基于数字图像的水泥混凝土路面嵌缝料损坏识别  

Recognition on Joint Sealant Rupture of Cement Concrete Pavement Based on Digital Image

作　　者：马正军[1] 英红[2] 付琴 谈至明[1] 陈智杰 

机构地区：[1]同济大学道路与交通工程教育部重点实验室,上海201804 [2]桂林电子科技大学建筑与交通工程学院,广西桂林541004 [3]广西交通投资集团有限公司,广西南宁530028

出　　处：《建筑材料学报》2013年第2期349-353,359,共6页Journal of Building Materials

基　　金：国家自然科学基金资助项目(51208130);西部交通建设科技项目(2007 318 223 01-9)

摘　　要：针对目前水泥混凝土路面嵌缝料损坏评价方法的不足,提出了1种基于数字图像的水泥混凝土路面嵌缝料损坏识别方法.该方法根据水泥混凝土路面接缝图像特征对接缝进行定位,并根据嵌缝料损坏图像特征对嵌缝料损坏进行分类.接缝定位主要有2个步骤,一是基于灰度投影的粗定位,二是在粗定位的基础上提取接缝附近图像,利用灰度投影和边缘投影进行精定位.嵌缝料损坏分类过程中,提取了空隙相对宽度、空隙相对位置、空隙外接矩形相对宽度和空隙投影相对值4个特征,并由BP神经网络和线性直接判别式法构成分类器.试验表明,上述方法对水泥混凝土路面嵌缝料损坏识别正确率达到94%.To overcome the shortcomings of traditional methods for joint sealant rupture evaluation, a new method for recognition joint sealant rupture of cement concrete paveoaent based on digital image was pro posed. Based on the digital image processing in accordance with the joint feature,the slab joints can be po sitioned. The joint sealant rupture can be classified by pattern recognition according to the feature of ima ges of joint sealant rupture. Joint positioning was divided into two main steps：approximate location based on the gray projection feature of who/e image and accurate location based on the character of gray projec tion and edge projection around the joints image. In the process of pattern recognition, the features inclu ding the relative width of joint sealant interspace, the relative location of joint sealant interspace, the rela tive width of outer rectangle of joint sealant interspace and the relative projection value of joint sealant in terspace were extracted from the digital images. BP network and linear discriminant were adopted for the classification. The experimental results show that accuracy of recognition on joint sealant rupture of cement concrete pavement reaches 94%.

关 键 词：水泥混凝土路面 嵌缝料 接缝定位 模式识别 数字图像 

分 类 号：U414.0[交通运输工程—道路与铁道工程]