Crack Automatic Detection of CCTV Video of Sewer Inspection with Low Resolution

In South Korea, sewage pipeline exploration devices have been developed using high resolution digital camera of 2 mega-pixels or above. However, most of the devices are less than 300 kilo-pixels due to poverty of the business. Moreover, since 100 kilo-pixels devices are widely used, environment for image processing is very poor. In this study, we adapted very low resolution (240 x 320 = 76,800 pixels) images by which it is difficult to detect cracks. Considering that images of sewers in South Korea have very low resolution, this study selected low resolution images to be investigated. An automatic crack detection technique has been studied using digital image processing technology for low resolution images of sewage pipeline. Authors have developed a program to automatically detect cracks as per eight steps based on MATLAB's functions. In this study, the third step covers an algorithm developed to find optimal threshold value, and the sixth step deals with algorithm to determine cracks. When we select [1.11:1.29] of zero padding range, exact detection rate is 89.2% and error rate is 4.44%. As the result, in spite of very low-resolution images, the performance of crack detection turned out to be excellent.