Two-dimensional image-assisted depth image enhancement method

A depth image, two-dimensional image technology, applied in the field of depth image enhancement based on two-dimensional image assistance, can solve problems such as poor effect, achieve the effect of suppressing noise, ensuring depth uniformity, and clear edges

Inactive Publication Date: 2017-02-15
NANJING UNIV OF SCI & TECH
View PDF2 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is fast and simple to implement, but it is not effe

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
  • Two-dimensional image-assisted depth image enhancement method
  • Two-dimensional image-assisted depth image enhancement method
  • Two-dimensional image-assisted depth image enhancement method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0060] In order to illustrate the algorithm of the present invention, it is fully demonstrated that the algorithm can not only improve the resolution of the ToF depth image, but also ensure the depth uniformity inside the reconstructed object, make the depth transition between the reconstructed objects discontinuous, and effectively eliminate the The burrs and blurring of the edge make the edge clearer and suppress the noise. The experiment of completing the depth image enhancement is as follows:

[0061] (2) Experimental initial conditions and parameter settings

[0062] Experiments are performed with high-resolution color and depth images of the same scene. The test data set uses the Middlebury public data set (http: / / vision.middlebury.edu / stereo / data.). The resolution of the original high-resolution color image and depth image are both 1390×1110, image 3 The input is a 1390×1110 high-resolution color image and a low-resolution depth map with a downsampling factor of 8 an...

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 two-dimensional image-assisted depth image enhancement method. The method includes the steps of utilizing a ToF camera and a high-resolution color camera to obtain a low-resolution depth image and a high-resolution color image of a same scene, and mapping a low-resolution depth map to a high-resolution color space; constructing data items of an objective function according to reconstruction constraints of a depth image; utilizing edge information of the color image to perform weighting on a regularization model, introducing diffusion tensor to a second-order generalized total variation model, and forming a regularization model for characteristics of the depth image; and solving through iterative reweighting and a primal-dual algorithm, so as to obtain a reconstruction result. The two-dimensional image-assisted depth image enhancement method provided by the invention can effectively solve the problems of low resolution, unclear margin and existence of noise of the depth image, and effectively protects the edge structure of the image.

Description

technical field [0001] The invention relates to a depth image enhancement method acquired by a ToF camera, in particular to a depth image enhancement method based on two-dimensional image assistance. Background technique [0002] In recent years, with the continuous development of 3D technology, many applications such as: human-computer interaction, 3D TV, scene reconstruction, gesture recognition, etc. have put forward higher requirements for obtaining the depth information of the scene. Currently, there are two mainstream ways to obtain in-depth information: passive acquisition and active acquisition. Due to the influence of factors such as light changes, occlusion, and high complexity, passive acquisition cannot meet the needs of most practical applications. The ToF (Time of Flight) camera is widely used in active acquisition, which can collect scene depth information in real time. Its working principle is to measure distance by emitting controllable frequency modulated ...

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): G06T5/00G06T7/13
CPCG06T5/002G06T5/003G06T2207/20192
Inventor 赵高鹏章婷婷陈杰杨滨华李双双薄煜明王建宇曹飞
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap