Check patentability & draft patents in minutes with Patsnap Eureka AI!

Depth image post-processing method

A depth image and pixel technology, applied in image data processing, image enhancement, image analysis, etc., can solve problems such as poor operation effect, and achieve good filling effect and smooth object edge effect

Active Publication Date: 2019-07-30
ZHEJIANG UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention aims at the problem existing in the post-processing of the existing binocular depth reconstruction, that is, the effect of directly using the interpolation operation on the disparity map with various holes is not good, and proposes a new method

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 image post-processing method
  • Depth image post-processing method
  • Depth image post-processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0022] The present invention is a post-processing method of a depth image, comprising the following steps:

[0023] 1) small hole filling;

[0024] For the sparse small holes in the disparity map Disp, design a 5*5 circular filling template C, use this template to traverse each pixel in Disp, and obtain the maximum parallax value of the pixels covered by the circular filling template C, and use it as The disparity value Disp(x,y) of the current pixel. The circular filling template C can well fill the small holes in the disparity map with the disparity values ​​of adjacent pixels, which solves the problem of small holes in the disparity map. The filling formula of the circular filling template C is as follows, where Disp represents the disparity map, (x, y) represents the coordinates of each pixel in the disparity map, x and y represent the h...

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

A depth image post-processing method comprises the following steps: (1) small hole filling: filling small holes with parallax values of adjacent pixels by using a circular filling template; (2) filling of large holes: filling of large holes is carried out by using a square closed template, meanwhile, discrete object edges are closed, and the edges are kept smooth; (3) edge contraction: contractingthe edge of the expanded object in the step (2) by using a square template; and (4) Mask filling: filling the result obtained in the step (3) in the step (2) into the cavity of the disparity map after the operation in the step (1), and keeping the details of the disparity map. Through the four steps, holes with different sizes in the disparity map can be effectively filled, and a smooth object edge is obtained.

Description

technical field [0001] The invention relates to a post-processing method of a depth image. Background technique [0002] As one of the popular development directions of computer vision, the field of depth reconstruction has developed rapidly in the past few years. Compared with other methods of obtaining depth information, such as radar ranging, TOF camera, etc., the binocular depth reconstruction system only needs two ordinary cameras, the equipment requirements are simple, and the cost is lower. In many fields such as robot navigation, intelligent driving and Virtual reality has more application value. [0003] Traditional binocular reconstruction methods are mainly divided into local stereo matching methods and global stereo matching methods. The local stereo matching algorithm is relatively simple to implement, with a small amount of calculation, and can generally achieve real-time results. Since it only considers local pixels, there are often some abnormalities in the...

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): G06T5/00
CPCG06T2207/20192G06T5/77G06T5/70
Inventor 宋明黎王海阳许睿
Owner ZHEJIANG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com