基于支持向量机方法的车型分类

Vehicle Classification Based on Support Vector Machine

车型分类是交通流检测系统的子功能,也是智能交通系统(ITS)中的重要环节。支持向量机方法被看作是对传统学习分类方法的一个好的替代,特别在小样本、非线性情况下,具有较好的泛化性能。论文基于视频检测技术,采用支持向量机方法对车型分类进行了研究。实验表明,支持向量机方法能获得比神经网络方法更好的车型分类性能。

Vehicle Classification is a sub-function of the vehicle detection system,is also an important part of the intelligence transportation system （ ITS ） .Support Vector Machine approach is considered a good candidate because of its good generalization performance,especially when the number of training samples is very small and input space is nonlinear.This paper presents a study on the vehicle classification based on support vector machine.Experimental results indicate that the classification performance of support vector machine is better than that of neural networks.