Three-dimensional pavement disease PCI calculation methodbased on graph-point-graph transformation

Abstract

The invention relates to a three-dimensional pavement disease PCI calculation method based on graph-point-graph transformation. The calculation method can directly calculate a three-dimensional pavement disease PCI through an RGB image, three-dimensional disease image screening is realized through a GA-CNN network, the RGB image is converted into a gray mapping graph containing distance information through the graph-point-graph transformation, the three-dimensional features of the three-dimensional disease are extracted by processing the two-dimensional gray mapping graph, and damage grading and PCI calculation are carried out. According to the calculation method, the two-dimensional image is recognized in the whole process, a large amount of calculation time and calculation power are saved compared with three-dimensional network processing of three-dimensional data, the workload is reduced by setting the GA-CNN algorithm, an accurate volume calculation mode is given, the gray mapping image generation precision is higher, the submillimeter pixel precision can be achieved, and rapid identification of three-dimensional disease types, accurate extraction of disease three-dimensional morphological characteristics and efficient grading of disease damage degrees are realized.

Description

technical field [0001] The invention relates to a PCI calculation method for three-dimensional pavement damage based on graph-point-graph transformation. Background technique [0002] In order to ensure the safe driving of vehicles on the road and prolong the service life of the road, it is necessary to regularly inspect and maintain the road. The pavement performance index has decisive significance for the decision-making of the pavement maintenance plan, so the calculation of the pavement performance index is very necessary. Pavement Condition Index (PCI) is an index for evaluating the damage degree of road pavement, which integrates the quantitative status of three aspects: damage type; damage degree; damage range or density, etc., and uses the deduction method for analysis. Pavement damage evaluation and maintenance decision analysis are shown in Table 1: [0003] [0004] The type of disease, the degree of damage and the damage range (area) of the disease are the th...

AI Technical Summary

Problems solved by technology

For the method of manual identification and measurement of diseases, the detection even needs to close the road, which will consume a lot of manpower, material and financial resources, and the detection efficiency is difficult to guarantee

Manual detection is easily affected by subjective judgment and lacks consistent judgment standards

The acquisition equipment such as laser or radar carried by the road inspection vehicle is expensive, and the collected data is distance information, which cannot realize the calculation of the road damage index

Traditional digital graphics can only obtain texture information of pavement damage, but cannot obtain high-precision three-dimensional damage depth, damage volume and other three-dimensional features of damage. At present, there is no high-precision identification of three-dimensional damage and extraction of three-dimensional damage features and calculation of road surface through digital images. Actionable Methodology for Condition Index (PCI)

Images