Unlock instant, AI-driven research and patent intelligence for your innovation.

Train wheel tread image enhancement method based on adaptive learning particle swarm optimization

A technology of particle swarm optimization and self-adaptive learning, which is applied in the field of image processing, can solve the problem of poor detail level effect after the original image is enhanced, and achieve the effect of improving the optimization effect, detail level and contrast

Pending Publication Date: 2020-03-27
NANJING TYCHO INFORMATION TECH
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a method for enhancing the tread image of train wheels, which solves the problem that the existing methods have poor effect on the level of detail after enhancing the original image

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
  • Train wheel tread image enhancement method based on adaptive learning particle swarm optimization
  • Train wheel tread image enhancement method based on adaptive learning particle swarm optimization
  • Train wheel tread image enhancement method based on adaptive learning particle swarm optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be further described below in conjunction with the accompanying drawings.

[0026] Particle Swarm Optimization (PSO) is a nonlinear optimization algorithm based on group evolution. It is based on the principle that birds search for food in a certain area. It regards each particle as a bird and uses multiple particles in the search space according to particle The individual behavior and group behavior automatically find the objective function f(x):R n → The optimal solution of R. particle variable x∈R n , then the search target can be expressed as:

[0027]

[0028] At each moment k, the ith particle Adjust your own search behavior according to the following two formulas, and adjust the position and speed respectively:

[0029]

[0030]

[0031] c 1 is the individual cognitive acceleration constant of the particle, c 2 is the group cognitive acceleration constant, parameter c 1 and c 2 Represents the influence of the individua...

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 discloses a train wheel tread image enhancement method based on adaptive learning particle swarm optimization. Carrying out enhancement processing on the train wheel tread image by usingan adaptive gamma correction factor selected by a particle swarm optimization algorithm; fusing the gray scale standard variance into an evaluation function; entropy, edge content and gray scale standard deviation are used as an objective function of each particle to evaluate an obtained image enhancement result, global enhancement is performed on the image by searching for an optimal gamma value, detail enhancement of the train wheel tread image is realized, and the optimization effect of the standard particle swarm algorithm is improved by adaptively adjusting learning factors; compared with a traditional method, the method has the advantages that the image contrast is remarkably improved, the image viewing comfort and detail recognizable degree are higher, and image details are richer.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a train wheel tread image enhancement method based on adaptive learning particle swarm optimization. Background technique [0002] With the development of the railway industry, the detection and maintenance of the wheel tread, which is an important component of train running, has been paid more and more attention. At present, the contact measurement based on the impact load method and the manual visual inspection method are the main methods in practical applications, but these two detection methods have the problems of low detection efficiency and low work efficiency in practical applications. The method of image processing can achieve the function of visual inspection due to its non-contact, fast, efficient and stable characteristics, and has been widely used in the field of non-destructive testing. When actually shooting tread images in a moving state, it is easily af...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00G06N3/00
CPCG06N3/006G06T2207/20081G06T2207/30252G06T5/80G06T5/73
Inventor 郭其昌梅劲松蒋银男付军董辉王干
Owner NANJING TYCHO INFORMATION TECH