Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for matching multiple image segments by using non geometric constraints

A technology of line segment matching and geometric constraints, applied in image analysis, image data processing, instruments, etc., to achieve the effect of ensuring accuracy

Inactive Publication Date: 2013-10-16
XI AN JIAOTONG UNIV
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The above matching methods all use geometric knowledge for line segment matching. Although this method is more intuitive, it needs to know more accurate geometric constraints in advance.

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 for matching multiple image segments by using non geometric constraints
  • Method for matching multiple image segments by using non geometric constraints
  • Method for matching multiple image segments by using non geometric constraints

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific examples. These examples are illustrative only and not restrictive of the invention.

[0028] figure 1 It is a flow chart of a method for line segment matching of multiple images without geometric constraints according to the present invention, and each step in the flow chart is described below.

[0029] Step S1: Collect images and input them into the computer. Use a handheld device to take multiple images of the same scene from different perspectives and input them into the computer.

[0030] Step S2: extracting line segments.

[0031] The input is M images, and each image is extracted by LSD algorithm J m feature line segment, m=1,2,...M, then the jth line segment of the mth image is recorded as l mj ...

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 method for matching multiple image segments by using non geometric constraints. The method comprises the steps of collecting images and inputting the images into a computer; extracting feature segments for the inputted images; selecting a plurality of groups of base images from the inputted images; matching segment features between two images of each group of the base image pairs by using the non geometric constraints; building a corresponding relation among the segment features of multiple images on the basis of the matched segments of each group of the base image pairs so as to form matched segment groups; screening the formed matched segment groups, removing incompatible matched segment groups, and keeping and combining compatible matched segment groups. The method provided by the invention avoids the defects that an epipolar geometry relation needs to be known in advance and the like when using the geometric constraints. In addition, a dual-view matching algorithm adopted by the method has the invariance properties such as rotation, illumination, scaling and the like, and provides guarantee for the accuracy of the matched segment groups.

Description

technical field [0001] The invention relates to the technical field of feature line segment matching for three-dimensional reconstruction, in particular to a method for line segment matching of multiple images without geometric constraints. Background technique [0002] Multiple image line segment matching is to find the projection of the same spatial line segment on different imaging images among the feature line segments extracted from different images, and the feature line segments corresponding to the same spatial line segment are a group of matching line segments. This technology can be applied in object recognition, 3D reconstruction, robot navigation and so on. [0003] The traditional multiple image matching algorithm (such as the literature Baillard, C., et al., Automatic line matching and 3D reconstruction of buildings from multiple views. ISPRS Conference on Automatic Extraction of GIS Objects from Digital Imagery, Munich: Allemagne (1999)) is Divide the input im...

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): G06T7/00
Inventor 黄华张琳彦
Owner XI AN JIAOTONG UNIV