Depth image post-processing method

A depth image and image technology, applied in the field of post-processing of depth images, can solve the problem of loss of original image details, achieve the effect of eliminating edge blurring, accurate position, and ensuring edge details

Inactive Publication Date: 2015-04-22
BEIJING JIAOTONG UNIV
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this algorithm overcomes the shortcomings of the first two methods and impro

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] figure 1 It is a schematic diagram of a main flow of a method for post-processing a depth image provided in this embodiment.

[0031] see figure 1 As shown, the method for post-processing a depth image provided in this embodiment mainly includes the following process steps.

[0032] Step 1: Obtain the original depth image d through the machine vision system.

[0033] Step 2: Upsample the original depth image d using a simple difference algorithm, and obtain the depth value information of the upsampled depth image D' and the gradient value information of the color image C. The simple difference algorithm may be a classical interpolation algorithm with low time complexity, for example, a nearest neighbor interpolation algorithm, a bilinear interpolation algorithm, or a bicubic interpolation algorithm.

[0034] Step 3: According to the depth value information of the upsampled depth image D', perform edge detection on the point in D', if the depth value of the point chan...

Embodiment 2

[0038] figure 2 It is a schematic diagram of a boundary line correction process of a depth image post-processing method provided by an embodiment of the present invention.

[0039] This embodiment is a preferred solution of Embodiment 1. Due to the influence of the spatial domain and the pixel value domain, D' has a blurred phenomenon in the boundary area. When detecting the edge, there are many possibilities for the position of the boundary point. It brings many uncertain factors, and there are few common points between the extracted edge and the geometric edge of the matching color image, indicating that the position of the extracted boundary point is very inaccurate, so the obtained boundary map E' also needs Further corrections. To make its edges coincide with the geometric edges of the matching color image, it is necessary to use the gradient value information of the color image to guide the correction process.

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 relates to the field of digital image processing, and discloses a depth image post-processing method. The depth image post-processing method includes the steps that up-sampling is carried out depth images firstly through the adoption of a classic interpolation algorithm with the lower time complexity; two times of post processing including edge line correction and boundary area repairing are carried out on the depth images obtained after up-sampling. By means of the technical scheme, boundaries of the depth images can be coincident with geometrical boundaries of images in corresponding colors through boundary correction while the good subjective visual effect of the up-sampling depth images is improved, the quality of synthesis viewpoints is effectively improved, and the fuzzy boundaries caused by up-sampling are eliminated.

Description

technical field [0001] The invention relates to the field of digital image processing, in particular to a post-processing method of a depth image. Background technique [0002] Obtaining the distance of a 3D scene relative to the camera is one of the most basic contents in computer vision research. The distance of each point in the scene relative to the camera can be represented by a depth image, that is, the pixel value of a point in the depth image represents a certain point in the corresponding scene. The distance of a point relative to the camera. Depth images represent the third-dimensional information of objects, so they have important applications in researches such as 3D reconstruction, pattern recognition, and human-computer interaction. [0003] At present, the technology of machine vision system to obtain scene depth image can be divided into two categories: passive light method and active light method. The basic principle of the passive light method is to obser...

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 林春雨袁艺天赵耀刘美琴白慧慧
Owner BEIJING JIAOTONG UNIV
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