Low-illumination-image noise reduction method and device

A technology for image noise reduction and low illumination, which is applied in the field of image processing to reduce image noise, ensure color saturation, and improve subjective experience.

Inactive Publication Date: 2018-06-05
SANECHIPS TECH CO LTD
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiment of the present invention expects to provide a low-illuminance image noise reduction method and device, which aims to solve the above-mentioned problems existing in the existing noise reduction methods after low-light image processing, which can effectively reduce image noise and maximize Keep the original information of the image

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 noise reduction method and device
  • Low-illumination-image noise reduction method and device
  • Low-illumination-image noise reduction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 1 As shown, the implementation process of the low-illuminance image noise reduction method in the embodiment of the present invention includes the following steps:

[0041] Step 101: Acquiring low-illumination images;

[0042] Before performing this step, the method further includes: training and learning a reference background image with normal light intensity.

[0043] Here, first of all, according to the image motion estimation algorithm, the moving object and the still object in the image under normal light intensity are separated. Usually, the area where the moving object is located is called the foreground image area, and the area where the still object is located is called the foreground image area. is the background image area; then, the intelligent learning algorithm is used to train and learn the reference background image with normal light intensity. Preferably, the intelligent learning algorithm can adopt the k-means clustering algorithm in ...

Embodiment 2

[0068] The specific implementation process of the low-illuminance image noise reduction method according to the embodiment of the present invention will be further described in detail below.

[0069] figure 2 A schematic diagram of the specific implementation flow of the low-illuminance image noise reduction method in the embodiment of the present invention is given, as shown in figure 2 shown, including the following steps:

[0070] Step 201: collecting monitoring images;

[0071] Step 202: Determine whether the current lighting environment belongs to normal lighting or a low-illumination scene according to the light perception, if it is normal lighting, go to step 203; if it is a low-lighting scene, go to step 205;

[0072] Here, a light sensor may be used to detect the light.

[0073] Step 203: Carry out motion detection background learning on images with normal illumination;

[0074] Here, according to the image motion estimation algorithm, the moving object and the ...

Embodiment 3

[0097] In order to realize the above method, an embodiment of the present invention also provides a low-illuminance image noise reduction device, such as image 3 As shown, the device includes an image acquisition module 301, an area division module 302, and a noise reduction processing module 303; wherein,

[0098] The image acquisition module 301 is configured to acquire low-illuminance images;

[0099] The region division module 302 is configured to divide the low-illuminance image into different texture regions according to different image texture information, and divide the texture regions into foreground image regions and background image regions;

[0100] The noise reduction processing module 303 is configured to respectively perform noise reduction processing on the foreground image area and the background image area using different processing strategies, obtain the processed foreground image area and the background image area, and convert the processed The final fore...

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 noise reduction method. The method includes: acquiring a low-illumination image; segmenting the low-illumination image into different texture regions according to differences of image texture information, and dividing the texture regions into foreground image regions and background image regions; adopting different processing strategies to respectively carry out noise reduction on the foreground image regions and the background image regions to obtain processed foreground image regions and background image regions; and synthesizing the processedforeground image regions and background image regions to obtain a noise-reduced image. The invention also discloses a low-illumination-image noise reduction device.

Description

technical field [0001] The invention relates to image processing technology, in particular to a low-illuminance image noise reduction method and device. Background technique [0002] In recent years, with the popularity of networks and computers, the application of video surveillance equipment to urban public security and smart homes has shown a rapid development trend. At the same time, people have higher and higher requirements for the image quality obtained by video surveillance, that is, they hope to obtain high-definition, low-bit-rate video images. However, low illumination conditions such as night, backlight, and indoor conditions often greatly reduce the performance of video surveillance equipment and reduce the visibility of images obtained by video surveillance equipment, making it difficult to identify key people or objects in the image. Usually, the images taken in the above-mentioned low-illuminance scenes are called low-illumination images, and because the low...

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): G06T5/00
CPCG06T5/00G06T5/002G06T5/003G06T2207/20081
Inventor 刘浩
Owner SANECHIPS TECH CO LTD
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