Development of new automated crack measurement algorithm using laser images of pavement surface

Over the years, many Automated Image Collection Systems (AICS) have been developed to capture pavement images. The cameras used by most of the AICS are based on Charge-Coupled Device (CCD) image sensors where visible ray is projected. However, the quality of the images captured by the CCD cameras was limited by the inconsistent illumination and shadows caused by sunlight. To enhance the CCD image quality, a high-power artificial lighting system has been used, which required a complicated strobe lighting system and a significant power source. Recently, Laser Road Imaging System (LRIS) was introduced which captures images without a shadow under an invisible laser frequency. The images captured using the LRIS were very sharp and did not present any shadow but, due to a high contrast of pavement surface, it resulted in a higher amount of background noises. The main purpose of this study is to present a new automated crack measurement algorithm to accurately analyze the laser images collected using LRIS. The new algorithm suppresses the background noises while enhancing crack images based on the unique characteristics of the laser image. Based on the limited set of laser images, the proposed algorithm is more accurate than a typical thresholding method with a relative precision up to 87.3%.