Road surface crack growth detection method based on historical crack data

Abstract

The invention discloses a road surface crack growth detection method based on historical crack data, and the method comprises the steps: carrying out the initial positioning through a GPS, and extracting a plurality of similar images which are close to a current road surface image through the comparison of the current positioning information and the position information in historical map data; carrying out image-level positioning,carrying out feature point matching to obtain finely matched image data in a plurality of similar images close to the current road surface image; carrying out pixel-level positioning, calculating an H matrix through image feature points matched with ORB,, and mapping historical mark crack pixels to a current crack image through the H matrix; and analyzing distribution of historical crack pixels mapped in the current crack image based on the historical cracks of the RGM, representing intensity distribution of the mapped crack pixels by using a Gaussian model, and finally dividing pixel values meeting conditions into cracks. According to the method, by referring to historical crack data, an effective and reliable strategy for researching the change of the crack state along with time is provided, and crack detection and recognition are greatly simplified and improved.

Description

technical field [0001] The invention relates to image processing technology, in particular to a pavement crack growth detection method based on historical crack data. Background technique [0002] At present, there have been some achievements in pavement crack detection. For example, the patent CN106548182 has been applied for, and the application date was November 02, 2016. The patent title is "Pavement crack detection method and device based on deep learning and main cause analysis" A Pavement Crack Detection Method Based on Convolutional Neural Network and Principal Cause Analysis. The applied patent CN106324084, the application date is August 30, 2016, and the patent title is "Crack Depth Detection Method", which discloses a method and instrument for detecting crack depth. [0003] In recent years, with the rapid development of pavement crack detection technology, the demand for pavement crack detection methods, especially crack propagation analysis on pavement, has bec...

AI Technical Summary

Problems solved by technology

[0003]In recent years, with the rapid development of pavement crack detection technology, the demand for pavement crack detection methods, especially crack propagation analysis on pavement, is becoming increasingly urgent. The supervised method of learning is the main means of pavement crack detection. The premise of the application of this method is to train a large amount of labeled data, which is difficult to be widely used in practice.

Images