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

Method and system for extracting vanishing points based on global search

A global search and extraction method technology, applied in the field of image processing, can solve the problems that RANSAC does not have a global optimal solution, the vanishing point does not have global optimality, etc., and achieves strong real-time performance, simple implementation, and low time complexity Effect

Active Publication Date: 2019-10-25
WUHAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this algorithm can maintain the orthogonality of the vanishing point and is fast, but because RANSAC itself does not have the characteristics of a global optimal solution, the obtained vanishing point theoretically does not have global optimality.

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
  • Method and system for extracting vanishing points based on global search
  • Method and system for extracting vanishing points based on global search
  • Method and system for extracting vanishing points based on global search

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The specific embodiments of the present invention will be further described below.

[0044] 1. Construct a polar coordinate grid on the equivalent spherical surface.

[0045] This step includes the following sub-steps:

[0046] Step 1.1, calculate the latitude and longitude (λ, φ) of the corresponding point on the equivalent sphere (Equivalent Sphere) of point p(x, y) on the image.

[0047] The specific implementation process of this sub-step is as follows:

[0048] The internal parameters of the known image: the focal length f and the principal point of the image (x 0 ,y 0 ), given any point p(x,y) on the image, the corresponding three-dimensional coordinates of the point p(x,y) in the camera space coordinate system are p(X,Y,Z):

[0049]

[0050] The three-dimensional sphere surrounded by all points p(X, Y, Z) is the equivalent sphere. The aforementioned camera space coordinate system is a right-handed coordinate system, with the camera imaging center as the o...

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 varnishing point extracting method and system based on global search. The method comprises the first step of constructing a polar coordinate grid of an image based on an equivalent sphere; the second step of renewing a polar coordinate grid value; the third step of obtaining all possible varnishing point assumptions based on a minimum calculating set composed of two straight lines and orthogonal properties of the varnishing point; the fourth step of conducting verification on all the possible varnishing point assumptions based on the polar coordinate grid value, and selecting the most precise varnishing point assumption as a varnishing point extracting result. According to the varnishing point extracting method and system based on global search, the varnishing point can be steadily extracted on a scene in which only one, two or three varnishing points exist, and the varnishing point extracting system has robustness; varnishing point extracting is simple to implement, the time complexity is low, parallel processing is suitable in all steps, and the varnishing point extracting system has instantaneity; through a method of adopting dense sampling and global search to seek optimal varnishing point, the varnishing point is extracted, and theoretically the varnishing point has global optimum.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a method and system for extracting vanishing points based on global search. Background technique [0002] In perspective projection, the projection of a bundle of parallel lines parallel to the projection plane can remain parallel, while the projections of parallel lines not parallel to the projection plane will converge to a point, which becomes the Vanishing Point. The vanishing point can be regarded as the projection of a point at infinity on the projection surface. The vanishing point with orthogonal information is of great significance for recovering the orientation of the camera at the moment the photo is taken, estimating the structure of the world coordinate system and solving the internal parameters of the image. At the same time, as an underlying technology, vanishing point extraction can be used in many applications, such as 3D reconstruction of scenes based ...

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 Patents(China)
IPC IPC(8): G06T7/536
Inventor 姚剑鲁小虎李昊昂刘亚辉张笑枫
Owner WUHAN UNIV
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