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

A Grain-Controllable Low-Illumination Image Enhancement Method

A low-illumination, image-based technology, applied in the field of image processing, can solve problems such as high robustness, adaptive adjustment of brightness, and high complexity of enhancement algorithms

Inactive Publication Date: 2017-01-18
HUAQIAO UNIVERSITY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the shortcomings of the previous low-illuminance image enhancement algorithm, such as high complexity, general visual effect, and inability to adjust the brightness according to the scene adaptively, and propose a low-illuminance image enhancement method with controllable granularity, using atmospheric light scattering The model can restore high-quality pictures by adjusting the parameters of the Gaussian filter and the brightness repair factor according to different scenes and brightness. It has a general enhancement effect on videos and images in low-light environments, and has high robustness. After enhancement The visual effect of the image is better

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 Grain-Controllable Low-Illumination Image Enhancement Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] Through observation, it is found that when using a Gaussian filter with a fixed window size and standard deviation, the robustness to detail processing and noise suppression of low-light images is not strong, and when using a fixed brightness repair factor and basic light intensity, it is not robust to The effect of increasing the brightness of each scene is better.

[0048] First define the following variables to facilitate the description of the present invention:

[0049] The size of the entire image to be processed is imagesize: imagesize=Height*Width, where Height is the height of the image, and Width is the width of the image;

[0050] The Gaussian filter is gaussfilter(N,σ), where N is the window size of Gaussian filtering, and σ is the variance of Gaussian filtering;

[0051] Basic light intensity A: the intensity of atmospheric light components. The present invention adopts an adaptive calculation method, which can determine different values ​​according to dif...

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 provides a method for enhancing a granularity-controllable low-illuminance image. The method includes the steps that firstly, an light radiation field of an original low-illuminance image is obtained, then through estimation of the brightness of the original low-illuminance image, an adaptive brightness repair factor omega and basic light intensity A are prepared, and by the utilization of the standard deviation of the light radiation field, two adaptive Gaussian filters are prepared; finally, noise removal and fuzzification are conducted on the light radiation field through the two Gaussian filters and a recovered image is obtained through the adaptive brightness repair factor omega and the basic light intensity A. Due to the fact that an airglow scattering model reflecting the visible light imaging low is adopted, the image recovery effect can meet the human vision characteristic; the Gaussian filters are designed adaptively and the brightness repair factor and the basic light intensity are calculated adaptively, the adaption to scene changes is achieved; the method is suitable for color images, or gray level images or optical images or other spectrum images and has universality.

Description

technical field [0001] The invention relates to a method for enhancing low-illuminance images with controllable granularity, which can be used for single images or continuous videos, belongs to the field of image processing, and relates to scalable computational complexity, adaptive Gaussian filters based on regional consistency, and self-adaptive Image processing methods such as brightness restoration coefficients. Background technique [0002] At present, in order to enhance the safety factor of the people, video surveillance systems are installed in various important places in the society, such as houses, banks, roads, etc., so that once a crime or other emergency occurs, the video surveillance screen can be used. Monitor specific scenarios after the fact or in real time. However, most lawbreakers generally choose night or places with low brightness to carry out criminal activities. At this time, the monitoring system cannot capture a clearer picture because the ambient ...

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): G06T5/00
Inventor 戴声奎孙万源高剑萍
Owner HUAQIAO UNIVERSITY
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