Steel rail surface damage fine-grained image classification and detection method

A detection method and fine-grained technology, applied in image analysis, image enhancement, image data processing, etc., can solve the problems of digitalization, low automation and intelligence, low efficiency, and inability to provide predictive decision-making information for rail maintenance and repair, etc., to achieve The effect of improving driving safety and comfort and reducing costs

Active Publication Date: 2021-09-07
TONGJI UNIV
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The former is inefficient, relying on square rulers and other measuring tools for subjective and qualitative records of individual serious points, and cannot quantify the damage of the entire rail surface; the purpose of the latter is to detect rail surface damage, but it is limited to the distance between the lens and the rail surface Due to the high-speed motion of the body, the rail surface image is not rich and clear enough, and has not yet reached the leve

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
  • Steel rail surface damage fine-grained image classification and detection method
  • Steel rail surface damage fine-grained image classification and detection method
  • Steel rail surface damage fine-grained image classification and detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0061] Such as figure 1 As shown, the present invention provides a fine-grained image classification and detection method for rail surface damage, including the following:

[0062] (1) Constructing a target detection dataset: A standard process for constructing a rail surface damage target detection dataset is proposed, including shooting methods, damage category definition, instance-level fine-grained target detection and labeling paradigm, and auxiliary enhancement for low-contrast difficult images method, and then proposed the Subway-1094 track surface damage target detection dataset. The data set is superior to existing data sets in terms of image quantity, image quality, damage category, labeling quality, and target density, and can drive deep learning algorithm training.

[0063] (2) Training target detection algorithm: YOLOV5 deep learning target detection algorithm is trained based on the above data set. Evaluate the recognition performance of each category, optimize...

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

No PUM Login to view more

Abstract

The invention relates to a steel rail surface flaw fine-grained image classification and detection method. The method comprises the following steps: 1) constructing a fine-grained rail surface flaw target detection data set; 2) carrying out rail surface damage target detection by adopting a YOLOV5 algorithm; and 3) performing rail surface damage visual measurement and quantitative evaluation according to a detection result, and performing interactive map visual display of damage distribution. Compared with the prior art, the invention has the advantages of rail surface damage automation, intelligent image recognition and digital storage management, and is helpful to guide and formulate a steel rail maintenance strategy.

Description

technical field [0001] The invention relates to the field of rail surface damage detection, in particular to a fine-grained image classification and detection method for rail surface damage. Background technique [0002] With the significant increase in the operating mileage, operating speed, locomotive axle load, traffic density and passenger and freight volume of rail transit, the wheel-rail structure as the main carrier of railway transportation has been subjected to cyclic, high-speed, heavy-duty load states, wheel-rail relations and stresses. The state gradually deteriorates, manifested as wheel and rail damage, and rail damage may occur in various parts inside and outside the rail, especially the surface damage of the rail head tread surface in direct contact with the wheel and rail (referred to as rail surface damage in the present invention) is the most typical. Surface damage includes fatigue cracks, peeling off blocks, wear, wave wear (abbreviated as wave wear in t...

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
no application Login to view more
IPC IPC(8): G06T7/00G06T7/194G06T7/13G06T5/00G06T7/62G06N3/04
CPCG06T7/0004G06T7/194G06T7/13G06T5/009G06T7/62G06N3/045
Inventor 周宇张子豪
Owner TONGJI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap