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

Method for tracking depth image

A technology of depth image and image, which is applied in the field of computer vision stereoscopic video, can solve problems such as blurred object edges, zigzags, and mismatching points in depth maps, and achieve the effects of improving efficiency, avoiding block effects, and improving blur effects

Inactive Publication Date: 2011-08-24
无锡景象数字技术有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] During the implementation of the present invention, the inventor found that the existing technology has the following problems: the depth map tracked by the motion estimation method based on block matching has a large block effect, which often makes the boundary of the object become zigzag However, the depth map obtained by the motion estimation method based on the optical flow method has mismatching points, so that there are many "snowflake points" near the edge of the object.
The existing bilateral filtering method does not have the problem of block effect and mismatch, but it will make the edge of the object blurred, and the more obvious is the narrow and long transition area like "comet tail".

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
  • Method for tracking depth image
  • Method for tracking depth image
  • Method for tracking depth image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be further described below in conjunction with drawings and embodiments.

[0022] In this implementation case, the selection of relevant parameters is as follows: alpha=8, wsize=9 (this value is related to the maximum movement distance of two frames of images, the greater the movement, the greater the value should be), MAX_CLR_DIF=10000 (the value It is related to the estimation accuracy, if the value is too small, there will be many points that cannot estimate the depth during bilateral filtering, and if the value is too large, the filtering effect will be lost), the block size is 8 during motion compensation, and the motion search range is 20. wsize is an algorithm input parameter, and its value is generally between 3 and 19. The alpha value is used to measure the filtering degree of the bilateral filter. The smaller the value, the larger the proportion of the depth of the point with the smaller color difference.

[0023] Such as figure 2...

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 tracking a depth image, which belongs to the field of computer visual three-dimensional videos. The method comprises the following steps of: acquiring two frames of images p and q, and the depth image of the p; acquiring an estimated depth image of the q by using an improved bilateral filtering algorithm first; and then modifying the estimated depth image of the q by using a motion compensation algorithm based on block matching so as to acquire an accurate depth image of the q. The method can acquire a very accurate depth image, so the efficiency of manufacturing a three-dimensional video.

Description

technical field [0001] The invention relates to a method for tracking dense depth images in stereoscopic video production, and belongs to the field of computer vision stereoscopic video. Background technique [0002] With the development of computer technology, flat video can no longer meet people's needs for expressing the world, and the research of stereoscopic video has become a hot spot. [0003] The biggest difference between stereoscopic video and ordinary planar video is that stereoscopic video contains depth information, that is, the distance between the object in the video and the observer, which is impossible in planar video. However, in the production of stereoscopic video, the cost of obtaining depth images is also very high, so it is necessary to study how to use limited depth images to obtain more depth images. [0004] Currently, there are two main methods for depth image tracking, motion estimation and bilateral filtering. The motion estimation method inclu...

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): G06T7/20G06T7/00
Inventor 戴琼海黎政曹汛刘晓冬刘磊
Owner 无锡景象数字技术有限公司
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