Rail fastener positioning method based on linear template matching

Abstract

The invention relates to a rail fastener positioning method based on linear template matching. The rail fastener positioning method comprises the following steps: (1) a fastener template is manufactured; (2) according to the width size wf of the fastener area and the coordinates of the steel rail area, and a line-shaped segmentation area of the fastener area is segmented from the original image ofa track line to obtain a line-shaped segmentation area graph, wherein the unit of wf is a pixel; (3) accurate positioning is carried out, a symmetric fastener template on the line-shaped segmentationregion graph is scanned, and the similarity between a scanning area and a template are measured by using a normalized correlation coefficient; and (4) the processes in steps (2)-(3) are recycled, andall the collected rail line original drawings are traversed to position all the fasteners on the track, wherein each track line original drawing only comprises a pair of complete fasteners. The positioning method is suitable for a ballasted line and a ballastless line at the same time, the positioning accuracy is high, the fastener in the damaged state can be effectively positioned, and meanwhilethe positioning speed is 0.3 s/piece or below.

Description

technical field [0001] The invention belongs to the technical field of rail fastener positioning, and relates to a rail fastener positioning method based on one-word template matching. Background technique [0002] Railway fasteners are fasteners that fix rails on sleepers. The loss or breakage of fasteners is likely to cause major accidents such as train derailment. With the rapid growth of my country's railway operating mileage, ordinary manual inspections have problems such as high cost, low efficiency, and various safety hazards, which have been unable to meet the needs of frequent inspections of railway networks represented by high-speed railways. Therefore, railway deduction Automated identification of files has also begun to appear particularly important. However, if the entire image captured on the line is detected, it will not only fail to meet the real-time requirements of fastener detection due to the long recognition time, but also the complex background in the e...

AI Technical Summary

Problems solved by technology

[0003] In recent years, scholars at home and abroad have carried out in-depth research on the positioning algorithm of fasteners. Document 1 (Railway Standard Design, 2016, 60(12): 49-53.) proposes an improved cross-track fastener positioning method , narrow the processing area through prior knowledge, then use the median filter to preprocess the image, and finally use the cross method to locate fasteners, but the fastener positioning based on the cross method is mainly for ballasted lines, while ballastless tracks This kind of method is gradually being eliminated; Document 2 (Computer Measurement and Control, 2018, 26(5): 166-169.) proposes a method using the edge gradient direction field of image texture information as a template to realize ballastless...

Images