论文部分内容阅读
为实现桥梁裂缝检测的快速化和智能化,基于Matlab图像处理技术,提出一种非接触式的桥梁裂缝测定方法,其主要通过预先获取桥梁裂缝图像,采用图像灰度化和中值滤波去噪的方法对目标裂缝图像进行预处理,并通过多次腐蚀和膨胀操作,消除裂缝二值图像的边缘毛刺,最后调用Minboundrect函数对目标裂缝图像进行精确测定。结果表明:所选裂缝样本点的宽度尺寸测定值与真值间的相对误差满足工程要求。
In order to realize the quick and intelligent detection of bridge crack, based on the Matlab image processing technology, a non-contact bridge crack detection method is proposed. The bridge crack image is obtained in advance, and the image gray and median filter The target image was preprocessed. After multiple erosion and expansion operations, the edge burr of the binary image of the crack was eliminated. Finally, the Minboundrect function was used to measure the target crack accurately. The results show that the relative error between the measured value and the true value of the selected crack sample point meets the engineering requirements.