Automatic identification method for asphalt pavement crack types

Abstract

The invention provides an automatic identification method for asphalt pavement crack types. The automatic identification method comprises the steps that a crack image is extracted from a pavement image, several adjacent sections of cracks are connected into a crack binary image with a connected domain, the connected domain is subjected to grid dividing, and then the cracks are gradually identified; the two major types of cracks, that is, transverse cracks or longitudinal cracks as well as block-shaped cracks or chaps are accurately divided and identified at first; the types of the transverse cracks and the types of the longitudinal cracks are accurately identified; the types of the block-shaped cracks and the types of the chaps are accurately identified; the lengths of the transverse cracks or the lengths of the longitudinal cracks are worked out; the areas of the block-shaped cracks or the areas of the chaps are worked out; and the crack damage severity degree is judged. The pavement distress identification accuracy rate can be effectively increased; the pavement distress detection false identification rate is decreased; the automatic identification method is not affected by the pavement weather conditions; the all-weather working capability is achieved; and meanwhile, the detection speed and the detection efficiency are high, the interference to the traffic is avoided, and good economic and social benefits are brought.

Description

technical field [0001] The present invention relates to the measurement of irregular surfaces or contours in IPC classification or E01C23 / 00 auxiliary technology for repairing or removing road pavement, especially the automatic identification method of asphalt pavement crack type. Background technique [0002] Asphalt pavement is widely used on highways because of its short initial maintenance period, comfortable driving, convenient maintenance, low noise and good skid resistance. Asphalt pavement is prone to various diseases due to various reasons. If it is not treated in time, it will affect the operation of the road and thus affect the economic development. Therefore, it is particularly important to analyze and control the causes of pavement diseases. [0003] Pavement damage is divided into functional attenuation and structural damage. Functional attenuation is manifested in the decrease of pavement service ability, smoothness and anti-skid performance. Damage that le...

AI Technical Summary

Problems solved by technology

[0011] 1), poor robustness

Cracks on asphalt pavement often have discontinuity, and the crack image extracted from the pavement image will also show discontinuity due to various interferences, so the calculation results based on the ideal state deviate greatly from the actual situation

[0012] 2) The identification error between planar cracks and linear cracks such as massive cracks or cracks is relatively large

[0017] The above-mentioned quantitative evaluation method and quality evaluation method are not specifically aimed at the transverse cracks of expressway asphalt pavement, but only conduct qualitative analysis, or only evaluate a certain aspect of cracks, such as crack rate, and only evaluate from the affected area of ​​cracks , it is impossible to clarify the distribution of cracks on the pavement, and it cannot fully reflect the degree of influence of transverse cracks on the quality of the pavement, which has certain limitations

Because its results are not comprehensive and intuitive enough, it is difficult to apply directly in actual engineering

Images