Depth extraction method of merging motion information and geometric information
A technology of geometric information and depth extraction, applied in image communication, image data processing, instruments, etc., can solve the problem that two-dimensional video sources cannot be applied to stereoscopic display systems, and the cost is high
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0110] (1) The Hall Monitor test code stream with an image resolution of 352×288 is used as a 2D video file to generate a depth map. Figure 4 It is a screenshot of the Hall Monitor video.
[0111] (2) Establish a statistical background model and generate a background image. Figure 5 It is the background image modeled for the Hall Monitor video.
[0112] (3) By comparing with the background image, detect the moving foreground of the Hall Monitor video, binarize the separated foreground and background, and perform median filtering and mathematical morphology filtering. Figure 6 that is Figure 4 The binary image of the separated background and background after filtering corresponding to the video screenshot;
[0113] (4) For the background image obtained by background modeling, a method based on scene geometric information is used to generate a geometric depth map. Figure 7 that is Figure 5 The geometric depth map of the background image.
[0114] (5) Obtain the motio...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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