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

Multimodal image feature extraction and matching method based on ASIFT (affine scale invariant feature transform)

A multi-modal image and feature extraction technology, which is applied in image analysis, image data processing, character and pattern recognition, etc., can solve the problems of inability to extract and match multi-modal image features, and obtain no results

Inactive Publication Date: 2012-12-26
XIDIAN UNIV
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This makes the above two feature extraction and matching methods very limited in application, because affine transformation widely exists between images in the real world and is one of the most basic geometric transformations.
[0006] (2) Neither of the two types of algorithms can be widely used in feature extraction and matching of multimodal images
Therefore, feature extraction and matching of multi-modal images is a more difficult task than feature extraction and matching of single-modal images. Applying the above two types of methods directly to the problem of feature detection of multi-modal images often fails to obtain Satisfying result

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
  • Multimodal image feature extraction and matching method based on ASIFT (affine scale invariant feature transform)
  • Multimodal image feature extraction and matching method based on ASIFT (affine scale invariant feature transform)
  • Multimodal image feature extraction and matching method based on ASIFT (affine scale invariant feature transform)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be described in further detail below with reference to the accompanying drawings.

[0033] refer to figure 2 , taking two images p1 and p2 as an example, the implementation steps are:

[0034] Step 1: Perform affine transformation processing on the images p1 and p2 respectively according to the ASIFT affine transformation matrix, so that each image forms a group of views.

[0035] (1.1) Sampling the absolute tilt parameter t and the longitude angle parameter φ of the ASIFT affine transformation physical model to obtain all the affine transformation matrices caused by the changes of these two parameters, such as image 3 As shown, the parameter t follows the geometric sequence t=1, a, a 2 ,...,a n to sample, where n=5, the parameter φ is sampled according to the arithmetic sequence φ=0, b / t, ..., kb / t, wherein kb / t<180°, b=72;

[0036] (1.2) Bring the sampled values ​​of t and φ into the matrix in turn I ′ ...

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 multimodal feature extraction and matching method based on ASIFT (affine scale invariant feature transform), and the method is mainly used for realizing the point feature extraction and matching of the multimodal image which cannot be solved in the prior art. The method can be realized through the following steps: carrying out sampling on the ASIFT affine transformational model tilting value parameters and longitude parameters, thus obtaining two groups of views of two input images; adopting a difference of Gauss (DoG) feature detection method to detect the position and size of the feature point on the two groups of views; using an average squared-gradient method to set the principle directions of the features and setting the feature vector amplitude by a counting method; calculating the symmetric ASIFT descriptor of the features; and adopting a nearest neighborhood method to carry out coarse matching on the symmetric ASIFT descriptor, and using an optimized random sampling method to remove mis-matching features. In the invention, features can be extracted and matched in the images sensed by various sensors, and the method provided by the invention has the characteristic of invariability after complete affine, and can be applied to the fields of object recognition and tracking, image registration and the like.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an image feature extraction and matching method, which can be used in the fields of multimodal image registration, target recognition and tracking, and the like. Background technique [0002] In the fields of image registration, target recognition and tracking, it is necessary to find the geometric relationship between multiple views of the same scene, so as to obtain more comprehensive information of the whole scene. One of the most common methods to solve this kind of problem is to obtain the geometric relationship between these views through a large amount of common information in different views of the same scene. However, due to the different imaging mechanisms of different sensors, the movement of objects in the field of view over time, the differences in the internal parameters of different imaging devices, and the differences in the angles of the shooting scenes, how to us...

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): G06K9/46G06T7/00
Inventor 张强李慧娟王龙杨茹
Owner XIDIAN 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