Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Fusion Method of Infrared and Visible Light Images Based on Feature Embedding

An image fusion and visible light technology, applied in the field of infrared image and visible light fusion, can solve the problem of insufficient utilization of source image feature information

Active Publication Date: 2021-08-17
SICHUAN UNIVERSITY OF SCIENCE AND ENGINEERING
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods can achieve relatively ideal results, but because most of the existing methods only use single-level features of the source image, or use different levels of feature information separately, this will lead to the use of source image feature information in the process of fusion tasks. insufficient

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
  • A Fusion Method of Infrared and Visible Light Images Based on Feature Embedding
  • A Fusion Method of Infrared and Visible Light Images Based on Feature Embedding
  • A Fusion Method of Infrared and Visible Light Images Based on Feature Embedding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0075] The specific embodiments of the present invention are described below so that those skilled in the art can understand the present invention, but it should be clear that the present invention is not limited to the scope of the specific embodiments. For those of ordinary skill in the art, as long as various changes Within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions and creations using the concept of the present invention are included in the protection list.

[0076] Such as figure 1 , figure 2 As shown, the present invention provides a method for fusion of infrared and visible light images based on feature embedding, including the following steps S1 to S4:

[0077] S1. Construct a self-calibrating convolutional network model to extract source image features of infrared and visible light images, and obtain source image feature information;

[0078] Such as image 3 As shown,...

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 fusion method of infrared and visible light images based on feature embedding, which extracts the source image features of infrared and visible light images by constructing a self-calibration convolutional network model, and obtains source image feature information; and utilizes ZCA whitening to process the source image feature information Perform preprocessing to obtain the feature activity map of the source image; embed the high-level feature activity map in the source image feature activity map into the low-level feature activity map to obtain a weight map, and finally construct a fusion image through the source image and the weight map. The present invention improves the quality evaluation of infrared and visible light image fusion in target detection, target tracking, and biometric recognition in terms of pixel feature mutual information, difference correlation, structural similarity, edge preservation index, and fusion performance based on noise evaluation. effectiveness.

Description

technical field [0001] The invention relates to fusion of infrared images and visible light, in particular to a method for fusion of infrared and visible light images based on feature embedding. Background technique [0002] The fusion of infrared images and visible light images is of great significance. Objects cannot obtain useful information only through visible light images under harsh lighting or camouflage occlusion environments. Infrared images come from infrared sensors, which can capture electromagnetic waves of different frequencies radiated by objects, also known as thermal radiation. At the same time, since the heat emitted by the object is hardly affected by the texture, the infrared image will also lose the texture detail information. Infrared and visible light image fusion generates complementary information from different sensors into the same image, while retaining the thermal radiation information of infrared images and the texture information of visible ...

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 Patents(China)
IPC IPC(8): G06T3/40G06T5/50G06N3/04G06N3/08
CPCG06T3/4007G06T5/50G06N3/08G06T2207/10004G06T2207/10048G06T2207/20081G06T2207/20084G06N3/045
Inventor 骆忠强代金鹏
Owner SICHUAN UNIVERSITY OF SCIENCE AND ENGINEERING
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com