Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Generalized stereopair three-dimensional reconstruction method adopting variance component estimation

A technique of variance component estimation and stereo image pairing, which is applied in the field of 3D reconstruction, can solve the problems of resolution difference, image resolution difference, and imbalance of 3D reconstruction methods, so as to improve the utilization efficiency and improve the accuracy.

Active Publication Date: 2013-04-03
严格集团股份有限公司
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem of the existing RFM-based generalized stereo pair 3D reconstruction in the face of different imaging systems due to the large angle caused by the pixel resolution difference of the same image and the large resolution difference between images under different imaging conditions. The method has the problem of generalized linear equations with severe imbalance, and the invention provides a generalized stereo pair three-dimensional reconstruction method using variance component estimation

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
  • Generalized stereopair three-dimensional reconstruction method adopting variance component estimation
  • Generalized stereopair three-dimensional reconstruction method adopting variance component estimation
  • Generalized stereopair three-dimensional reconstruction method adopting variance component estimation

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0020] Specific implementation mode one: combine figure 1 Describe this embodiment, the generalized stereo image pair three-dimensional reconstruction method using variance component estimation described in this embodiment,

[0021] It includes the following steps:

[0022] Step 1: According to the parameters of the imaging sensor, obtain the pixel-level resolution of the corresponding point of the target point to be reconstructed in each image of the generalized stereo pair;

[0023] Step 2: Utilize the RFM universal sensor model of each image of the generalized stereo image to construct a generalized linear equation system about the three-dimensional reconstruction of the target point to be reconstructed;

[0024] Step 3: Use the pixel-level resolution obtained in Step 1 to initialize the weight matrix of the generalized linear equations constructed in Step 2;

[0025] Step 4: Initially estimate the three-dimensional coordinates of the target point to be reconstructed by w...

specific Embodiment approach 2

[0030] Specific embodiment 2: This embodiment is a further limitation of the generalized stereo image pair 3D reconstruction method described in specific embodiment 1 using variance component estimation,

[0031] In step 1, according to the parameters of the imaging sensor, the method of obtaining the pixel-level resolution of the target point to be reconstructed in each image of the generalized stereo pair is as follows:

[0032] According to the height H of the imaging sensor, the instantaneous field of view angle θ, the pitch angle β and the image size N*N, the resolution of the kth pixel in the image obtained by the sensor is:

[0033]

[0034] The resolution Res k As the pixel-level resolution of the target point to be reconstructed in each image of the generalized stereo pair, N is a positive integer.

[0035] In this embodiment, according to the actual situation of the acquired data, first, if the imaging parameters of the imaging sensor can be acquired in detail, s...

specific Embodiment approach 3

[0045] Specific embodiment three: this embodiment is a further limitation of the generalized stereo pair 3D reconstruction method described in specific embodiment one using variance component estimation,

[0046] In step 1, according to the parameters of the imaging sensor, the method to obtain the pixel-level resolution of the corresponding point of the target point to be reconstructed in each image of the generalized stereo pair is: according to the known average resolution Res of the front-view image of the imaging sensor n and the pitch angle β, the pixel-level resolution of the target point to be reconstructed in each image of the generalized stereo pair is obtained as Res β = Res n cos 2 β .

[0047] When only the average resolution of the imaging sensor and its imaging pitch angle a...

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 generalized stereopair three-dimensional reconstruction method adopting variance component estimation, relates to a three-dimensional reconstruction method and aims at solving the problem that a generalized linear equation set with serious unbalancedness exists in the traditional generalized stereopair three-dimensional reconstruction method based on RFM (Rational Function Model) when the pixel resolution difference of same images and the resolution difference of images with different imaging conditions are serious because of a large angle facing to different imaging systems. The generalized stereopair three-dimensional reconstruction method disclosed by the invention realizes that a variance component estimation method is embedded into a classical three-dimensional reconstruction method based on the front convergence of a rational polynominal model RFM by utilizing the pixel-level resolution relation of corresponding target points, which are to be reconstructed, of a generalized stereopair and realizes the weight value matrix self-adaption adjustment in the process of iteratively solving an unknown three-dimensional coordinate, thereby effectively enhancing the three-dimensional reconstruction accuracy and enhancing the feasibility of the three-dimensional reconstruction of the generalized stereopair; and in addition, the generalized stereopair three-dimensional reconstruction method is used for the three-dimensional reconstruction of the generalized stereopair.

Description

technical field [0001] The invention relates to a three-dimensional reconstruction method, in particular to a generalized three-dimensional image pair three-dimensional reconstruction method using variance component estimation. Background technique [0002] With the rapid development of remote sensing technology, sensor technology and computer technology, human beings have achieved unprecedented leapfrog development in the field of earth observation. The emergence of more and more observation platforms such as high-resolution remote sensing commercial satellites, military satellites, near-space vehicles, aviation aircraft, and unmanned reconnaissance aircraft has made it possible for people to obtain large-scale high-precision 3D scene models. [0003] Among them, the use of remote sensing data for 3D reconstruction has become a research hotspot in the field of remote sensing. In the early days, people used strict sensor models to accurately obtain the internal and external...

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 谷延锋曹志民张晔
Owner 严格集团股份有限公司
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
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