Track elastic strip fastener defect recognition method, device and computer equipment

Abstract

The invention discloses a track elastic strip fastener defect recognition method and device and computer equipment, and belongs to the technical field of machine vision detection. The recognition method comprises the following steps: constructing an imaging system based on a line laser sensor to collect a track contour height; using a color mapping method to construct the contour height into a color depth image; judging whether the depth image contains a complete fastener area or not, and if the fastener area is incomplete, splicing the front fastener image and the rear fastener image; extracting a depth image region of the fastener; and the deep convolutional neural network classifies the fastener region image to identify the defect fastener. According to the method, the height contour value of the track is collected and constructed into the depth image, and the fastener defect is recognized according to the difference of the depth image, so that the problem of simultaneously detecting the defects of loss, dislocation, fracture and looseness of the fastener is solved. Meanwhile, the defect detection rate of the fastener is improved.

Description

technical field [0001] The invention relates to the technical field of machine vision defect detection, in particular to a method, device and computer equipment for identifying defects of rail clip fasteners based on depth images. Background technique [0002] As an important infrastructure of railway, track is the basis of train operation. With the development of railways in the direction of heavy load and speed increase, high-speed and heavy-load trains will increase the destructive power to the infrastructure of the railway, resulting in various types of defects. The infrastructure of the railway mainly includes rails, fasteners, sleepers, etc. The fasteners are responsible for connecting the rails and sleepers to prevent the rails from shifting. A complete clip fastener consists of a bolt and a retaining ring, and the bolt tightens the retaining ring to secure the rail to the sleeper. Fastener defects are mainly manifested as loss of buckle rings, misalignment, and los...

AI Technical Summary

Problems solved by technology

[0005] However, the two-dimensional image of the track obtained by the two-dimensional image sensor lacks the depth information of the third dimension, and cannot detect whether the fastener bolts are loose

The 3D point cloud does not have any spatial topology and texture information, so it is difficult to detect out-of-position defects of fasteners, and the data volume of the 3D point cloud is large, resulting in slow data processing

Images