Wheelset tread damage detection method based on laser strip centerline location extraction algorithm

Abstract

The invention discloses a wheel set tread damage detection method based on a laser strip centerline positioning and extraction algorithm, and relates to the technical field of railway traffic. The method uses a contour tracking extraction algorithm to extract the contour boundary line of a detected laser strip from a tread detection image, And in the normal direction of the contour boundary line, select the center line candidate area in the predetermined range, apply the Steger algorithm to locate and extract the center line of the laser bar for detecting the laser bar in the center line candidate area, and then realize the damage to the wheel tread Detection; this method has a small amount of data calculation, better extraction speed and real-time performance, and can not only effectively locate and detect the laser bar, eliminate the interference of stray spots, but also effectively use the differential characteristics of the laser bar image, and finally achieve high precision The rapid extraction has a better surface in terms of extraction speed and extraction accuracy, which can improve the speed and accuracy of wheel tread damage detection.

Description

technical field [0001] The invention relates to the technical field of railway transportation, in particular to a wheel set tread damage detection method based on a laser strip center line positioning extraction algorithm. Background technique [0002] With the increasing volume of rail transportation, the development of high-speed and large-load rail transportation has become an inevitable development trend, which poses a severe test to the detection of vehicle safety status. Therefore, the quality of train components, especially the quality of wheelsets, has a non-negligible impact on the operational safety of the railway transportation industry. The train has the characteristics of continuous and uninterrupted use. During the continuous operation, various parts will inevitably wear out. Therefore, it is necessary to detect the damage of the train parts in time, and repair and replace the train parts with wear exceeding the specified limit. This increases train safety. ...

AI Technical Summary

Problems solved by technology

[0005] The existing laser bar centerline extraction methods can be mainly divided into two categories: one is the traditional centerline extraction method that only considers the distribution characteristics of the laser bar gray value, mainly including the extreme value method, the threshold method, the gray center of gravity method, and the edge method. and geometric center method, etc., but the extraction accuracy of these methods is not high and the robustness is poor

The second is the centerline extraction method based on the characteristics of the laser bar (such as differential characteristics and morphological characteristics, etc.), mainly including the Steger method and the direction template method. There is still a gap in the method

It can be seen that the existing laser strip centerline extraction method is difficult to perform well in both extraction accuracy and extraction speed, which affects the effect of using line structured light scanning technology to realize wheel set tread damage detection

Images