Research on pavement crack detection algorithm in complex background

Abstract

Cracks are the most common diseases of highway pavement, which affect the safe operation of highway. Therefore, timely and effective detection and maintenance of cracks in highway pavement is essential. The existing pavement crack detection methods are mainly based on the condition that the image quality is good, the pavement is clean, and the image has no shadow. But in the actual situation, the background of the pavement image is complex. Therefore, it is necessary to conduct in-depth research on pavement crack detection under complex background. The pavement cracks under complex background are characterized by uneven illumination, more interference noise and weak crack information. In this paper, a pavement crack image enhancement algorithm based on luminance region is proposed, which is used to eliminate the shadows on the pavement image, and then the maximum entropy threshold segmentation algorithm is used to extract the cracks on the pavement image. The experimental results show that the algorithm can accurately detect cracks on shadowed pavement.