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

Method for extracting feature points with invariable affine sizes

A feature point extraction, scale-invariant technology, applied in image data processing, instrumentation, computing, etc., can solve problems such as multiple mismatches, and achieve the effect of reducing mismatches, enhancing robustness, and reducing detection range.

Active Publication Date: 2013-07-03
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
View PDF1 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The ASIFT algorithm can handle the transition slope up to 36 or higher, but in some cases there are too many feature points detected by ASIFT, and there will be more mismatches

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 extracting feature points with invariable affine sizes
  • Method for extracting feature points with invariable affine sizes
  • Method for extracting feature points with invariable affine sizes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below with reference to the accompanying drawings and in conjunction with preferred embodiments.

[0020] 1. Determination of camera affine model parameters

[0021] Surface deformation of solid objects can be simulated using an affine plane transformation. The affine transformation of the image can be expressed by the formula u(x, y)→u(ax+by+e, cx+dy+f), where a, b, c, d, e, f represent affine transformation parameters; if The affine mapping matrix A has a strict positive determinant and is similar, then A has a unique decomposition equation:

[0022] A = a b c d = H λ R ( Ψ ) T R ...

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 method for extracting feature points with invariable affine sizes. The method comprises the steps of determining a gradient parameter and a longitude parameter according to a camera affine model, respectively carrying out affine transformation on two images to be matched, simulating affine warping possibly caused by the images; detecting maximally stable extremal regions (MSER) in the images subjected to affine transformation, fitting each detected MSER by adopting an elliptical region equation; and further detecting the feature point in each MSER through a DoG Gaussian difference operator and generating a corresponding feature point description operator according to a location where the feature point is positioned and the size information. The method is capable of accurately extracting the feature points with invariable affines and sizes from the images and detecting more feature points when the images largely incline, and has better anti-affine property. Meanwhile, by adopting the detection of the MSERs, the detection range of the feature points can be reduced, the mis-matching is reduced, and the executing efficiency of an algorithm is increased.

Description

technical field [0001] The invention belongs to the technical field of computer image processing, in particular to an affine scale-invariant feature point extraction method, which is used for matching when the viewing angle scale of two images changes. Background technique [0002] Image matching is a very important research topic in computer vision, widely used in image matching, target tracking, object recognition, stereo matching, image stitching and other fields. A common problem that needs to be solved in these fields is to find the geometric relationship between multiple views in the same scene. However, during the image collection process, there will be great differences between the images collected in the same scene due to problems such as shooting angle, illumination, and scale. In order to solve this kind of problem, many scholars have proposed many methods of feature extraction and matching from different perspectives. [0003] The SIFT algorithm is widely used,...

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): G06T7/00
Inventor 王好谦张新张永兵戴琼海
Owner SHENZHEN GRADUATE SCHOOL TSINGHUA 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com