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

Depth map up-sampling method and device based on hierarchical clustering and boundary enhancement

A layered clustering and depth map technology, which is applied in image enhancement, image data processing, character and pattern recognition, etc., can solve the problem of poor restoration effect of depth maps with similar colors, so as to prevent depth confusion artifacts and reduce The effect of increasing the number of targets and computing efficiency

Pending Publication Date: 2022-07-15
QUANZHOU INST OF EQUIP MFG
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method does not perform well in inpainting depth maps with similar colors

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 map up-sampling method and device based on hierarchical clustering and boundary enhancement
  • Depth map up-sampling method and device based on hierarchical clustering and boundary enhancement
  • Depth map up-sampling method and device based on hierarchical clustering and boundary enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0107] This embodiment provides a depth map upsampling method based on hierarchical clustering and boundary enhancement, such as figure 1 shown, including: image preprocessing process and hierarchical depth map upsampling process;

[0108] The image preprocessing process includes:

[0109] The low-resolution depth map is preprocessed and divided into continuous depth regions and discontinuous depth regions, and the preprocessed depth map D is obtained. I ; The pixel that is positioned at the described depth continuous area is used as the seed pixel for interpolation; The pixel that is positioned at the described depth discontinuous area is used as the target pixel, and the target pixel interpolation is carried out by the seed pixel;

[0110] Use the initial sketch map model to process the high-resolution color image to obtain an original sketch and a sketchable image, and use the sketchable image to smooth the high-resolution color image to achieve fast and effective clusteri...

Embodiment 2

[0127] In this embodiment, a depth map upsampling device based on hierarchical clustering and boundary enhancement is provided, such as Image 6 As shown, including: image preprocessing module and hierarchical depth map upsampling module;

[0128] The image preprocessing module is used to preprocess the low-resolution depth map, and divide it into a depth continuous region and a depth discontinuous region to obtain a preprocessed depth map D I ; The pixel that is positioned at the described depth continuous area is used as seed pixel for interpolation; The pixel that is positioned at the described depth discontinuous area is used as the target pixel, and the target pixel interpolation is carried out by the seed pixel; Utilize the initial sketch map model to high Distinguish the color image for processing to obtain an original sketch and a sketchable image, and use the sketchable image to smooth the high-resolution color image to achieve fast and effective clustering; Describe...

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 map up-sampling method and device based on hierarchical clustering and boundary enhancement, and relates to the technical field of depth map up-sampling. According to the method, the low-resolution depth map is preprocessed and divided into the depth continuous region and the depth discontinuous region, the seed pixels of the depth continuous region are directly interpolated, the target pixels of the depth discontinuous region need to be processed, the number of targets is reduced, and the calculation efficiency is improved. In addition, an initial sketch map algorithm is used for preprocessing the high-resolution color image, an anisotropic filter is used for obtaining a smooth uniform area and an enhanced image boundary, and for a depth discontinuous area with similar colors, boundary information of a sketch map is used for processing, so that subsequent fine image segmentation is facilitated. When depth map up-sampling is carried out, a hierarchical classification up-sampling method is provided, classification interpolation can be carried out on target pixels, and depth confusion artifacts of depth discontinuous areas are effectively prevented.

Description

technical field [0001] The present invention relates to the technical field of depth map upsampling, in particular to a depth map upsampling method and device based on hierarchical clustering and boundary enhancement. Background technique [0002] In recent years, the collection of 3D depth information has played an important role in various 3D applications, such as intelligent human-computer interaction, 3D scene reconstruction, and autonomous robot navigation. However, due to high manufacturing costs, the resolution of depth sensors has developed slowly and lagged far behind demand. The laser scanning method is not suitable for real-time applications and the equipment is very expensive, while the passive stereo vision method can neither eliminate occlusion nor solve the problem of lack of texture in the rendering process. Fusion camera systems consisting of color cameras and depth sensors are widely used for depth acquisition due to their low cost. Typical depth cameras ...

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 Applications(China)
IPC IPC(8): G06V10/762G06V10/26G06V10/764G06K9/62G06T5/00G06T5/50
CPCG06T5/50G06T2207/20192G06T2207/20028G06T2207/20221G06F18/231G06F18/24G06T5/70
Inventor 方立沈慧芳张静茹周树东刘金洲
Owner QUANZHOU INST OF EQUIP MFG
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