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

Depth representing method based on light stream and image segmentation

An image segmentation and optical flow technology, applied in image communication, electrical components, stereo system, etc., can solve the problems of noise and block effect

Active Publication Date: 2010-06-30
万维显示科技(深圳)有限公司
View PDF0 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the window matching method is simple, it often has a lot of noise and block effects, while the optical flow method can obtain the motion information of the object more accurately.

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
  • Depth representing method based on light stream and image segmentation
  • Depth representing method based on light stream and image segmentation
  • Depth representing method based on light stream and image segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0103] (1) The Akko&Kayo_p00026 test code stream with an image resolution of 640×480 is used as the 2D video file to be converted. Figure 4 It is a screenshot of Akko&Kayo_p00026 video.

[0104] (2) For each frame image in the original two-dimensional video, refer to its next adjacent frame image in the time direction, perform optical flow analysis, and obtain the optical flow map of the current image. Figure 5 that is Figure 4 Video screenshot Optical flow diagram obtained by optical flow analysis.

[0105] (3) Image segmentation is performed on each frame image in the original two-dimensional video to obtain a segmentation map. Figure 6 that is Figure 4 Segmentation map obtained by segmenting video screenshot images.

[0106] (4) Combining the optical flow map and segmentation map corresponding to each frame image in the original 2D video to obtain a depth map for the expression of 3D video. Figure 7 is the combination Figure 5 optical flow map and Figure 6 De...

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 depth representing method based on light stream and image segmentation, which comprises the following steps: (1) for each frame image in an original two-dimensional video, referring an adjacent latter frame image in the time direction, carrying out light stream analysis, and obtaining a light stream map of the current image; (2) carrying out image segmentation on each frame image in the original two-dimensional video to obtain a segmentation map; and (3) combining the light stream map and the segmentation map of each frame image in the original two-dimensional video to obtain the depth map for representing the three-dimensional video. The invention extracts the motion information of the two-dimensional video by a light stream analyzing method, is more accurate compared with a window matching method, simultaneously combines the image segmentation method to generate the depth map for representing the three-dimensional video, effectively smoothes the noise, and modifies the edge contour of an object.

Description

technical field [0001] The invention relates to a depth representation method when converting a two-dimensional video into a three-dimensional video, in particular to a depth representation method based on optical flow and image segmentation. Background technique [0002] With the continuous development of digital TV technology, the traditional two-dimensional picture can not meet people's requirements for visual enjoyment, and three-dimensional TV with its vivid and lifelike scenes can give people an immersive feeling, and it is becoming more and more important for the future development of digital TV. of a trend. [0003] What 3D TV uses is a kind of film source that is different from traditional 2D TV, and it usually requires more than 2 channels of video for the special 3D video needed for final composite display. There are roughly two approaches in this film source production process: one is to directly produce 3D video with a stereo camera, but this method is expensiv...

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 黄晓军李东晓张明
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