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

Sub-task rail wagon image quality judgment method based on sparse representation and SVM

A technology of sparse representation and quality judgment, applied in the field of image processing, which can solve problems such as low accuracy and failure

Active Publication Date: 2020-10-27
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to solve the problem of low accuracy or even failure when the existing image quality judgment method detects truck images

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
  • Sub-task rail wagon image quality judgment method based on sparse representation and SVM
  • Sub-task rail wagon image quality judgment method based on sparse representation and SVM
  • Sub-task rail wagon image quality judgment method based on sparse representation and SVM

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0054] Specific embodiment one: combination figure 2 Describe this embodiment,

[0055] The method for judging the image quality of a sub-task railway freight car based on sparse representation and SVM described in this embodiment includes the following steps:

[0056] 1. Collect image diseases to establish image quality judgment data set:

[0057] Set up high-definition cameras on both sides and bottom of railway trucks. For example, you can install 2 cameras on both sides of the truck, and 3 cameras on the bottom to obtain images of the truck after the truck passes; due to camera angle, focus, sunlight, weather, uneven speed, etc. As a result, the captured images will have low quality, which will seriously affect the subsequent recognition tasks. Therefore, it is necessary to judge the image quality before fault detection to improve the accuracy of fault detection.

[0058] The present invention judges the image quality according to tasks, respectively evaluates whether the bright...

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 sub-task rail wagon image quality judgment method based on sparse representation and SVM, and belongs to the technical field of image processing. The objective of the invention is to solve the problem that an existing image quality judgment method is low in accuracy and even fails when truck images are detected. Truck images are sent to a trained quality judgment networkto obtain an image quality judgment result; in the determination process of the quality judgment network, five quality judgment data sets are constructed according to positive samples and negative samples of brightness, definition, symmetry, stretching degree and noise, and the image quality of each image is scored to serve as a quality label; and for the five quality judgment tasks, different features of the image are extracted, feature coding is performed by adopting sparse representation, different quality judgment models are respectively constructed and trained, five quality scores are obtained according to the five quality judgment models, a final quality score is determined, and the final quality score is taken as a judgment result of image quality judgment. The method is mainly used for wagon image quality judgment.

Description

Technical field [0001] The invention relates to a method for judging the image quality of railway freight cars. It belongs to the field of image processing technology. Background technique [0002] Railway freight cars have always played an important role in transportation. Railway departments need to conduct safety inspections on railway freight cars frequently to ensure the safe and stable operation of railway freight cars. For a long time, the equipment inspection of railway freight cars has basically adopted the method of manually viewing images to inspect the whole freight train, which has always been high cost and low efficiency. Using the method of manually viewing images makes the work boring, easy to slack, effective working time is limited, efficiency is further reduced, and it is very prone to missing parts, false alarms, etc., and it is difficult to ensure accuracy. [0003] Compared with the fault detection method of manually checking the image, the automatic fault d...

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): G06T7/00G06K9/46G06K9/62B61K9/00
CPCG06T7/0002B61K9/00G06T2207/30168G06V10/40G06V10/513G06F18/2411
Inventor 韩旭
Owner HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD