一种基于改进渗流模型的混凝土表面裂缝快速检测算法

Algorithm of Accelerated Cracks Detection Based on Improved Percolation Model in Concrete Surface Image

由于混凝土表面不平整、光照不均、裂缝背景较为复杂等因素的干扰,传统的基于图像处理的裂缝检测方法对裂缝检测的效果不佳,尤其是不清晰和比较细小的裂缝。基于渗流模型的裂缝检测方法充分考虑了裂缝亮度低、形状较为细长的特点,对裂缝的检测效果很好,尤其是图像中的细小裂缝,但是该方法需要大量的处理时间。为了解决上述问题,提出了一种加速渗流处理的算法,该算法通过暗点预提取来减少渗流时需要处理的像素点个数,以此来减少渗流处理时间。实验结果表明,所提算法能明显加快渗流处理的速度,并且精确率基本保持不变。

Due to concrete surface roughness, uneven illumination, shadows, complex background and other disruptive factors, the traditional concrete crack detection method based on image processing cannot accurately detect concrete cracks, especially unclear cracks and some tiny cracks. Crack detection method based on percolation model which fully considered the low brightness and slenderness features of cracks can accurately detect unclear and tiny cracks. But this method is time-consuming. In order to solve these problems, an improved algorithm of image crack inspection based on percolation model was proposed in the article,which can reduce processing time through reducing the number of perco- lated pixels. Experimental results show that the proposed algorithm in this article can significantly accelerate crack de- tection and maintain a high detection precision.