Denoising method of depth image

A technology in depth images and images, applied in the field of image processing, can solve the problems of lack of deep mining of image structure information, loss of detailed information, unsuitable for depth image restoration, etc., achieving robustness, low computational complexity, Simple and efficient method

Inactive Publication Date: 2014-06-25
BEIJING UNIV OF TECH
View PDF4 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method lacks deep mining of image structure information, and the filtered image is too smooth, losing a lot of detail information, especially the edge structure informati

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
  • Denoising method of depth image
  • Denoising method of depth image
  • Denoising method of depth image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Such as image 3 As shown, the denoising method of this depth image includes the following steps:

[0023] (1) Acquire the median filter image

[0024] (2) Obtain the residual image ΔY;

[0025] (3) Obtain the singular point detection template W;

[0026] (4) Obtain a mixed depth image

[0027] (5) Obtain overlapping mixed depth image blocks

[0028] (6) Obtain the dictionary and sparse coefficients;

[0029] (7) Obtain the reconstructed depth image

[0030] The median filtering algorithm has strong robustness to non-Gaussian noise such as singular points, and the computational complexity of the algorithm is low, simple and efficient. interfering pixels) for fast detection and initial repair. The sparse representation dictionary learning model fully exploits the sparse nature of the depth image signal, and can adaptively mine the deep structural information of the image through the dictionary learning method, so this method can better retain the structura...

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 denoising method of a depth image. The denoising method of the depth image is simple and efficient, and has robustness to non-Gaussian noise. The denoising method comprises the steps of (1) acquiring a median filtering image Y, (2) acquiring a residual image delta Y, (3) acquiring a singular point detection template W, (4) acquiring the mixed depth image (please see the specifications for the formula), (5) acquiring overlapped mixed depth image blocks (please see the specifications for the formula), (6) acquiring the dictionary and sparse coefficients, and (7) acquiring a reconstructed depth image (please see the specifications for the formula).

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a denoising method of a depth image. Background technique [0002] The depth image describes the relative spatial position information of the object. In the depth image, the "pixel" value of each point represents the relative distance information of a point on the object in space (that is, the point on the object relative to a certain projection plane distance). Since the depth image can effectively describe the geometric position and structure information of objects in the real world, which cannot be replaced by ordinary optical plane images, the depth image plays an important role in the field of computer vision research and application. In recent years, with the continuous popularization of depth image acquisition, the application of depth image has gradually become a research hotspot, such as the application in multi-angle visual synthesis technology and...

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
Inventor 孙艳丰刘喜恩胡永利
Owner BEIJING UNIV OF 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