基于支撑矢量机的路面破损识别  

Automation of recogniting pavement surface distress based on support vector machine

作　　者：丁爱玲[1] 焦李成[2] 

机构地区：[1]长安大学信息工程学院,陕西西安710064 [2]西安电子科技大学电子工程学院,陕西西安710071

出　　处：《长安大学学报（自然科学版）》2007年第2期34-37,共4页Journal of Chang’an University(Natural Science Edition)

基　　金：国家自然科学基金项目(60372047)

摘　　要：针对路面破损自动识别技术中的路面裂缝分类问题,提出了基于支撑矢量机(SVM)的路面破损裂缝分类方法,对于训练样本数很少的5种裂缝,建立了相应的支撑矢量机分类器算法,并分别构造了对应的分类器,根据最优分类面原则来获取最佳参数,确定出裂缝类型,从而实现对路面裂缝的正确分类。试验表明:4种破损路面的正确识别率均得到显著提高。In order to improve the accuracy and efficiency to identify the asphalt pavement surface distress by the image information, a novel support vector machine （SVM） is proposed. For the five types of pavement surface distress of limited training samples, the classification algorithm is founded, and the classifiers are established. According to the optimal hyperplane, the best parameters are obtained and pavement surface distress can be distilled and classified by those parameters. Experimental results show that the classification is well improved with this algorithm. 2 tabs, 1 fig, 10 refs.

关 键 词：道路工程 支撑矢量机 路面检测 破损识别 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]