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

Three-dimensional scene reconstruction method based on picture

A technology of three-dimensional scenes and pictures, applied in the field of three-dimensional scene reconstruction based on pictures, can solve problems such as limited application scenarios, and achieve the effects of low labor cost, simple operation, and low requirements for acquisition equipment

Pending Publication Date: 2018-11-30
王斌
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] But this method needs operator to buy Kinect equipment, needs higher performance computer to process the data that Kinect sends simultaneously
In addition, when using Kinect, the device needs to be connected to a computer, which limits the application scenarios of reconstruction operations
It is precisely because of the above shortcomings that using Kinect to reconstruct 3D model technology can only reconstruct objects or small-scale scene models

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
  • Three-dimensional scene reconstruction method based on picture
  • Three-dimensional scene reconstruction method based on picture
  • Three-dimensional scene reconstruction method based on picture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be further described below in conjunction with specific embodiments. The exemplary embodiments and descriptions of the present invention are used to explain the present invention, but not as a limitation to the present invention.

[0038] Such as figure 1 Shown, technical scheme of the present invention is specified as follows:

[0039] Step 1: Use the SIFT algorithm to find feature points in different scale spaces, and extract their position, size, rotation invariant and other feature values ​​to obtain a sparse point cloud.

[0040] The SIFT feature is based on some local appearance interest points on the object independent of the size and rotation of the image. The tolerance for light, noise, and slight changes in viewing angle is also quite high. Based on these characteristics, they are highly salient and relatively easy to extract, and objects are easily recognized with little misidentification in a feature database with a large number...

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 three-dimensional scene reconstruction method based on a picture. A SIFT (Scale Invariant Feature Transform) algorithm is used for extracting characteristic points in an unordered picture to obtain the spare point cloud data of a model; then, a Bundler+PMVS (Patch-based multi-view environment) algorithm is used for encrypting characteristic points to obtain dense point cloud; and finally, a Poisson interval reconstruction algorithm is used for connecting information points in the point cloud to obtain a final three-dimensional model. Compared with the prior art, the method can use a mobile phone or a camera to shoot a picture which needs to reconstruct the model to reduce true three-dimensional model characteristics including the form, the color, the surface texture and the like, of the model.

Description

technical field [0001] The invention relates to the technical field of three-dimensional reconstruction of pictures, in particular to a three-dimensional scene reconstruction method based on pictures. Background technique [0002] With the development of computer graphics and computer vision technology, 3D reconstruction technology is widely used in medicine, virtual reality, 3D measurement, computer animation, industrial inspection and geology. Image-based 3D reconstruction technology is the process of extracting the required 2D information from the obtained images, and recovering the 3D information of the object through related technologies such as camera calibration, feature point extraction, feature matching, and 3D reconstruction algorithms. [0003] At present, a large number of institutions at home and abroad are conducting research with the help of Kinect. Users need to hold the kinect device and scan the objects or scenes that need to be reconstructed. The computer ...

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): G06T17/00G06K9/46
CPCG06T17/00G06T2207/10028G06V10/462
Inventor 王斌杨晓春张鑫
Owner 王斌
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