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

Deep image post-processing method

A deep image and post-processing technology, applied in the field of image processing, can solve problems such as blurred object edges, error point diffusion, and inability to distinguish correct points from wrong points.

Active Publication Date: 2012-07-04
万维显示科技(深圳)有限公司
View PDF2 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these filtering methods are limited to a fixed window, and cannot distinguish the correct point and the wrong point in the image, which will easily cause the spread of the wrong point and blur the edge of the object in the image.

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
  • Deep image post-processing method
  • Deep image post-processing method
  • Deep image post-processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0100] (1) The left and right perspective stereo images of Art with an image resolution of 463×370 and the corresponding left and right perspective depth images are used as input images, and the maximum depth DMax=67. image 3 (a) is the left view image of Art, image 3 (b) is the depth image of the left viewpoint of Art, image 3 (c) is the right view image of Art, image 3 (d) is the right-view depth image of Art.

[0101] (2) Set left-right consistency detection error threshold η LR =2, uniqueness detection error threshold η PK = 0.4.

[0102] (3) Take the left viewpoint image as the main viewpoint and the right viewpoint image as the auxiliary viewpoint, and detect credible points and untrustworthy points in the depth image of the left viewpoint. Figure 4 (a) is the credibility-marked image of the left view, where the white areas are untrustworthy points.

[0103] (4) Take the right viewpoint image as the main viewpoint and the left viewpoint image as the auxiliary ...

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 deep image post-processing method, which comprises the following steps of: (1) based on to-be-processed left and right view point three-dimensional images and corresponding left and right view point deep images, taking one view point image as a main view point and the other view point image as an auxiliary view point, and detecting reliable points and unreliable points of the main view point deep image; (2) determining filtering size range for processing the main view point deep image according to the basic size of a filtering window; and (3) carrying out multi-size filtering on the main view point deep image by utilizing the main view point image and the reliability of each pixel in the main view point deep image, retaining reliable points, and gradually correcting the unreliable points. According to the invention, aiming at the deep image generated by a three-dimensional matching algorithm, the unreliable points in the shielding region and low-texture region in the deep image can be quickly and effectively corrected, the object edges can be effectively retained, and the accurate and smooth deep image is obtained.

Description

technical field [0001] The present invention relates to an image processing method, in particular to a depth image post-processing method. Background technique [0002] Objects in the real world are three-dimensional, but general photography technology can only record space objects in two-dimensional form, thus losing the depth information of objects. With the development of computer technology and multimedia technology, more applications need to use the depth information of the scene to truly reproduce the objective world and bring people a three-dimensional experience. At present, naked-eye free stereoscopic TV is booming. It can get rid of the restriction of glasses and watch 3D stereoscopic effect with naked eyes at any viewpoint. The common autostereoscopic display technology uses depth information, uses DIBR (Depth-Image-Based Rendering) algorithm to generate multiple virtual viewpoint images at the reconstruction display end, and finally synthesizes stereoscopic imag...

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): G06T5/00
Inventor 杨青青张静王梁昊李东晓张明
Owner 万维显示科技(深圳)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