Three-dimensional scene reconstruction method based on statistical model

A three-dimensional scene and statistical model technology, applied in computing, 3D modeling, image data processing and other directions, can solve the problems of iterative easy to fall into local extremum, and the low sampling efficiency of Markov chain Monte Carlo algorithm.

Inactive Publication Date: 2010-06-23
NORTHWESTERN POLYTECHNICAL UNIV
View PDF0 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the sampling efficiency of its Markov chain Monte Carlo (MCMC) algorithm is not high, and only the local optimization algorithm BA is used to solve the model, so that the iteration is easy to fall into the local extremum

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 statistical model
  • Three-dimensional scene reconstruction method based on statistical model
  • Three-dimensional scene reconstruction method based on statistical model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0045] 1. Use the Harris corner detection algorithm to extract the corners of the image:

[0046] Take 48 images of the Bell Tower in Xi'an, and use integers between 1-48 to encode and mark these 48 images, and use the Harris corner detection algorithm to extract corner points as image feature points for each image, and use the corner point set U= {u ik |k∈1...n i , i∈1...48}, where k is the corner number in the image, i is the image number, n i is the number of corner points in the i-th image, u ik is the two-dimensional coordinates of the kth corner point in the i-th image.

[0047] 2. Generate a 3D point set X and a camera parameter set M:

[0048] The number of corner points in each image is compared to obtain the maximum number of corner points N, where N=213. Use a random function that satisfies the Gaussian distribution N(0, 1) to generate 213 three-...

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 three-dimensional scene reconstruction method based on a statistical model, which comprises the following steps: using a Harris corner detection algorithm to extract the corners in each image and generating a three-dimensional point set X and a camera parameter set M; using a Markov Chain Monte Carlo(MCMC) method to estimate the match probability among the image corners and the three-dimensional points and subjecting the image corners to weighted mean by using the match probability between the image corners and the three-dimensional points to obtain a virtual measuring point matrix V; subjecting the virtual measuring points to projective reconstruction by using a projective factorization algorithm capable of processing occlusion, adding a deterministic annealing algorithm to iteratively solve a global optimal protective reconstruction result, and using a camera self-calibration algorithm based on an absolute dual quadric surface to promote the projective reconstruction to metric reconstruction. The original process of one-time calculation is converted into a process of iterative refinement. Even though a matching relationship is unknown or a primary matching result is bad, a three-dimensional reconstruction result is finally obtained precisely through an iterative feedback method.

Description

technical field [0001] The invention relates to a three-dimensional scene reconstruction method based on a statistical model, which belongs to the field of image-based three-dimensional scene reconstruction in computer vision, and in particular relates to the establishment and optimization of matching relationships between feature points in images. Background technique [0002] Currently in the field of 3D reconstruction, Noah Snavely, Steven M.Seiz, and Richard Szeliski proposed a method of using large-scale images on the Internet in the literature Modeling the World from Internet Photo Collections (IJCV, vol.80, pp.189-210, 2008). A complete algorithm for 3D reconstruction of images at scale. The algorithm extracts local invariant features for each image, establishes a match between two images through the kd tree, and uses the normalized 8-point algorithm to calculate the basic matrix, and then uses feature point tracking to obtain the feature matching relationship between...

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): G06T17/00G06T7/00
Inventor 王庆徐炯杨恒潘杰何周灿王雯
Owner NORTHWESTERN POLYTECHNICAL 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