Comparison of Keypoint Detectors and Descriptors for Relative Radiometric Normalization of Bitemporal Remote Sensing Images
This article compares the performances of the most commonly used keypoint detectors and descriptors (SIFT, SURF, KAZE, AKAZE, ORB, and BRISK) in keypoint-based relative radiometric normalization (RRN) of unregistered bitemporal multispectral images. The keypoints matched between subject and referenc...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9392236/ |
id |
doaj-fdfc2617aafd4f51a092bb588881f321 |
---|---|
record_format |
Article |
spelling |
doaj-fdfc2617aafd4f51a092bb588881f3212021-06-03T23:03:54ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01144063407310.1109/JSTARS.2021.30699199392236Comparison of Keypoint Detectors and Descriptors for Relative Radiometric Normalization of Bitemporal Remote Sensing ImagesArmin Moghimi0https://orcid.org/0000-0002-0455-4882Turgay Celik1https://orcid.org/0000-0001-6925-6010Ali Mohammadzadeh2https://orcid.org/0000-0003-3329-5063Huseyin Kusetogullari3https://orcid.org/0000-0001-5762-6678Department of Photogrammetry and Remote Sensing, Geomatics Engineering Faculty, K. N. Toosi University of Technology, Tehran, IranSchool of Electrical and Information Engineering and the Wits Institute of Data Science, University of the Witwatersrand, Johannesburg, South AfricaDepartment of Photogrammetry and Remote Sensing, Geomatics Engineering Faculty, K. N. Toosi University of Technology, Tehran, IranDepartment of Computer Science, Blekinge Institute of Technology, Karlskrona, SwedenThis article compares the performances of the most commonly used keypoint detectors and descriptors (SIFT, SURF, KAZE, AKAZE, ORB, and BRISK) in keypoint-based relative radiometric normalization (RRN) of unregistered bitemporal multispectral images. The keypoints matched between subject and reference images represent possible unchanged regions and form a radiometric control set (RCS). The initial RCS is further refined by removing the matched keypoints with a low cross-correlation. The final RCS is used to approximate a linear mapping between the corresponding bands of the subject and reference images. This procedure is validated on five datasets of unregistered multispectral image pairs acquired by inter/intra sensors in terms of RRN accuracy, visual quality, quality, and quantity of the samples in the RCS, and computational time. The experimental results show that keypoint-based RRN is robust against variations in spatial-resolution, illumination, and sensors. The blob detectors (SURF, SIFT, KAZE, and AKAZE) are more accurate on average than the corner detectors (ORB and BRISK) in RRN, with an expense of higher computational cost. The source code and samples of datasets used in this study are made available at <uri>https://github.com/ArminMoghimi/keypoint-based-RRN</uri> to support reproducible research in remote sensing.https://ieeexplore.ieee.org/document/9392236/AKAZEBRISKchange detectionKAZEkeypoint detector and descriptorkeypoint matching |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Armin Moghimi Turgay Celik Ali Mohammadzadeh Huseyin Kusetogullari |
spellingShingle |
Armin Moghimi Turgay Celik Ali Mohammadzadeh Huseyin Kusetogullari Comparison of Keypoint Detectors and Descriptors for Relative Radiometric Normalization of Bitemporal Remote Sensing Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing AKAZE BRISK change detection KAZE keypoint detector and descriptor keypoint matching |
author_facet |
Armin Moghimi Turgay Celik Ali Mohammadzadeh Huseyin Kusetogullari |
author_sort |
Armin Moghimi |
title |
Comparison of Keypoint Detectors and Descriptors for Relative Radiometric Normalization of Bitemporal Remote Sensing Images |
title_short |
Comparison of Keypoint Detectors and Descriptors for Relative Radiometric Normalization of Bitemporal Remote Sensing Images |
title_full |
Comparison of Keypoint Detectors and Descriptors for Relative Radiometric Normalization of Bitemporal Remote Sensing Images |
title_fullStr |
Comparison of Keypoint Detectors and Descriptors for Relative Radiometric Normalization of Bitemporal Remote Sensing Images |
title_full_unstemmed |
Comparison of Keypoint Detectors and Descriptors for Relative Radiometric Normalization of Bitemporal Remote Sensing Images |
title_sort |
comparison of keypoint detectors and descriptors for relative radiometric normalization of bitemporal remote sensing images |
publisher |
IEEE |
series |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
issn |
2151-1535 |
publishDate |
2021-01-01 |
description |
This article compares the performances of the most commonly used keypoint detectors and descriptors (SIFT, SURF, KAZE, AKAZE, ORB, and BRISK) in keypoint-based relative radiometric normalization (RRN) of unregistered bitemporal multispectral images. The keypoints matched between subject and reference images represent possible unchanged regions and form a radiometric control set (RCS). The initial RCS is further refined by removing the matched keypoints with a low cross-correlation. The final RCS is used to approximate a linear mapping between the corresponding bands of the subject and reference images. This procedure is validated on five datasets of unregistered multispectral image pairs acquired by inter/intra sensors in terms of RRN accuracy, visual quality, quality, and quantity of the samples in the RCS, and computational time. The experimental results show that keypoint-based RRN is robust against variations in spatial-resolution, illumination, and sensors. The blob detectors (SURF, SIFT, KAZE, and AKAZE) are more accurate on average than the corner detectors (ORB and BRISK) in RRN, with an expense of higher computational cost. The source code and samples of datasets used in this study are made available at <uri>https://github.com/ArminMoghimi/keypoint-based-RRN</uri> to support reproducible research in remote sensing. |
topic |
AKAZE BRISK change detection KAZE keypoint detector and descriptor keypoint matching |
url |
https://ieeexplore.ieee.org/document/9392236/ |
work_keys_str_mv |
AT arminmoghimi comparisonofkeypointdetectorsanddescriptorsforrelativeradiometricnormalizationofbitemporalremotesensingimages AT turgaycelik comparisonofkeypointdetectorsanddescriptorsforrelativeradiometricnormalizationofbitemporalremotesensingimages AT alimohammadzadeh comparisonofkeypointdetectorsanddescriptorsforrelativeradiometricnormalizationofbitemporalremotesensingimages AT huseyinkusetogullari comparisonofkeypointdetectorsanddescriptorsforrelativeradiometricnormalizationofbitemporalremotesensingimages |
_version_ |
1721398743607017472 |