An unsupervised learning method and system for low-light image enhancement

An unsupervised learning and image enhancement technology, which is applied in image enhancement, image analysis, image data processing, etc., can solve problems such as too strong loss function design assumptions, underexposure, and poor color restoration, so as to improve brightness and reduce model bad effect

Active Publication Date: 2021-12-21
HANGZHOU INNOVATION RES INST OF BEIJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The calculation speed of this method is fast, but the assumption of the loss function design of this method is too strong, and the enhancement results are prone to problems of poor color restoration and underexposure

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
  • An unsupervised learning method and system for low-light image enhancement
  • An unsupervised learning method and system for low-light image enhancement
  • An unsupervised learning method and system for low-light image enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present application as recited in the appended claims.

[0033] The terminology used in this application is for the purpose of describing particular embodiments only, and is not intended to limit the application. As used in this application and the appended claims, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise.

[0034]In order to reduce the problem that the amount of supervised data is small and difficult to obtain, the present invention designs an unsupervised learning method and system for low-light image enhancement, whi...

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 unsupervised learning method and system for low-light image enhancement, belonging to the field of low-light image enhancement. Aiming at the problem that the amount of supervised data is small and difficult to obtain, the present invention firstly constructs a training set of unpaired samples, and secondly considers the brightness and semantic information of the image to construct the generator and discriminator of the generative adversarial network, and input the low-light images in the training set to generate In the discriminator, the enhanced image is input to the discriminator, the authenticity of the input image is discriminated; the optimized network parameters are updated by minimizing the loss function, and the trained model is obtained; finally, the trained generative adversarial network is used to deal with the low The illumination image is enhanced to obtain an enhanced image. The method can regularize the unpaired training based on the brightness and semantic segmentation information of the input image, so as to reduce the problem of poor model effect due to lack of supervision information, and the present invention can also solve the problem of overexposure and uneven color distribution after image enhancement. question.

Description

technical field [0001] The invention belongs to the field of low-light image enhancement, and relates to a non-supervised learning method and system for low-light image enhancement, which can be widely applied to various low-light scenes that need to increase the brightness of images or videos to improve visibility. Background technique [0002] With the development of photographic technology, image quality has greatly improved in terms of resolution and clarity. However, due to unavoidable environmental or technical limitations, images captured under non-uniform lighting environments are still affected by low-light conditions, resulting in low visibility. Images in low-light environments are important analysis data in many scenes, so nighttime surveillance video / image enhancement processing is the key to fully maximizing the effectiveness of video surveillance systems, and it is also the premise of applying intelligent systems based on computer vision algorithms at night ....

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): G06T5/00G06N3/04
CPCG06T5/007G06T2207/20081G06N3/045
Inventor 罗喜伶王雪檬潘洋洋
Owner HANGZHOU INNOVATION RES INST OF BEIJING UNIV OF AERONAUTICS & ASTRONAUTICS
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