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

A Visual Saliency Extraction Method of Stereo Image Based on Sparse Representation in Frequency Domain

A technique of stereoscopic image, sparse representation, applied in instrumentation, computing, character and pattern recognition, etc., can solve problems such as staying

Active Publication Date: 2020-06-26
深圳牧野微电子技术有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current visual saliency extraction method for stereo images still stays on the visual saliency extraction method for planar 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
  • A Visual Saliency Extraction Method of Stereo Image Based on Sparse Representation in Frequency Domain
  • A Visual Saliency Extraction Method of Stereo Image Based on Sparse Representation in Frequency Domain
  • A Visual Saliency Extraction Method of Stereo Image Based on Sparse Representation in Frequency Domain

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0029] A method for visually salient extraction of stereoscopic images based on frequency-domain sparse representation proposed by the present invention, its overall realization block diagram is as follows figure 1 shown, which includes the following steps:

[0030] ① For any test stereo image S test , the S test The left-viewpoint image of is transformed into the Lab color space, and the size is transformed to 200×200 pixel size, and the transformed image is denoted as {L Lab200 (x 1 ,y 1 )}; then put {L Lab200 (x 1 ,y 1 )}'s L-channel image, a-channel image, and b-channel image are correspondingly denoted as {L Lab200,L (x 1 ,y 1 )}, {L Lab200,a (x 1 ,y 1 )}, {L Lab200,b (x 1 ,y 1 )}; among them, S test The width is W, S test The height is H, 1≤x 1 ≤200, 1≤y 1 ≤200, L Lab200 (x 1 ,y 1 ) means {L Lab200 (x 1 ,y 1 )} ...

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 stereoscopic image visual saliency extraction method based on frequency domain sparse representation, which acquires a small-sized three-channel image and a small-sized normalized disparity map of a left viewpoint image of a test stereoscopic image; for the three-channel image and The normalized disparity map is divided into blocks to obtain the matrix corresponding to the block image; the four matrices are composed of a quaternion matrix, and the transformed quaternion matrix is ​​obtained after the two-dimensional quaternion Fourier transform, and according to the real part and the three The low-frequency component of the imaginary part is used to obtain the low-frequency component map; the sparse weight matrix of the low-frequency component map is extracted with a sparse representation dictionary; according to the sparse weight matrix and the center preference image, two prominent images around the center are obtained; two prominent images around the center are blurred , and then fused to obtain a fused image; use the center preference image to strengthen the center of the fused image; the image around the center is enhanced to obtain a visually significant image after size conversion; the advantage is that it has strong extraction stability and high extraction accuracy.

Description

technical field [0001] The invention relates to an image signal processing method, in particular to a method for extracting stereoscopic image visual salience based on frequency domain sparse representation. Background technique [0002] After people receive natural images, because the human brain needs to treat different levels of information resources differently, when processing natural image information, people will classify different information to show the characteristics of selection. When people watch an image or a video clip, their attention is not evenly distributed to each area of ​​the image, but the semantic information part that is more interesting is prioritized. Calculating salient regions of images is an important research content in the field of computer vision and content-based video detection. With the rapid development of stereoscopic image projection and acquisition equipment, visual saliency detection of stereoscopic images has become a very important...

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): G06K9/46
CPCG06V10/464G06V10/513G06V10/40
Inventor 周武杰蔡星宇张爽爽顾鹏笠潘婷郑飘飘吕思嘉袁建中陈昱臻胡慧敏金国英王建芬王新华孙丽慧吴洁雯
Owner 深圳牧野微电子技术有限公司
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