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

Time domain consistency depth video estimation method based on self-adaptive weight

An adaptive weight and depth video technology, applied in image communication, electrical components, stereo systems, etc., can solve problems such as time domain inconsistency, depth video quality degradation, and observer discomfort, and achieve time domain continuity The effect of improving and improving quality

Active Publication Date: 2015-12-23
TIANJIN UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If the depth estimation algorithm for images is directly transplanted into the process of depth video estimation, ignoring the correlation between adjacent video frames, it will lead to the degradation of depth video quality and inconsistency in time domain
The temporal inconsistency of the depth video caused by the single-frame independent depth estimation method will cause the discontinuity effect of the virtual viewpoint video, which in turn will cause the quality degradation of the virtual viewpoint and the discomfort of the observer.

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
  • Time domain consistency depth video estimation method based on self-adaptive weight
  • Time domain consistency depth video estimation method based on self-adaptive weight
  • Time domain consistency depth video estimation method based on self-adaptive weight

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The purpose of the present invention is to aim at the problem of depth video estimation, according to the basic framework of energy function minimization, use the motion information between frames to construct the time domain item of adaptive weight, and update the energy function. The new energy function contains space and time domain information. Through the minimization of the energy function, the time domain continuity of the depth video can be improved, and the quality of the depth video and its drawn virtual viewpoint can be improved at the same time.

[0034] Depth video estimation cannot ignore inter-frame correlation, so temporal correlation information should be introduced into depth estimation. In depth video estimation methods using constant weights, it is often necessary to select different weights for different video inputs in order to obtain better results. At the same time, this method does not significantly improve the quality of depth video and drawing...

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 belongs to the field of video processing technology and three-dimensional display, and discloses a time domain consistency depth video estimation method based on self-adaptive weight. The time domain consistency depth video estimation method aims to increase time domain continuity of depth video through minimization of an energy function, and increase quality of the depth video and drawn virtual viewpoints. Therefore, the invention adopts the technical scheme that the time domain consistency depth video estimation method based on self-adaptive weight comprises the steps of: 1, energy function construction; 2, inter-frame motion estimation; 3, self-adaptive weight calculation; 4, motion-based energy function updating; 5, and energy function minimization. The time domain consistency depth video estimation method is mainly used in video processing applications.

Description

technical field [0001] The invention belongs to the field of video processing technology and stereoscopic display, and relates to a time-domain consistency depth video estimation method based on multi-viewpoint video based on adaptive weight. Specifically, it relates to a temporally consistent depth video estimation method based on adaptive weights. technical background [0002] 3D display technology can provide observers with an immersive visual experience. Compared with the traditional 2D system, the main feature of the 3D system is that it can provide the observer with a deep perception of the scene, and then obtain a stereoscopic experience. Therefore, the acquisition of depth information plays an important role in 3D systems. [0003] Depth data can be directly obtained by shooting with a depth camera, but due to the physical limitations of the device, the resolution of the depth map obtained by this method is often low. In stereo / multi-view systems, depth informatio...

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
IPC IPC(8): H04N13/00
Inventor 雷建军刘建英侯春萍张翠翠梅旭光李乐乐
Owner TIANJIN 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