Steel rail surface detection method based on image recognition
A surface detection and image recognition technology, applied in image analysis, image enhancement, image data processing, etc., can solve the problems of inability to realize automatic identification of damage models, limited detection coverage, etc., to reduce costs and improve efficiency.
Inactive Publication Date: 2020-09-04
东莞先知大数据有限公司
View PDF9 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, this invention only detects the top surface of the rail, the detection coverage is limited, and the damage on both sides of the rail is ignored
This inventive method only realizes the defect judgment, but cannot realize the automatic recognition of the damage model
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
Embodiment Construction
[0020] The present invention will be further described below through specific embodiments in conjunction with the accompanying drawings. These embodiments are only used to illustrate the present invention, and are not intended to limit the protection scope of the present invention.
[0021] Such as figure 1 As shown, the rail surface detection method based on image recognition of the present invention includes collecting rail surface images by high-speed ultra-clear cameras, converting the rail surface images into grayscale images, calculating grayscale co-occurrence matrices, calculating texture feature quantities, and training gradients Model, using the trained gradient ascent model to judge six parts.
[0022] The specific implementation is as follows:
[0023] The rail surface detection method based on image recognition is characterized in that it comprises the following steps:
[0024] S1, using a high-speed ultra-clear camera to collect rail surface images; the high-sp...
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 relates to the field of rail transit and steel rail flaw detection, in particular to a steel rail surface flaw detection method based on image recognition. The method comprises the stepsthat S1, collecting a steel rail surface image by a high-speed super-definition camera; S2, converting the steel rail surface damage image into a grey-scale map; S3, calculating a gray level co-occurrence matrix of the image; S4, calculating texture characteristic quantity according to the gray level co-occurrence matrix; S5, establishing a Graded Boosting model, and the Graded Boosting model isused for injury type classification; and S6, inputting a to-be-judged steel rail surface image into the trained gradient rising model to obtain a corresponding damage type. The method has the advantages that the surface damage of the steel rail can be automatically and accurately judged, the damage judging accuracy and efficiency are improved, and rail breakage accidents can be effectively prevented.
Description
technical field [0001] The invention relates to the field of rail transit and rail flaw detection, in particular to an image recognition-based rail surface detection method. Background technique [0002] With the expansion of my country's rail transit network layout, the speed and safety requirements of the rails are also increasing. During the running process, the train rubs against the rail surface, which causes damages and defects on the rail surface in different degrees, which affects the driving safety. Existing rail surface damage detection usually uses ultrasonic detection, three-dimensional detection and other technologies combined with manual detection. Although these methods and technologies can achieve the purpose of detection, they are easily affected by external interference, and the efficiency and accuracy are not high, requiring manual judgment of defects And manually record the type of defect and the marked area. [0003] In the CN101893580B digital image-b...
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 Patent Type & AuthorityApplications(China)
IPC IPC(8): G06T7/00G06T7/45G06K9/46G06K9/62
CPCG06T7/0004G06T7/45G06T2207/10004G06T2207/20081G06T2207/30164G06T2207/30136G06V10/40G06F18/24
Inventor梁帆余旸
Owner东莞先知大数据有限公司