A Method to Enhance Homogeneous Distribution of Matched Features for Image Matching
Features are distinctive landmarks of an image. There are various feature detection and description algorithms. Many computer vision algorithms require matching of features from two images. Large number of correct matches with homogeneous distribution in the images is needed for robustness of the...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IJEGEO
2020-04-01
|
Series: | International Journal of Environment and Geoinformatics |
Subjects: | |
Online Access: | https://dergipark.org.tr/tr/download/article-file/1029954 |
id |
doaj-a4f7185a84b444f19419ea0c81b6f1b9 |
---|---|
record_format |
Article |
spelling |
doaj-a4f7185a84b444f19419ea0c81b6f1b92020-11-25T03:36:23ZengIJEGEOInternational Journal of Environment and Geoinformatics2148-91732148-91732020-04-017110210710.30897/ijegeo.710634A Method to Enhance Homogeneous Distribution of Matched Features for Image MatchingBaran Gulmez0Fatih Demirtas1İrem Yıldırım2Uğur M. Leloglu3Mustafa Yaman4Eylem T. Guneyi 5ESEN Sistem Entegrasyon, Titanyum C Blok, ODTU Teknokent, 06800, Çankaya, Ankara, Turkey1 ESEN Sistem Entegrasyon, Titanyum C Blok, ODTU Teknokent, 06800, Çankaya, Ankara, Turkey 2 Hacettepe University, Department of Electrical and Electronics Engineering, 06800 Cankaya Ankara, Turkey1 ESEN Sistem Entegrasyon, Titanyum C Blok, ODTU Teknokent, 06800, Çankaya, Ankara, Turkey 2 Hacettepe University, Department of Electrical and Electronics Engineering, 06800 Cankaya Ankara, TurkeyMiddle East Technical Univesity, Geodetic and Geographic Information Technologies Department, 06800 Çankaya Ankara, TurkeyESEN Sistem Entegrasyon, Titanyum C Blok, ODTU Teknokent, 06800, Çankaya, Ankara, TurkeyESEN Sistem Entegrasyon, Titanyum C Blok, ODTU Teknokent, 06800, Çankaya, Ankara, TurkeyFeatures are distinctive landmarks of an image. There are various feature detection and description algorithms. Many computer vision algorithms require matching of features from two images. Large number of correct matches with homogeneous distribution in the images is needed for robustness of the image matching. The matches are generally obtained using a feature distance threshold and ambiguous matches are rejected using a ratio test. This paper proposes a method that can be added to image matching pipeline for enhancing homogeneous distribution and increasing the number of matched feature points. After successfully matching an image pair, spatially close feature points go through an elimination process which aims to decrease ambiguity at the second matching step. Then, a coarse geometric transformation between two images is calculated, through which the detected feature points in one image (i.e. the moving image) are projected to the other image (i.e. the fixed image). Then, feature points from the moving image are matched to neighboring feature points of the fixed image within a pre-determined spatial distance. This narrows down the possible candidates and enables less correct matches being rejected because of the ratio test. The effectiveness and feasibility of our method is demonstrated with experiments on images acquired from a drone camera during flight.https://dergipark.org.tr/tr/download/article-file/1029954featurehomogeneityfeature matchingimage matchingfeature distribution |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Baran Gulmez Fatih Demirtas İrem Yıldırım Uğur M. Leloglu Mustafa Yaman Eylem T. Guneyi |
spellingShingle |
Baran Gulmez Fatih Demirtas İrem Yıldırım Uğur M. Leloglu Mustafa Yaman Eylem T. Guneyi A Method to Enhance Homogeneous Distribution of Matched Features for Image Matching International Journal of Environment and Geoinformatics feature homogeneity feature matching image matching feature distribution |
author_facet |
Baran Gulmez Fatih Demirtas İrem Yıldırım Uğur M. Leloglu Mustafa Yaman Eylem T. Guneyi |
author_sort |
Baran Gulmez |
title |
A Method to Enhance Homogeneous Distribution of Matched Features for Image Matching |
title_short |
A Method to Enhance Homogeneous Distribution of Matched Features for Image Matching |
title_full |
A Method to Enhance Homogeneous Distribution of Matched Features for Image Matching |
title_fullStr |
A Method to Enhance Homogeneous Distribution of Matched Features for Image Matching |
title_full_unstemmed |
A Method to Enhance Homogeneous Distribution of Matched Features for Image Matching |
title_sort |
method to enhance homogeneous distribution of matched features for image matching |
publisher |
IJEGEO |
series |
International Journal of Environment and Geoinformatics |
issn |
2148-9173 2148-9173 |
publishDate |
2020-04-01 |
description |
Features are distinctive landmarks of an image. There are various feature detection and description algorithms. Many computer
vision algorithms require matching of features from two images. Large number of correct matches with homogeneous distribution in
the images is needed for robustness of the image matching. The matches are generally obtained using a feature distance threshold and
ambiguous matches are rejected using a ratio test. This paper proposes a method that can be added to image matching pipeline for
enhancing homogeneous distribution and increasing the number of matched feature points. After successfully matching an image
pair, spatially close feature points go through an elimination process which aims to decrease ambiguity at the second matching step.
Then, a coarse geometric transformation between two images is calculated, through which the detected feature points in one image
(i.e. the moving image) are projected to the other image (i.e. the fixed image). Then, feature points from the moving image are
matched to neighboring feature points of the fixed image within a pre-determined spatial distance. This narrows down the possible
candidates and enables less correct matches being rejected because of the ratio test. The effectiveness and feasibility of our method is
demonstrated with experiments on images acquired from a drone camera during flight. |
topic |
feature homogeneity feature matching image matching feature distribution |
url |
https://dergipark.org.tr/tr/download/article-file/1029954 |
work_keys_str_mv |
AT barangulmez amethodtoenhancehomogeneousdistributionofmatchedfeaturesforimagematching AT fatihdemirtas amethodtoenhancehomogeneousdistributionofmatchedfeaturesforimagematching AT iremyıldırım amethodtoenhancehomogeneousdistributionofmatchedfeaturesforimagematching AT ugurmleloglu amethodtoenhancehomogeneousdistributionofmatchedfeaturesforimagematching AT mustafayaman amethodtoenhancehomogeneousdistributionofmatchedfeaturesforimagematching AT eylemtguneyi amethodtoenhancehomogeneousdistributionofmatchedfeaturesforimagematching AT barangulmez methodtoenhancehomogeneousdistributionofmatchedfeaturesforimagematching AT fatihdemirtas methodtoenhancehomogeneousdistributionofmatchedfeaturesforimagematching AT iremyıldırım methodtoenhancehomogeneousdistributionofmatchedfeaturesforimagematching AT ugurmleloglu methodtoenhancehomogeneousdistributionofmatchedfeaturesforimagematching AT mustafayaman methodtoenhancehomogeneousdistributionofmatchedfeaturesforimagematching AT eylemtguneyi methodtoenhancehomogeneousdistributionofmatchedfeaturesforimagematching |
_version_ |
1724550190935834624 |