Unlock instant, AI-driven research and patent intelligence for your innovation.

Disparity Estimation Method Based on Classification Frequency Sensitive 3D Self-Organizing Map

A self-organizing mapping and disparity estimation technology, applied in the field of image processing, can solve the problems of large amount of calculation, complex feature extraction, no disparity estimation method, etc., and achieve the effect of good quality and small amount of calculation.

Active Publication Date: 2017-11-10
GUILIN UNIV OF ELECTRONIC TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Such algorithms can only obtain sparse disparity estimates, and feature extraction is more complicated
It can be seen that the current disparity estimation technology is still immature, there is no universal disparity estimation method, and the amount of calculation is huge

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
  • Disparity Estimation Method Based on Classification Frequency Sensitive 3D Self-Organizing Map
  • Disparity Estimation Method Based on Classification Frequency Sensitive 3D Self-Organizing Map
  • Disparity Estimation Method Based on Classification Frequency Sensitive 3D Self-Organizing Map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The content of the present invention will be further described in detail below in conjunction with the examples, but the embodiments of the present invention are not limited thereto.

[0036] A disparity estimation method based on classification frequency-sensitive three-dimensional self-organizing map, comprising the following steps:

[0037] Step 1) Build a training vector set, see figure 1 .

[0038] Step 1.1) Divide each frame of disparity sequence samples into 8×8 sub-blocks to obtain the total training vector set.

[0039] Step 1.2) Classify the image blocks according to the brightness. The number of classifications is determined according to needs. In the invention, the image blocks are divided into two categories, that is, the training vector set of the high-brightness area and the training vector set of the low-brightness area. The classification method can use the equal division method, that is, all image blocks are divided into two categories according to ...

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 parallax estimation method based on classification frequency sensitive three-dimensional self-organizing mapping, and the method comprises the steps: respectively training a low-brightness region and a high-brightness region of a parallax image through employing an FS-DSOM algorithm, and obtaining a low-brightness mode library and a high-brightness mode library in optimal matching; respectively carrying out the parallax mode recognition of the low-brightness region and the high-brightness region of a to-be-estimated parallax image, obtaining a parallax prediction map, and completing the parallax estimation. The obtained parallax prediction map is better in quality, and the calculation burden is small.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a disparity estimation method based on classification frequency-sensitive three-dimensional self-organizing maps. Background technique [0002] As a key technology of stereoscopic video coding, disparity estimation has received more and more attention and attention, and various algorithms have been proposed one after another. Traditional disparity estimation algorithms can be roughly divided into two categories, one is region-based disparity estimation, that is, a certain point or a certain block in an image is used as a basic matching unit, and the corresponding point or block is searched in another image, so that The disparity of each point is obtained, and this type of algorithm can obtain dense disparity estimation. According to different matching strategies, region-based disparity estimation can be divided into local methods and global methods. A representative lo...

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): H04N13/00
CPCH04N13/128H04N13/161H04N2013/0081
Inventor 黎洪松程福林
Owner GUILIN UNIV OF ELECTRONIC TECH