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

Adversarial neural network-based infrared image super-resolution method

An infrared image, neural network technology, applied in image data processing, graphic image conversion, instruments, etc., can solve the problems of slow speed, fast speed, poor effect, etc., and achieve the effect of fast speed, best performance and clear image.

Pending Publication Date: 2021-06-18
数量级(上海)信息技术有限公司
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current embedded super-resolution algorithm is either poor in effect and fast in speed; or good in effect but slow in speed, which cannot meet the needs of the development of autonomous driving

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
  • Adversarial neural network-based infrared image super-resolution method
  • Adversarial neural network-based infrared image super-resolution method
  • Adversarial neural network-based infrared image super-resolution method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0082] Next, the technical solutions in the embodiments of the present invention will be apparent from the embodiment of the present invention, and it is clearly described, and it is understood that the described embodiments are merely embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained without the premise of creative labor are not made in the premise of creative labor.

[0083] It should be noted that the features and embodiments in the present invention can be combined with each other in the case of an unable conflict.

[0084] The present invention is further explained in conjunction with the accompanying drawings and specific examples, but is not limited as the present invention.

[0085] A super-resolution method disclosed in the present invention is applied to an embedded apparatus, wherein the anti-neural network comprises generating a network and a discriminating network, and th...

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 an adversarial neural network-based infrared image super-resolution method, which is applied to embedded equipment and comprises the following steps of: A1, acquiring a plurality of low-resolution initial infrared images, and inputting the low-resolution initial infrared images into a generative network to obtain corresponding high-resolution images; A2, inputting the high-resolution image into a discrimination network, and discriminating the high-resolution image; A3, inputting the high-resolution image and the initial infrared image into a discrimination network together, and discriminating the high-resolution image and the initial infrared image respectively; executing the steps A1-A3 circularly, so that the generative network and the discriminant network conform to respective training conditions at the same time, and the training process is completed; and inputting the low-resolution infrared image into the trained generative network to output a high-resolution infrared image. The method has the beneficial effects that the structure of the super-resolution method disclosed by the invention is particularly designed for embedded equipment, so that the contour of the image quality is clear, and the image is clearer.

Description

Technical field [0001] The present invention relates to an image super-resolution technique, and more particularly to an infrared image super-resolution method based on counter neural network. Background technique [0002] Infrared imaging technology is a wide range of high technology. Everything can radiate infrared rays, so the infrared image is measured by the detector itself and the infrared line between the object itself and the background, and the infrared image can be obtained. The information, feature distribution, signal-to-noise ratio, clarity, etc., and visible light images are distinguished, and the infrared imaging technology has many applications in civil or military. Infrared imaging has a lot of advantages that wear smoky fog and the detection distance is far. However, infrared imaging is a low resolution picture of the visible light image. When we analyze the infrared picture, the target detection, due to the less information on the scenery of the infrared pictur...

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): G06T3/40
CPCG06T3/4046G06T3/4053
Inventor 肖琳王海伟付泽强刘文豪
Owner 数量级(上海)信息技术有限公司
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