A Compressed Sensing Image Reconstruction Method Based on Multi-view Image

A multi-view image, compressed sensing technology, applied in image enhancement, image analysis, image data processing and other directions, can solve problems such as low image quality

Active Publication Date: 2021-09-14
BEIJING UNIV OF TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] To sum up, the existing multi-viewpoint image reconstruction algorithms obtain low image quality through the under-sampling reconstruction of compressed sensing technology, which has certain limitations.

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 Compressed Sensing Image Reconstruction Method Based on Multi-view Image
  • A Compressed Sensing Image Reconstruction Method Based on Multi-view Image
  • A Compressed Sensing Image Reconstruction Method Based on Multi-view Image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] In order to describe the technical content of the present invention more clearly, further description will be given below in conjunction with specific examples:

[0054] The frame diagram of the present invention is as figure 1 , the specific implementation process is divided into two stages, the constraint condition preparation stage and the joint model reconstruction stage.

[0055] 1. Preparatory stage for constraints

[0056] The preparation phase of constraints is divided into four steps: obtaining reconstructed images and multi-view image sets, generating dynamic image sets, image prediction, and computing low-rank tensor approximations.

[0057] 1. Obtain reconstructed images and multi-viewpoint image sets

[0058] First, the target image i to be reconstructed and its corresponding series of multi-viewpoint image sets are acquired. These image data are very low-quality compressive sensing preliminary reconstruction images.

[0059] 2. Generate a dynamic image...

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 compression sensing image reconstruction method based on multi-viewpoint images. First, for each target reconstruction, the corresponding dynamic image set is selected by calculating the parallax compensation size between images, and then multi-viewpoints are realized based on the selected dynamic image set. Image reconstruction. In the process of reconstruction, high-quality reconstruction results are obtained according to the adaptive total variational regularization constraints based on parallax compensation and non-local low-rank tensor constraints.

Description

Technical field: [0001] The invention relates to the field of computer image processing, in particular to a method for compressive sensing reconstruction based on multi-viewpoint images. Background technique: [0002] In recent years, many emerging applications require cameras to simultaneously record multi-directional images from different perspectives of the same scene, such as surveillance systems, robotics, and medical imaging. In addition, with the widespread application of single-pixel imaging technology, single-pixel cameras will directly generate a series of multi-view compressed sensing images. However, the application of compressed sensing technology to the field of multi-view image reconstruction often has the problem of low image reconstruction quality caused by undersampling, which makes these multi-view images unable to meet the above application requirements. [0003] Compressed sensing reconstruction algorithms for multi-view images have made great progress,...

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
CPCG06T5/007G06T2207/20004
Inventor 王瑾朱佳乐朱青
Owner BEIJING UNIV OF TECH
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