桥梁混凝土结构表面裂缝自动识别技术研究

Study of Automatic Identification Technology for Surface Cracks in Bridge Concrete Structures

为了满足桥梁检测发展的需求,提高混凝土结构表面裂缝的识别精度,基于既有图像预处理技术,提出一种新的裂缝提取及宽度计算方法。在图像预处理基础上,通过裂缝连接保留细小裂缝,将裂缝区域当作连通区域,根据裂缝特征参数过滤虚假裂缝,提取真实裂缝;寻找裂缝区域的交叉点,通过交叉点将整个裂缝区域划分成多个小裂缝,将小裂缝的最小外接矩形分割成多个小矩形区域,计算小矩形区域中裂缝特征参数,得到裂缝宽度。以混凝土试件重力加载形成的表面裂缝为对象,改变相机拍摄距离与拍摄倾斜角度获取裂缝图像,应用该方法计算裂缝宽度,并与裂缝观测仪的测量结果进行误差对比分析。结果表明:该算法裂缝识别率高、检测误差小,裂缝检测误差随拍摄距离或拍摄倾斜角度的增大而增大;为了满足实际工程的需要,采集裂缝图像时,拍摄距离最好保持在1m以内,倾斜角度尽量不要超过15°。

To meet the demands of bridge inspection development and improve the identifica-tion accuracy of surface cracks in concrete structures, a new type of cracks pick-up and width cal-culation method based on image pre-processing technique is proposed. On the basis of image pre-processing ,tiny cracks are reserved via crack connection, and the cracking zone is taken as the connection zone, and the fake cracks are filtered according to the eigen parameters of the cracks, aiming to pick up the real cracks. The intersections in the cracking zone are found, and by which the cracking zone is divided into many tiny cracks. The smallest external rectangle of the tiny cracks is divided into many small rectangular zones and the eigen values of cracks in these zones are calculated to gain the crack widths. The surface cracks in the concrete samples induced by gravity loading were taken as examples. The images of the cracks were gained by changing the photograp-hing distance and inclination angle. The method mentioned was used to calculate the widths of cracks, and error comparisons were done between the calculating results and the results gained by the crack visualization. The results show that this method has the advantages of high crack identi-fication rate and minor inspection error. The crack inspection error increases as the photographing distance and inclination angle becomes bigger. To suit the actual projects, the photographing dis-tance is better to set within one meter and the inclination angle won＇t surpass 15° when collecting the crack images.