Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Low-illumination image enhancement method based on conditional re-enhancement network

A technology of network enhancement and image enhancement, applied in image enhancement, image analysis, image data processing and other directions, can solve the problem of inability to deal with low contrast, low brightness and noise and color distortion at the same time

Active Publication Date: 2020-11-06
HARBIN INST OF TECH
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem that the existing low-illuminance image enhancement method needs to manually select the optimal supervision image and manually adjust the parameters, and cannot simultaneously deal with low contrast, low brightness, noise and color distortion, the present invention proposes a condition-based re-enhancement method. Low-light image enhancement method based on network

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
  • Low-illumination image enhancement method based on conditional re-enhancement network
  • Low-illumination image enhancement method based on conditional re-enhancement network
  • Low-illumination image enhancement method based on conditional re-enhancement network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0063] Specific implementation mode one: combine figure 1 To describe this embodiment,

[0064] A low-light image enhancement method based on a conditional re-enhancement network, comprising the following steps:

[0065] Step 1. Design a conditional re-enhancement network based on deep learning. The conditional re-enhancement network can enhance the input low-light image S and output the final enhanced image E;

[0066] Input the low-light image to be enhanced into the conditional re-enhancement network;

[0067] The input of the conditional re-enhancement network is the low-illumination image S and its maximum channel image S max and its expected maximum channel image S expect_max , S is a matrix of M*N*3, M is the number of rows, N is the number of columns, 3 is {r, g, b} three color channels, S max Obtained by taking the maximum value of the three color channels, it is a matrix of M*N*1, in the test phase, S expect_max Any image enhancement method such as histogram equ...

specific Embodiment approach 2

[0078] Specific implementation mode two: combination figure 2 To describe this embodiment,

[0079] A low-illuminance image enhancement method based on a conditional re-enhancement network described in this embodiment, the conditional re-enhancement network is specifically as follows:

[0080] The input is input to the first convolutional layer and the second convolutional layer respectively, and the first convolutional layer and the second convolutional layer are respectively 9*9 convolutional layer and 3*3 convolutional layer;

[0081] The first convolutional layer is connected to the third convolutional unit, and the third convolutional unit is connected to a ReLU layer after the convolutional layer of 3*3;

[0082] The third convolution unit is connected to the fourth convolution unit, the fourth convolution unit is connected to the fifth convolution unit, the fifth convolution unit is connected to the sixth convolution unit, the fourth convolution unit, the fifth convol...

specific Embodiment approach 3

[0091]A low-illuminance image enhancement method based on a conditional re-enhancement network described in this embodiment, the specific process of the third step includes the following steps:

[0092] Step 31. Extract the maximum value channel image S of the low-illumination image S max :

[0093]

[0094] Among them, S max (i, j) is the maximum channel image S max The i-th row and the j-th column element; max represents the maximum value operation; c is r, g, b, corresponding to the three color channels of red, green and blue in the rgb color space, S c (i,j) is the i-th row and j-th column element of a certain channel of the low-illuminance image S in the rgb color space;

[0095] Step 32: Extract the maximum value channel image H of the normal illumination image H max :

[0096]

[0097] Among them, H max (i, j) is the maximum channel image H max The i-th row and the j-th column element; max represents the maximum value operation; c is r, g, b, corresponding ...

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 low-illumination image enhancement method based on a conditional re-enhancement network, belongs to the field of digital image processing, and aims to solve the problem thatlow contrast, low brightness, noise and color degradation cannot be processed at the same time in an existing low-illumination image enhancement method. According to the enhancement method provided bythe invention, a conditional re-enhancement network is included, input of the network is a low-illumination image and a maximum channel image thereof and an expected maximum channel image thereof, the output of the network is a final enhanced image. The expected maximum value channel image is obtained by adding blurring and noise to the maximum value channel image of the supervision image or performing tone mapping on the maximum value channel image of the low-illumination image in the training stage, and the expected maximum value channel image is the maximum value channel image of the low-illumination image processed by any image enhancement method in the test stage. According to the method, the brightness and contrast of the low-illumination image can be remarkably enhanced, noise is removed, and phenomena of color distortion are reduced. The method can be used for enhancing the low-illumination image.

Description

technical field [0001] The invention belongs to the field of digital image processing, and in particular relates to an enhancement method for low-illuminance images. Background technique [0002] Cameras are important sensing elements for various types of unmanned equipment. However, in many low-light environments, such as nighttime and darkrooms, the captured images often have problems such as low contrast, low brightness, high noise, and color degradation. Recently, methods based on deep learning have achieved good results in various image processing tasks. Currently, in the field of low-light image enhancement, image enhancement methods based on deep learning can be divided into two categories: supervised and unsupervised. [0003] Unsupervised image enhancement method based on deep learning: This type of method does not require pairs of low-illumination images and normal-illumination images, so it does not require too much cost when constructing a training data set, and ...

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): G06T5/00G06T5/40G06T7/90G06K9/62G06N3/04G06N3/08
CPCG06T5/40G06T7/90G06N3/08G06T2207/10004G06T2207/10024G06T2207/20081G06T2207/20084G06N3/048G06N3/045G06F18/214G06T5/90
Inventor 张雨遆晓光张斌闫诗雨李青岩李赟玺王春晖
Owner HARBIN INST 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
Eureka Blog
Learn More
PatSnap group products