Infrared image temperature estimation method and system based on full convolutional neural network

A convolutional neural network and infrared image technology, applied in the infrared image temperature estimation method and system field, can solve the problems of infrared image temperature storage information redundancy, excessive consumption of network transmission and file storage resources, and improve storage and transmission efficiency , solve the gradient disappearance problem of backpropagation, the effect of strong generalization ability

Pending Publication Date: 2021-11-26
QILU UNIV OF TECH
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, a large number of temperature tags lead to excessive redundancy of infrared image temperature storage information. When a large number of infrared image files need to be collected on site, it will lead to excessive consumption of network transmission and file storage resources.

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
  • Infrared image temperature estimation method and system based on full convolutional neural network
  • Infrared image temperature estimation method and system based on full convolutional neural network
  • Infrared image temperature estimation method and system based on full convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] In the infrared image temperature estimation method based on the fully convolutional neural network in this embodiment, the basic network model adopted is a fully convolutional neural network, and the improved fully convolutional neural network is first used to estimate the relative temperature of different pixels of the infrared image; then According to the singular point elimination algorithm proposed in this paper, smoothing is performed on the area where the pixel value of the original infrared image changes suddenly, so as to further reduce the estimation error and improve the prediction accuracy. Realize the temperature estimation of different areas of the infrared image through the temperature estimation algorithm, solve the problem of too large infrared image files caused by the temperature matrix, and the high cost of storage and transmission efficiency, which is conducive to further reducing the cost of using infrared images and further popularizing the promotio...

Embodiment 2

[0128] This embodiment provides an infrared image temperature estimation system based on a fully convolutional neural network, including:

[0129] The primary relative temperature matrix prediction module is configured to: obtain a color infrared image, and predict the primary relative temperature matrix of the image size through the infrared image temperature estimation model;

[0130] Smoothing processing module, it is configured to: For primary relative temperature matrix, calculate the temperature average value and standard deviation in the sliding window; Determine whether the temperature value of each point in the sliding window and the difference value of the average value exceed the standard deviation, if , it is considered as a singular point, and the temperature value of this point is reset to the average value, otherwise, the temperature value of this point remains unchanged; the sliding window is moved until the primary relative temperature matrix is ​​traversed com...

Embodiment 3

[0133] This embodiment provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions are suitable for being loaded by a processor of a terminal device and executing the method for estimating an infrared image temperature based on a fully convolutional neural network.

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

Disclosed are an infrared image temperature estimation method and system based on a full convolutional neural network provided by the invention, an infrared image temperature marking method is replaced, so that the file size of an infrared image is effectively reduced; the method comprises the following steps: firstly, analyzing the influence of different activation functions, a batch normalization method, a temperature label and other factors on a temperature estimation result, optimizing a full convolutional neural network structure, and predicting to obtain a primary relative temperature matrix of an infrared image; secondly, using a singular point elimination algorithm to smooth the primary relative temperature matrix, so that the estimation precision of the temperature matrix is further improved;.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an infrared image temperature estimation method and system based on a fully convolutional neural network. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] With the advancement of infrared thermal imaging technology, infrared temperature measurement technology has been widely used in national defense and agriculture due to its unique advantages such as non-contact measurement, nondestructive testing, wide temperature measurement range, visible measurement results, low power consumption and good portability. , industry, construction, medical services and other fields. In recent years, scholars at home and abroad have carried out a lot of research on the improvement of infrared temperature measurement accuracy and image correl...

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): G06N3/04G01J5/00
CPCG01J5/00G06T2207/10048G06T2207/10024G01J2005/0077G06N3/045
Inventor 马宾娄爱涛马睿和徐健王春鹏李健周琳娜李宁宁
Owner QILU UNIV OF TECH
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