The potential & limitations of monoplotting in cross-view geo-localization conditions

Cross-view geolocalization (CVGL) describes the general problem of determining a correlation between terrestrial and nadir oriented imagery. Classical keypoint matching methods find the extreme pose transitions between cameras present in a CVGL configuration challenging to operate in, while deep neu...

Full description

Saved in:
Bibliographic Details
Main Authors: Bradley J. Koskowich, Michael J. Starek, Scott A. King
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:ISPRS Open Journal of Photogrammetry and Remote Sensing
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2667393225000092
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849710083754164224
author Bradley J. Koskowich
Michael J. Starek
Scott A. King
author_facet Bradley J. Koskowich
Michael J. Starek
Scott A. King
author_sort Bradley J. Koskowich
collection DOAJ
description Cross-view geolocalization (CVGL) describes the general problem of determining a correlation between terrestrial and nadir oriented imagery. Classical keypoint matching methods find the extreme pose transitions between cameras present in a CVGL configuration challenging to operate in, while deep neural networks demonstrate superb capacity in this area. Traditional photogrammetry methods like structure-from-motion (SfM) or simultaneous localization and mapping (SLAM) can technically accomplish CVGL, but require a sufficiently dense collection of camera views in order to recover camera pose. This research proposes an alternative CVGL solution, a series of algorithmic operations which can completely automate the calculation of target camera pose via a less common photogrammetry method known as monoplotting, also called single camera resectioning. Monoplotting only requires three inputs, which are a target terrestrial camera image, a nadir-oriented image, and an underlying digital surface model. 2D-3D point correspondences are derived from the inputs to optimize for the target terrestrial camera pose. The proposed method applies affine keypointing, pixel color quantization, and keypoint neighbor triangulation to codify explicit relationships used to augment keypoint matching operations done in a CVGL context. These matching results are used to achieve better initial 2D-3D point correlations from monoplotting image pairs, resulting in lower error for single camera resectioning. To gauge the effectiveness of the proposed method, this proposed methodology is applied to urban, suburban, and natural environment datasets. This proposed methodology demonstrates an average 42x improvement in feature matching between CVGL image pairs, which improves on inconsistent baseline methodology by reducing translation errors between 50%–75%.
format Article
id doaj-art-a383c8a75a3d432d9840da436eb302ca
institution DOAJ
issn 2667-3932
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series ISPRS Open Journal of Photogrammetry and Remote Sensing
spelling doaj-art-a383c8a75a3d432d9840da436eb302ca2025-08-20T03:15:03ZengElsevierISPRS Open Journal of Photogrammetry and Remote Sensing2667-39322025-08-011710009010.1016/j.ophoto.2025.100090The potential & limitations of monoplotting in cross-view geo-localization conditionsBradley J. Koskowich0Michael J. Starek1Scott A. King2Conrad Blucher Institute for Surveying and Science, Texas A&M University-Corpus Christi, 6300 Ocean Drive, Corpus Christi, 78414, TX, USA; College of Engineering and Computer Science, Texas A&M University-Corpus Christi, 6300 Ocean Drive, Corpus Christi, 78414, TX, USA; Corresponding author.Conrad Blucher Institute for Surveying and Science, Texas A&M University-Corpus Christi, 6300 Ocean Drive, Corpus Christi, 78414, TX, USA; College of Engineering and Computer Science, Texas A&M University-Corpus Christi, 6300 Ocean Drive, Corpus Christi, 78414, TX, USACollege of Engineering and Computer Science, Texas A&M University-Corpus Christi, 6300 Ocean Drive, Corpus Christi, 78414, TX, USACross-view geolocalization (CVGL) describes the general problem of determining a correlation between terrestrial and nadir oriented imagery. Classical keypoint matching methods find the extreme pose transitions between cameras present in a CVGL configuration challenging to operate in, while deep neural networks demonstrate superb capacity in this area. Traditional photogrammetry methods like structure-from-motion (SfM) or simultaneous localization and mapping (SLAM) can technically accomplish CVGL, but require a sufficiently dense collection of camera views in order to recover camera pose. This research proposes an alternative CVGL solution, a series of algorithmic operations which can completely automate the calculation of target camera pose via a less common photogrammetry method known as monoplotting, also called single camera resectioning. Monoplotting only requires three inputs, which are a target terrestrial camera image, a nadir-oriented image, and an underlying digital surface model. 2D-3D point correspondences are derived from the inputs to optimize for the target terrestrial camera pose. The proposed method applies affine keypointing, pixel color quantization, and keypoint neighbor triangulation to codify explicit relationships used to augment keypoint matching operations done in a CVGL context. These matching results are used to achieve better initial 2D-3D point correlations from monoplotting image pairs, resulting in lower error for single camera resectioning. To gauge the effectiveness of the proposed method, this proposed methodology is applied to urban, suburban, and natural environment datasets. This proposed methodology demonstrates an average 42x improvement in feature matching between CVGL image pairs, which improves on inconsistent baseline methodology by reducing translation errors between 50%–75%.http://www.sciencedirect.com/science/article/pii/S2667393225000092Image monoplottingCross-view geolocalizationKeypoint matching
spellingShingle Bradley J. Koskowich
Michael J. Starek
Scott A. King
The potential & limitations of monoplotting in cross-view geo-localization conditions
ISPRS Open Journal of Photogrammetry and Remote Sensing
Image monoplotting
Cross-view geolocalization
Keypoint matching
title The potential & limitations of monoplotting in cross-view geo-localization conditions
title_full The potential & limitations of monoplotting in cross-view geo-localization conditions
title_fullStr The potential & limitations of monoplotting in cross-view geo-localization conditions
title_full_unstemmed The potential & limitations of monoplotting in cross-view geo-localization conditions
title_short The potential & limitations of monoplotting in cross-view geo-localization conditions
title_sort potential amp limitations of monoplotting in cross view geo localization conditions
topic Image monoplotting
Cross-view geolocalization
Keypoint matching
url http://www.sciencedirect.com/science/article/pii/S2667393225000092
work_keys_str_mv AT bradleyjkoskowich thepotentialamplimitationsofmonoplottingincrossviewgeolocalizationconditions
AT michaeljstarek thepotentialamplimitationsofmonoplottingincrossviewgeolocalizationconditions
AT scottaking thepotentialamplimitationsofmonoplottingincrossviewgeolocalizationconditions
AT bradleyjkoskowich potentialamplimitationsofmonoplottingincrossviewgeolocalizationconditions
AT michaeljstarek potentialamplimitationsofmonoplottingincrossviewgeolocalizationconditions
AT scottaking potentialamplimitationsofmonoplottingincrossviewgeolocalizationconditions