A method for detect edge of pantograph slide plate of urban rail train

Abstract

The invention discloses a method for detecting the edge of a pantograph slide plate of a city rail train. At first, that gray image signal of the pantograph slide plate is obtained, and the image signal is convolution with a Gaussian convolution kernel with adaptive size; Then the gradient magnitude and direction of the filtered image are calculated by the gradient operator in the 8 neighborhoodsof 3*3. Finally, the gradient amplitude is suppressed by non-maximum method, and the edge image of pantograph skateboard is obtained by double threshold adaptive extraction and edge connection. The invention is based on an improved Canny operator, and has obvious detection result and strong applicability.

Description

technical field [0001] The invention belongs to the technical field of pantograph fault detection, in particular to a method for detecting the edge of a pantograph slide plate of an urban rail train. Background technique [0002] With the improvement of train speed and the increase of operating mileage, the safety performance of trains is becoming more and more important. The pantograph is generally installed on the top of the train, and is in sliding contact with the contact line during operation, and obtains electric energy from the contact line. It is an important part for the train to obtain reliable electric energy during operation. The carbon skateboard is a key part of the train pantograph system to obtain electric energy. During the operation of the train, the carbon skateboard is susceptible to wear. Once the wear exceeds the warning value, it will cause serious traffic accidents. [0003] John F.Canny proposed the Canny edge detection operator, which belongs to th...

AI Technical Summary

Problems solved by technology

However, Canny edge detection has the following defects: (1) In the first step of Gaussian filtering, the edge information is also weakened while filtering out the image noise, and some edges with inconspicuous features are missed; (2) The amplitude is calculated in the second step and gradient process, use 2×2 field to calculate gradient and amplitude, this method is very sensitive to noise and easy to detect false edges; (3) in the fourth step of setting double thresholds, the selection of double thresholds is very important to the edge has a great influence on the final determination of , it is difficult to choose an optimal value

After the threshold is set by the manual empirical method, the threshold cannot be reselected adaptively based on the information of each picture

Images