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

Compressed-sensing-based de-artifact fusion method of high-dynamic-range image

A high dynamic range, compressed sensing technology, applied in image enhancement, image analysis, image data processing and other directions, can solve image artifacts, blur and other problems, to solve artifacts or blur, save storage space, reduce sampling rate and The effect of computational complexity

Active Publication Date: 2018-02-23
SUN YAT SEN UNIV +2
View PDF6 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention effectively reduces the sampling rate and computational complexity of the image acquisition end, saves storage space, and solves the phenomenon of artifacts or blurring in existing fused images

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
  • Compressed-sensing-based de-artifact fusion method of high-dynamic-range image
  • Compressed-sensing-based de-artifact fusion method of high-dynamic-range image
  • Compressed-sensing-based de-artifact fusion method of high-dynamic-range image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0098] The present invention will be further elaborated below in conjunction with the accompanying drawings.

[0099] like figure 1 As shown, the present invention is based on the K-SVD dictionary learning and the high dynamic range image de-artifact fusion method of compressed sensing: 1) carry out block compression sampling to the input multi-exposure image sequence; 2) use normal Orthogonal Matching Pursuit (OMP) realizes the reconstruction of LDR image sequence; 3) Use PatchMatch and rank minimization algorithm to de-artifact fusion of high dynamic range image for multi-exposure image sequence after compressed sensing.

[0100] Each step is described in detail below:

[0101] 1) if Figure 5 Shown is a multi-exposure image sequence of a dynamic scene, with compression sampling and reconstruction of the input multi-exposure image sequence.

[0102] 11) Taking the currently input LDR image as a reference, carry out K-SVD dictionary learning to obtain a super-complete dict...

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 compressed-sensing-based de-artifact fusion method of a high-dynamic-range image. Compressed sampling is carried out on an inputted multi-exposure image sequence; reconstruction is carried out by using a reconstruction method to obtain multi-exposure image sequence after compressed sensing; and then an image set after compressed sensing is normalized, multi-exposure imagede-artifact fusion based on PatchMatch and a rank minimization algorithm is carried out on the image set to obtain a high-dynamic-range (HDR) image of a target. According to the invention, on the basis of latest research results of K-SVD dictionary learning, compressed sensing and de-artifact fusion, the sampling rate, the storage space and the computational complexity are reduced effectively; and a de-artifact de-blurring HDR image is obtained.

Description

technical field [0001] The invention relates to a method for synthesizing a low dynamic range image into a high dynamic range image, in particular, it relates to a low dynamic range image using K-SVD dictionary learning, compressed sensing and anti-artifact fusion algorithm to complete multiple exposures Compressive sensing and fusion of sequences, and finally methods for generating high dynamic range images without artifacts. Background technique [0002] High dynamic range imaging has started to become a commercial product, such as HDR cameras, HDR TVs, etc. In the same real scene, the limited dynamic range of most imaging sensors often cannot capture the brightness of the full dynamic range of the scene. However, a relatively simple and cheap way can solve this limitation, which is to capture several pairs of the same scene with different exposure times The images are then fused into a high dynamic range image that records the brightness of the scene, thus effectively ex...

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): G06T5/50G06T7/30
CPCG06T5/50G06T2207/20208G06T2207/20221G06T7/30
Inventor 谭洪舟吴炆芳朱雄泳陈荣军谢舜道刘付康
Owner SUN YAT SEN UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com