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

Method for matching feature points among multiple images

A feature point matching, multi-image technology, applied in image analysis, image data processing, graphic image conversion and other directions, can solve the problems of large matching calculation and high mismatch rate, achieve broad application prospects, avoid the probability of mismatching, The effect of reducing computational complexity

Active Publication Date: 2020-07-17
青岛联合创智科技有限公司
View PDF18 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the shortcomings of the existing feature point matching process between images, aiming at the shortcomings of large amount of matching calculation and high mismatch rate in the current process of feature point matching between images, a method for feature point matching between multiple images is designed and provided

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 feature points among multiple images
  • Method for matching feature points among multiple images
  • Method for matching feature points among multiple images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] A method for matching feature points between multiple images involved in this embodiment has the following specific process steps:

[0036] Step 1: Calculate the rotation matrix of each image using the mobile phone gyroscope data:

[0037] The world coordinate system is established with the true north direction parallel to the ground as the X-axis, the vertical direction of the X-axis parallel to the ground as the Y-axis, and the direction perpendicular to the ground as the Z-axis, and the world coordinate system is a left-handed coordinate system; The system is a local coordinate system, the mobile phone screen is the X-Y plane, the upper left corner of the mobile phone screen is the coordinate origin, the screen height is the X axis, the width is the Y axis, the main optical axis of the mobile phone is the Z axis, and is a left-handed coordinate system; read from the gyroscope Take the angle between the mobile phone coordinate axis and the world coordinate axis, and s...

Embodiment 2

[0056] This embodiment applies the feature point matching method between multiple images described in Embodiment 1 to match real images captured from multiple angles, such as figure 2 As shown in the figure, the black part in the middle is the three-dimensional object to be photographed, the multiple gray-white pyramids represent the selected shooting angles in various directions, and the images taken at adjacent angles are similar;

[0057] After using the existing image matching method to process the captured image, the image pair that needs to be matched is obtained, such as image 3 After processing the captured pictures by using the feature point matching method between multiple images of the present invention, the image pairs that need to be matched are obtained as follows: Figure 4 shown; in image 3 and Figure 4 , each point represents an image pair, by putting image 3 and Figure 4 It can be seen from the comparison that, after processing the captured pictures...

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 belongs to the technical field of computer image processing and computer graphics, and relates to a method for matching feature points among multiple images. The method comprises the following process steps: 1, calculating a rotation matrix of each image by utilizing data of a gyroscope of the mobile phone; 2, calculating an image viewing angle direction by using the rotation matrix;3, calculating an included angle between view angle directions of each image; 4, screening out a pre-selected image pair according to the size of the included angle; 5, matching feature points of thepre-selected image pair by using an existing algorithm to obtain a feature point matching relationship; 6, screening out a feature point matching relationship according to geometric constraints. Thesteps of the method are perfect and reasonable, the calculation complexity is greatly reduced and the image matching precision is remarkably improved through preliminary screening of image pairs and elimination of wrong feature point matching relationships, and the method has a wide application prospect in the fields of digital photogrammetry, computer vision and the like.

Description

Technical field: [0001] The invention belongs to the technical field of computer image processing and computer graphics, and relates to a feature point matching method between multiple images. Background technique: [0002] Feature point matching is to take the points (called feature points) extracted from the image with certain local special properties as the conjugate entity, and the attribute parameters of the feature points, that is, the feature description, as the matching entity, and realize the conjugate entity by calculating the similarity measure. Registered image matching method. Matching feature points is a relatively simple and effective matching method among feature matching methods. It is a very important method in many fields of digital photogrammetry (such as relative orientation, DEM generation, etc.), computer vision (such as 3D scene restoration, moving target detection, etc.). important basic process. [0003] In the prior art, the Chinese Patent Public...

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): G06T7/33G06T3/60G06K9/62
CPCG06T7/33G06T3/604G06F18/22Y02D30/70
Inventor 纪刚杜靖王云修安帅
Owner 青岛联合创智科技有限公司