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

Membrane Optimization Method and Dictionary Training Method for Light Field Camera Based on Compressive Sensing

A light field camera and compressive sensing technology, used in color TV parts, TV system parts, instruments, etc., can solve the problems of computer technology with a large amount of calculation, failure to verify theories, etc., to optimize observation, increase Effects of non-correlated, good reconstruction quality

Active Publication Date: 2019-02-12
BEIJING UNIV OF TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the large amount of calculation and the immature computer technology, the theory could not be verified at that 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
  • Membrane Optimization Method and Dictionary Training Method for Light Field Camera Based on Compressive Sensing
  • Membrane Optimization Method and Dictionary Training Method for Light Field Camera Based on Compressive Sensing
  • Membrane Optimization Method and Dictionary Training Method for Light Field Camera Based on Compressive Sensing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Such as Figure 7 As shown, this film optimization method based on compressed sensing light field camera includes the following steps:

[0028] (1) Use the KSVD algorithm to perform dictionary training from the sample library;

[0029] (2) Using the non-correlation of observation P and dictionary D, as well as the specific structure of observation, calculate the optimized membrane;

[0030] (3) Observation and sampling of four-dimensional light field data with membrane;

[0031] (4) Reconstruct the sparse coefficients from the observed two-dimensional image data;

[0032] (5) Reconstruct 4D light field data from sparse coefficients.

[0033] In the case of a fixed film, the present invention designs and optimizes the training dictionary to increase the non-correlation between the observation and the dictionary, reduces the storage space of the light field and has simple acquisition equipment, and optimizes the observation to obtain better Rebuild quality.

[0034] ...

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 light field camera film optimizing method and dictionary training method based on compressed sensing. The film optimizing method comprises steps of: (1) performing dictionary training from a sample database by using a KSVD algorithm; (2) computing an optimized film by using observation P and dictionary D non correlation and an observed specific structure; (3) performing observation sampling on four-dimensional light field data by using the film; (4) reconstructing four-dimensional light field data from observed two-dimensional image data; and (5) reconstructing four-dimensional light field data by a sparse coefficient. The dictionary training method comprises steps of: (1) using a random film and generating an observation matrix in specific structure according to the film; (2) training an optimized dictionary by using observation P and dictionary D non correlation; (3) performing observation sampling on four-dimensional light field data by using the film; (4) reconstructing four-dimensional light field data from observed two-dimensional image data; and (5) reconstructing four-dimensional light field data by a sparse coefficient.

Description

technical field [0001] The invention belongs to the technical field of optimizing light field acquisition and reconstruction, and in particular relates to a film optimization method of a light field camera based on compressed sensing and a training dictionary method thereof. Background technique [0002] With the development and application of light field research, light field has become a new type of multimedia data after sound, image and video. Due to the rapid increase in the size and complexity of light field data, it has brought great pressure to the acquisition, storage and processing of light field. Therefore, effective acquisition and storage methods have far-reaching significance for the light field. [0003] The light field is a parametric representation of the four-dimensional light radiation field, which contains both position and direction information. The pinhole imaging technology used by Ives in the binocular parallax display system more than 100 years ago,...

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): G06T17/00H04N5/232
Inventor 施云惠姚张钰丁文鹏尹宝才
Owner BEIJING UNIV OF TECH
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