。采用变分水平集方法对轿车图像进行分割,获得描述尾灯区域特征的三个特征参数——宽高比、矩形度、分散度作为支持向量机的分类的输入特征向量,对31种不同车型进行分类与识别,准确率达到100%。此研究表明利用轿车的局部特征也能够达到轿车车型识别的效果,具有较高的应用价值。

This paper studies feature extraction of car tail light,wihich is the basis of identification of cars.A variational level set approach is used to segment the image of car＇s back section and extracte car tail light,and get the three parameters（width-to-depth ratio,rectangle,dispersion） of car tail light area,which are as the supporting vector machine＇s input feature vector to discern car model,The experiment results show that recognition accurate rate can reach 100 percent for as many as 31 various models.