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

GPU (Graphics Processing Unit) frame based three-dimensional reconstruction method of dotted line optical flow field

A technology of three-dimensional reconstruction and optical flow field, which is applied in the field of three-dimensional reconstruction of point-line optical flow field based on GPU architecture, which can solve the problem that the unified model has not been established, and achieve the effect of accurate processing.

Inactive Publication Date: 2011-07-20
NANCHANG HANGKONG UNIVERSITY
View PDF1 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the parameter dimensions expressed by pixels and image lines are different, a unified model that can simultaneously reconstruct object point information and contour information has not yet been established.

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0007] The present invention is realized as follows: firstly, a unified model for reconstructing three-dimensional motion and structure based on the optical flow field of pixel points and contour lines is established. Point optical flow is calculated at low resolution, and linear optical flow is calculated at high resolution. The image straight line expression dimension is set to be consistent with the pixel point dimension, so the optical flow field reconstruction of the pixel point and the image straight line can be unified under one 3D reconstruction calculation model. Considering the three-dimensional reconstruction of pixel points and image linear optical flow field at the same time, it can reconstruct the local point information of the object, such as details such as inflection points, corner points, and protrusions. For straight line contours, using the above model reconstruction, curves with large curvature can be approximately fitted by piecewise straight lines, so th...

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 a GPU (Graphics Processing Unit) frame based three-dimensional reconstruction method of a dotted line optical flow field, comprising the following steps of: firstly building a three-dimensional motion and structure uniform model based on pixel point and profile straight-line optical flow field reconstruction; computing point optical flows at a low resolution ratio, and computing straight-line optical flows at a high resolution ratio; setting the straight-line expression dimensions of an image to be consistent with the dimensions of pixel points so as to unify the pixel point and profile straight-line optical flow field reconstruction to one three-dimensional reconstruction computation model; and finally adopting a VC++language programming implementation algorithm. The invention has the technical effects of being capable of fast completing the three-dimensional reconstruction, accurately processing the details of an object and integrally realizing the three-dimensional reconstruction of the object.

Description

technical field [0001] The invention relates to a method for three-dimensional reconstruction of point-line optical flow field, in particular to a method for three-dimensional reconstruction of point-line optical flow field based on GPU framework. Background technique [0002] The real world is three-dimensional. For a long time, due to the limitation of the development level of science and technology, most of the data we can obtain and effectively process and analyze are two-dimensional data, which makes the three-dimensional information of a large number of objects lost. With the development of computer technology, people's access to information has shifted from traditional two-dimensional plane images to three-dimensional images. 3D reconstruction can quickly obtain the shape, color information and texture information of objects, which is an effective way for people to understand the external environment. In recent years, with the rapid development of GPU 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): G06T17/00
Inventor 陈震江少锋危水根
Owner NANCHANG HANGKONG UNIVERSITY
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