A detection method for railway rail crawling displacement based on monocular vision measurement technology

Abstract

The invention relates to the technical field of railway precision measurement, and discloses a method for detecting crawling displacement of railway rails based on monocular vision measurement technology. Firstly, the images containing circular markers are collected by the image acquisition equipment installed on the inherent facilities next to the rail; secondly, the image resolution of the region of interest in the collected images is improved by using the image super-resolution reconstruction method; then, the template matching method is used to initially Locate the position of the marker in the reconstructed image, and combine edge detection and circle fitting methods to accurately calculate the centroid coordinates and radius of the marker; finally, the physical displacement of the rail crawl is detected based on the image imaging principle. The invention is a non-contact measurement, which solves the problem of relatively large estimation errors by the traditional human eye, avoids the soaring cost caused by the method of improving the measurement accuracy by improving the quality of the image acquisition equipment, and thus cannot be widely used, and effectively guarantees Improve the measurement accuracy and save manpower.

Description

technical field [0001] The invention relates to the technical field of railway precision measurement, in particular to a method for detecting crawling displacement of railway rails based on monocular vision measurement technology. Background technique [0002] In order to ensure the safe operation of the huge railway system, it is necessary to ensure that the parameters of the railway track are normal at all times. At present, it mainly relies on the staff to go to the railway site to use complex instruments to measure the creeping displacement of the rail. To use various contact or non-contact displacement sensors to measure rail crawling, high-precision sensors must be installed on the rails. However, the complex environment of the railway site is likely to affect the measurement accuracy of the sensors. Using machine vision technology to measure rail crawling does not require contact with the rails and can be detected at a safe distance that does not affect train operati...

AI Technical Summary

Problems solved by technology

At present, there are too many positions where crawling displacement needs to be detected in the mileage of railway tracks in operation in my country. The method of improving hardware quality will lead to a substantial increase in cost, which in turn restricts the application of machine vision technology in rail crawling displacement detection.

The acquisition field of view of rail crawling displacement detection is large, and the general target detection method cannot meet the accuracy requirements of rail crawling displacement detection

Images