Concrete crack quick recognition method

Abstract

The invention discloses a concrete crack quick recognition method. According to the method, in a to-be-detected concrete grayscale image, one pixel is taken at the interval of w rows and w columns toform a downsampling image with a reduced size; morphological opening operation is performed on the downsampling image to suppress the influence of brightness value isolated points on subsequent imageprocessing; grayscale clustering is performed on the downsampling image obtained after noise suppression, the pixels with approximate grayscales in the image are included into one type; all grayscalevalues of the type of pixels with a minimum center grayscale in the downsampling image obtained after noise suppression are set as 1, grayscale values of other pixels are set as 0, and a clustering result binary image is generated; and information entropy of the clustering result binary image is calculated, and whether cracks exist in the to-be-detected concrete image is judged according to the binary image entropy criterion. Through the method, collected concrete images can be quickly divided into crack images and non-crack images, so that the difficulty and time consumption in a subsequent crack extraction step are substantially lowered.

Description

technical field [0001] The invention relates to the technical field of computer vision detection, in particular to a method for quickly identifying cracks in concrete. Background technique [0002] To ensure the safety and performance of concrete infrastructure, it requires continuous condition monitoring and performance assessment. At present, the condition monitoring and performance evaluation of concrete facilities are mainly realized through manual inspection. With the continuous development of social economy, the mileage of concrete bridges and roads in countries around the world is getting longer and longer, and there are more and more concrete buildings. Manual inspection is not only costly, but also difficult to meet the requirements of a large number of concrete facilities. The need for continuous monitoring. [0003] Concrete facilities will produce cracks during use. Too wide cracks will not only affect the appearance of concrete facilities, but also cause corro...

AI Technical Summary

Problems solved by technology

However, the focus of these new methods is to accurately extract cracks from cracked images. In practical applications, pseudo cracks may be extracted from crack-free images after a large number of calculations, which is not suitable for crack-free image processing. In addition, these Most of the new methods require more computing time, and if all the collected concrete images are processed, the detection efficiency will be seriously affected

Images