High-speed rail heavy rail surface defect detection method based on point cloud method

Abstract

The invention relates to the technical field of surface defect detection, and provides a high-speed rail heavy rail surface defect detection method based on a point cloud method, which comprises the following steps of firstly, constructing a detection platform, and calibrating a color binocular linear array camera; collecting the initial linear array images of the to-be-detected high-speed rail heavy rail under n visual angles and preprocessing the initial linear array images; mapping the two two-dimensional images under each view angle into a three-dimensional depth image, utilizing a two-dimensional image registration method based on phase correlation to provide the initial registration for two to-be-registered point clouds under adjacent view angles, and performing ICP accurate iteration on each pair of point clouds after registration to obtain the complete surface point clouds; and finally, carrying out defect extraction and segmentation on the complete surface point cloud by utilizing a point cloud region growth algorithm taking the normal vector angle and the curvature change quantity as smooth thresholds to obtain the surface defect distribution of the high-speed rail heavyrail to be detected. According to the present invention, the influence of the image acquisition quality and the detection area range on detection can be reduced, the detection efficiency and the detection rate are improved, and the missed detection rate and the false detection rate are reduced.

Description

technical field [0001] The invention relates to the technical field of surface defect detection, in particular to a method for detecting surface defects of high-speed heavy rails based on a point cloud method. Background technique [0002] With the rapid development of my country's high-speed rail technology, high-speed rail has become an efficient, comfortable and safe way of travel. The safe production of high-speed heavy rails has become an important issue to ensure travel safety, and the detection of surface defects on heavy rails is an important task for the safe production of heavy rails. [0003] The existing surface defect detection methods for heavy rails of high-speed rail mainly include manual visual detection methods and heavy rail online detection methods based on machine vision. On the one hand, most steel mills are still at the stage of manual visual inspection, which is subject to the subjective factors of inspectors, with low detection efficiency, high miss...

AI Technical Summary

Problems solved by technology

However, the existing machine vision-based surface defect detection methods for high-speed rail and heavy rail mostly use two-dimensional image-based detection methods, which are very limited in the quality of image collection and are affected by the scope of the detection area, which is prone to missed detection and false detection. check problem

Images