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

A method for obtaining non-key frame depth images and a 2D video stereoscopic method

A non-key frame, depth image technology, applied in the field of image processing, can solve the problems of video image quality degradation, reduce the accuracy of depth image transmission, etc., and achieve the effect of improving quality

Inactive Publication Date: 2017-09-26
XIDIAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The accuracy of the depth image is highly dependent on the motion estimation vector, and the error of the motion estimation greatly reduces the accuracy of the depth image propagation, resulting in the degradation of the image quality of the video after converting to 3D video based on the depth 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
  • A method for obtaining non-key frame depth images and a 2D video stereoscopic method
  • A method for obtaining non-key frame depth images and a 2D video stereoscopic method
  • A method for obtaining non-key frame depth images and a 2D video stereoscopic method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] The present invention provides a method for acquiring a depth image of a non-key frame, the method for acquiring a depth image of a non-key frame, such as figure 1 shown, including:

[0068] 01. Acquire a 2D video, extract a key frame and a non-key frame from the 2D video, and determine a motion vector of the non-key frame relative to the key frame.

[0069] 02. Extract the depth image of the key frame from the 2D video, and determine the initial depth image of the non-key frame in combination with the motion vector.

[0070] 03. In the initial depth image, construct a detection window, perform smoothing and filtering processing on the initial depth image through the detection window, optimize the initial depth image in combination with geodesic distance data, and obtain the non-key frame An optimized depth image of .

[0071] In implementation, in order to obtain a high-quality depth map of a non-key frame based on a depth map of a key frame in a 2D video, the follow...

Embodiment 2

[0145] The present invention provides a method for stereoscopic 2D video based on acquiring depth images of non-key frames, and the method for stereoscopic 2D video includes:

[0146] Acquiring 2D video, extracting key frames and non-key frames from the 2D video, and determining motion vectors of the non-key frames relative to the key frames;

[0147] extracting the depth image of the key frame from the 2D video, and determining the initial depth image of the non-key frame in combination with the motion vector;

[0148] In the initial depth image, construct a detection window, perform smoothing filtering on the initial depth image through the detection window, optimize the initial depth image in combination with geodesic distance data, and obtain the optimized depth of the non-key frame image;

[0149] A virtual view is constructed according to the optimized depth image, and a 3D video corresponding to the 2D video is obtained according to the virtual view.

[0150] In imple...

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 method for acquiring a non-key frame depth image and a 2D video stereoscopic method, belonging to the field of image processing. The invention includes obtaining the motion vector of the non-key frame relative to the key frame in the 2D video, so as to obtain the initial depth image of the non-key frame according to the depth image of the key frame, and then substituting the geodesic distance for smoothing and filtering the initial depth image, Finally, the optimized depth image after processing is obtained. By using the above method, the present invention can improve the defect that the depth image obtained in the prior art relies too much on the motion estimation vector, resulting in a large error in the motion vector, which reduces the accuracy of the depth image, and at the same time improves the stereoscopic quality of 2D video.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a method for acquiring a non-key frame depth image and a 2D video stereoscopic method. Background technique [0002] In recent years, with the rapid development of 3D stereoscopic (Stereoscopic 3D, S3D) video media technology, the S3D video function brings consumers more vivid and lifelike 3D visual effects, and has become a selling point of high-end TVs today. Unfortunately, according to a recent survey and research, due to the lack of S3D video resources, consumers use S3D video functions for less than 1% of the total TV viewing time in watching 3DTV. Therefore, in order to make up for the shortage of S3D video resources, it is necessary to obtain 3D content by shooting with a 3D stereo camera. [0003] Converting 2D video resources to 3D stereo format is the process of stereoscopic 2D video, that is, by estimating depth images from 2D videos, and generating 3D ster...

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
Inventor 郑喆坤蔡济济陈旭凤崔玉
Owner XIDIAN UNIV
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