Low-light Video Denoising Method Based on Phase Consistency and Scene Motion Estimation

A motion estimation and consistency technology, applied in TV, color TV, color TV parts, etc., can solve problems such as target blur, tailing, long time, etc., to prevent image tailing, improve efficiency, and achieve obvious effects Effect

Active Publication Date: 2018-01-05
南京理工大学智能计算成像研究院有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Because wrong motion estimation will directly lead to blurring or smearing of the filtered target
However, the current traditional motion estimation methods usually need to perform motion estimation operations on all pixels in the image, which often takes a long time

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-light Video Denoising Method Based on Phase Consistency and Scene Motion Estimation
  • Low-light Video Denoising Method Based on Phase Consistency and Scene Motion Estimation
  • Low-light Video Denoising Method Based on Phase Consistency and Scene Motion Estimation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] combine figure 1 , the low-light video denoising method based on phase consistency and scene motion estimation in the present invention first obtains the edge images of the image to be registered and the reference image according to the phase consistency method, and then performs registration on the edge images according to the scene-based registration method Then, the difference between the two images after registration is calculated to find the corresponding pixels of the moving target, and then the motion estimation is performed on all the corresponding pixels of the moving target, so as to find out the corresponding relationship of all pixels between the image to be registered and the reference image , and finally perform a weighted average of all corresponding pixels between the two images, and output after completion. The schematic diagram of the process is as follows figure 1 As shown, the specific implementation steps are as follows:

[0023] Step 1: Read in t...

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-light video denoising method based on phase consistency and scene motion estimation. First, the edge images of the image to be registered and the reference image are obtained according to the phase consistency method, and then the edge images are obtained according to the scene-based registration method. The images are registered, and then the difference between the two registered images is calculated to find the corresponding pixels of the moving target, and then the motion estimation is performed on all the corresponding pixels of the moving target, so as to find out all the pixel points between the image to be registered and the reference image The corresponding relationship between the two images, and finally all the corresponding pixels between the two images are weighted and averaged, and the denoised image is output after completion. The invention can effectively guarantee the registration accuracy to achieve a better denoising effect, especially the denoising effect is obvious for low-light video images containing a lot of noise.

Description

technical field [0001] The invention belongs to the technical field of low-light video image denoising, in particular to a low-light video denoising method based on phase consistency and scene motion estimation. Background technique [0002] Image denoising is a basic technology in the field of image processing. For digital image denoising, there have been a large number of research results at home and abroad, and the research hotspots focus on two aspects: denoising algorithms based on space domain and transform domain. Among them, the spatial domain denoising is to directly process the pixels of the noisy image. Common methods include mean filtering, median filtering and various improved spatial domain denoising methods (see Document 1: Zhang Xuming, Xu Binshi, Dong Shiyun. for Adaptive Median Filtering for Image Processing [J]. Journal of Computer-Aided Design and Graphics, 2005, Vol.17, No.2.295-299). However, since the pixel points of the noisy image are directly proc...

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): H04N5/21H04N5/14
Inventor 张玉珍孙佳嵩陈钱左超顾国华胡岩张良
Owner 南京理工大学智能计算成像研究院有限公司
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