基于计算机视觉技术的结构表面裂缝检测方法研究

计算机视觉技术用于混凝土结构表面裂缝检测，具有现场检测方便、效率高、客观性强的特点，但图像数据分析是该技术的核心，其中裂缝提取与定量测量较为复杂。为提高裂缝图像处理效率和准确率，将深度学习和数字图像处理技术相结合，提出一种裂缝检测方法。建立基于深度卷积神经网络的裂缝识别模型，在图像上自动定位裂缝并结合图像局域阈值分割方法提取裂缝。在裂缝宽度定量测量方面，采用双边滤波算法和三段线性变换对裂缝图像进行预处理，提高了裂缝边缘识别的精确度。通过改进边缘梯度法，实现裂缝最大宽度的定位和裂缝最大宽度的自动获取。该研究为全自动识别裂缝图像及高精度测量裂缝宽度提供了一种解决方法。

Structural surface crack detection method based on computer vision technology

The application of computer vision technology to the surface crack detection of concrete structure is a new detection method, which has the characteristics of convenient site detection, high efficiency and strong objectivity. The image data analysis is the core of the technology, and image processing and crack detection are complex. In order to improve the efficiency and accuracy of image processing, a method based on deep learning and digital image processing is proposed in this paper. The deep convolution neural network (CNN) is used to establish the crack recognition model. The cracks are automatically located on the image and the image local threshold segmentation method is used to extract the cracks. For the measurement of crack width, the bilateral filtering algorithm and the three segment linear transformation are used to preprocess the crack image to improve the accuracy of crack edge recognition. By improving the edge gradient method, the maximum width of cracks can be located and the maximum width of cracks can be automatically acquired. This study provides a solution to automatic identification of crack images and quantitative measurement of crack width.