Railway electric locomotive fault detection method based on image feature registration
A fault detection and image feature technology, applied in image enhancement, image analysis, image data processing and other directions, can solve problems such as poor detection accuracy
Inactive Publication Date: 2021-05-07
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF4 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Aiming at the problem of poor detection accuracy of the image feature registration network detection method based on deep learning in the existing electric locomotive fault detection when the electric locomotive model changes, the present invention provides a railway electric locomotive fault detection based on image feature registration method
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0063] Specific implementation mode 1. Combination Figure 1 to Figure 11 As shown, the present invention provides a method for fault detection of railway electric locomotives based on image feature registration, including:
[0064] Step 1: Obtain the template image of the part to be detected and the image of the part to be detected;
[0065] Step 2: Process the image of the part to be detected and the corresponding template image using the SIFT algorithm to obtain the feature point description information of the image to be detected and the feature point description information of the template image respectively, and the feature point description information includes feature point position information;
[0066] Step 3: Match the feature point description information of the image to be detected with the feature point description information of the template image through the KNN algorithm to obtain the feature point description information of the nearest image to be detected an...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a railway electric locomotive fault detection method based on image feature registration, and belongs to the technical field of locomotive fault image recognition. The invention aims to solve the problem of poor detection precision of an image feature registration network detection method based on deep learning when the type of an electric locomotive is changed in the existing electric locomotive fault detection. The method comprises the steps of obtaining a template image of a to-be-detected part, collecting an image of the to-be-detected part, and obtaining feature point description information of the corresponding image by adopting an SIFT algorithm; performing matching through a KNN algorithm, filtering outlier feature points, and obtaining feature point position information of the filtered to-be-detected image and feature point position information of the template image; and performing clustering to obtain core feature point position information of the corresponding image, and then performing affine transformation on the to-be-detected part image by adopting a random sampling affine transformation algorithm to obtain a corrected to-be-detected image. According to the method, the fault detection precision can be ensured during vehicle type change.
Description
technical field [0001] The invention relates to a fault detection method for railway electric locomotives based on image feature registration, and belongs to the technical field of locomotive fault image recognition. Background technique [0002] In the image feature registration technology of traditional image processing, for images of different sizes, the images can be positioned by extracting the same feature points on the two images; for images of the same size, the same feature points on the two images can be extracted Point to image stitching; for images of any size, the image can also be corrected by extracting the same feature points on the two images. In the fault detection of electric locomotives, the correction technology in image feature registration is often used for fault recognition, but the corrected image often produces a certain deformation, so it is difficult to obtain accurate detection results in the subsequent fault recognition. [0003] Using the imag...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06T7/00G06T7/33G06T3/00G06K9/62
CPCG06T7/0002G06T7/33G06T2207/10004G06T2207/20016G06V10/751G06F18/23G06T3/02
Inventor 石玮龙施洋
Owner HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD