基于支持向量机的车辆自动分类方法

SVM Based Method for Vehicle Automatic?classification

提出一种基于支持向量机(SupportVectorMachine,SVM)理论的车辆分类方法,通过CCD摄像机采集标准车辆图像,由边缘检测算法获取图像中的车辆特征数据长度和宽度作为训练样本,离线训练SVM,得到分离器,然后将测试车辆的特征数据作为测试样本,根据本文提出的分类方法,通过离线获得的分类器对车辆类型进行判决,从而为交通参数的准确检测提供依据。实验表明SVM在有限训练样本情况下具有良好的泛化能力。

This paper proposes a vehicle automatic?classification method based on SVM theoryFirstly,the standard vehicle images are captured from CCD camera,with the vehicle characteristic data of length and width obtained by using edge detecting algorithm as training samples to train Support Vector Machine(SVM) off?line,and the tested vehicle characteristic data of length and width as tested samples,then the vehicle type can be judged by means of the trained SVM according to the method proposed in this paperSo this can provide the basis for detecting traffic parameter accuratelyThe test shows the generalization ability of SVM under the conditions of limited training samples