基于数字图像处理的路面裂缝自动分类算法

发布时间：2018-03-06 21:35

本文选题：道路工程　切入点：路面裂缝　出处：《中国公路学报》2014年09期 　论文类型：期刊论文

【摘要】：为了充分掌握路面裂缝信息,给路面养护管理、路面性能评价与预测、路面结构和材料设计提供参考,对路面裂缝图像自动分类与严重程度识别进行研究。首先,将裂缝轮廓进行矢量化处理,从而分离出单个裂缝区域进行特征计算与分析,提取倾角、块度、空洞等新的裂缝几何特征;然后,选择裂缝分类特征(裂缝空洞、长宽比和倾角明显程度),基于统计阈值区分线性裂缝和网状裂缝;最后,分别根据倾角和宽度对线性裂缝进行分类和严重程度识别,根据块度特征识别块状裂缝、龟裂及其严重程度。结果表明:裂缝分类和严重程度识别结果准确有效,可在无人为干预的情况下准确、自动、实时地提取路面裂缝种类和严重程度信息。
[Abstract]:In order to fully grasp pavement crack information, to provide reference for pavement maintenance management, pavement performance evaluation and prediction, pavement structure and material design, automatic classification and severity recognition of pavement crack image are studied. The fracture contour is vectorized, and a single fracture area is separated for feature calculation and analysis, and new geometric features of fracture, such as dip angle, block degree, cavity and so on, are extracted, and then the fracture classification features (crack cavity, crack cavity, etc.) are selected. Based on the statistical threshold, linear fractures and reticular fractures are distinguished. Finally, the linear fractures are classified and the severity is identified according to the inclination angle and width, and the block fractures are identified according to the characteristics of block size. The results show that the classification of cracks and the recognition of severity are accurate and effective, and can be used to extract accurately, automatically and in real time information of pavement crack types and severity in the case of no one intervention.
【作者单位】：西南交通大学交通运输与物流学院;俄克拉荷马州立大学土木与环境工程学院;西南交通大学综合运输四川省重点实验室;西南交通大学综合交通运输智能化国家地方联合工程实验室;
【基金】：国家自然科学基金项目(51108391) 中央高校基本科研业务费专项资金项目(A0920502051208-99)
【分类号】：U418.6

【参考文献】