Multi-scale geometric analysis super-resolution processing method of video blurred image

A technology of fuzzy images and processing methods, applied in image data processing, image enhancement, closed-circuit television systems, etc., can solve problems such as strong noise, weak texture, and ineffective clearing, and achieve improved resolution, improved resolution, and clarity degree of effect

Inactive Publication Date: 2009-12-23
江苏巨来信息科技有限公司
View PDF0 Cites 68 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] Aiming at the shortcomings of the existing fuzzy image processing technology that cannot be effectively cleared in the case of strong noise and weak texture, the present invention provides a super vision based on MGT (multi-scale geometric transformation, the same below) domain decomposition and reconstruction and HyperBF neural network A New Method for Super-resolution Reconstruction of Blurred Images Combining Degree Interpolation

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
  • Multi-scale geometric analysis super-resolution processing method of video blurred image
  • Multi-scale geometric analysis super-resolution processing method of video blurred image
  • Multi-scale geometric analysis super-resolution processing method of video blurred image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Depending on whether the acquired suspicious video blurred image is a single frame or multiple frames, the technical solution of the present invention can be divided into super-resolution reconstruction for a single-frame blurred image and super-resolution reconstruction for a sequence of blurred images, which are respectively described below:

[0039] 1. Schematic diagram of multi-scale geometric analysis super-resolution processing method for single-frame fuzzy image based on HyperBF interpolation in MGT domain. figure 1 As shown, the processing steps are as follows:

[0040] (1) Perform NSCT decomposition on the input blurred image

[0041] Drawing on the direction-specific mechanism of the dual-channel theory of human vision, combined with the multi-directionality and physiological "optimality" of NSCT decomposition, the multi-scale decomposition of the input blurred image is performed.

[0042] An image is decomposed into low-frequency coefficients and high-freque...

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 multi-scale geometric analysis super-resolution processing method of a video blurred image, belonging to the technical field of intelligent information processing. Single-frame blurred images or multi-frame blurred images are acquired by surveillance videos, the input blurred images are decomposed into low-frequency coefficients and high-frequency coefficients by NSCT, the blurred images are de-noised by an HMT model in the NSCT domain, edge details are enhanced by visual suppression networks, sub-band images with low-frequency coefficients and high-frequency coefficients are interpolated nonlinearly by a HyperBF neural network model, the processed NSCT decompression coefficients are reconstructed by NSCT, and the multi-scale Retinex algorithm is introduced to regulate the image contrast in accordance with human eye visual consciousness. The processing of multi-frame blurred images is based on an image fusion method in the MGT domain and a non-uniform interpolation method in the MGT domain. Without changing the hardware of traditional video surveillance imaging system, the method can effectively restrain common noise in video images and further improve the resolution and the definition of the blurred images.

Description

technical field [0001] The invention belongs to the technical field of intelligent information processing, and specifically relates to a physiological "optimum" directional decomposition and reconstruction of multi-scale geometric analysis and a HyperBF (hyper basis function, the same below) based on the super visual acuity mechanism of biological vision. ) A method for super-resolution processing of low-resolution fuzzy images combined with neural network directional prediction interpolation. Background technique [0002] At present, video surveillance and video recording systems have been widely used in daily life. Cameras and surveillance video recording systems are installed in many public places such as banks, toll stations, shopping malls, supermarkets, expressways, factories, and residential quarters. While ensuring and supervising public safety, surveillance video will also store a large amount of information and traces of criminals committing crimes, thus providing ...

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): G06T5/00H04N7/18
Inventor 霍冠英李庆武徐立中
Owner 江苏巨来信息科技有限公司
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