Unlock instant, AI-driven research and patent intelligence for your innovation.
Wagon wheel damage detection method based on image processing
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A railway freight car and image processing technology, applied in the field of image processing, can solve the problems of low failure efficiency and accuracy, reduce labor costs, avoid false detection and missed detection, and improve detection efficiency
Active Publication Date: 2021-02-05
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF6 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0004] The purpose of the present invention is: aiming at the problem of low efficiency and accuracy in the manual detection of railway wagon wheel damage faults in the prior art, a method for detecting railway wagon wheel damage based on image processing is proposed
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0046] Specific implementation mode one: refer to figure 1 Describe this embodiment in detail, the railway wagon wheel damage detection method based on image processing of this embodiment, comprises the following steps:
[0047] Step 1: Obtain the 3D image of the image to be detected and the linear image of the railway wagon wheel. The 3D image includes a 3D grayscale image and a 3D height image;
[0048] Step 2: use the 3D grayscale image as a template to perform histogram prescriptive processing on the linear image of the railway wagon wheel to obtain a prescriptive image;
[0049] Step 3: Extract ORB features of the standardized image and 3D grayscale image;
[0050] Step 4: Match the ORB features of the specified image and the 3D grayscale image to obtain a change matrix;
[0051] Step 5: Adjust the pixel points in the 3D height map so that the rim height value in the adjusted 3D height map is within the target range;
[0071] Embodiment 2: This embodiment is a further description of Embodiment 1. The difference between this embodiment and Embodiment 1 is that the detection method also includes inspection steps, and the inspection steps are specifically:
[0072] Step A: Intercepting the fault area sub-image and the non-fault area sub-image in the railway wagon wheel line array image;
[0073] Step B: Extract the LBP features of fault area subgraphs and non-fault area subgraphs, and train SVM according to LBP features. Such as image 3 shown.
specific Embodiment approach 3
[0074] Embodiment 3: This embodiment is a further description of Embodiment 2. The difference between this embodiment and Embodiment 2 is that the trained SVM is trained through the following steps:
[0075] Step A1: Intercepting the fault area sub-image and the non-fault area sub-image in the sample railway wagon wheel line array image;
[0076] Step A2: Extract the LBP features of the fault area subgraph and the non-fault area subgraph, and train the initial SVM according to the extracted LBP features to obtain a trained SVM.
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 wagon wheel damage detection method based on image processing, relates to the technical field of image processing, and aims to solve the problem of low accuracy of manual detection of rail wagon wheel damage faults in the prior art, replace manual detection with an automatic image recognition mode, improve the fault recognition detection efficiency and accuracy and reducethe labor cost. The detection range is recognized through a 3D camera, the efficiency is higher and more accurate, the defects of the 3D camera can be overcome more effectively by judging faults through grayscale images, and false detection and missing detection are avoided. Possible fault areas are extracted in a conventional mode and then classified and identified, so that the operation efficiency can be effectively improved.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to a method for detecting damage to railway wagon wheels based on image processing. Background technique [0002] At present, fault detection of EMUs generally adopts manual troubleshooting for troubleshooting. Since the inspection operation is greatly affected by factors such as the professional quality, sense of responsibility, and labor intensity of the operator, it is easy to miss inspection or simplify the operation. The efficiency and accuracy of manual inspection are low. Once a quality problem occurs, it is not conducive to finding the cause and time of the problem during the operation. [0003] Positioning is performed through the height image of the 3D camera, and the identification range of the entire wheel fault is selected. Faults are judged and identified through the grayscale image of the line scan camera. Calculate the gradient feature along the wheel ell...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More