A novel asphalt pavement crack detection algorithm based on multi-feature test of cross-section image

This paper attempts to overcome the difficulties in crack detection by cross-section images arising from low contrast and complex pavement texture. For this purpose. a crack detection algorithm was proposed through the multi-feature test of cross-sect ion image. Firstly, the crack image was subjected to dimension reduction, gray scale correction and filtering. After that, the crack section was determined in the processed crack image through the tests on multiple features, namely, inclination, Gaussian distribution and edge gradient. Finally, the proposed algorithm was applied to detect the cracks on actual asphalt pavement. The results show that our algorithm can achieve a high accuracy in the detection process.