A New Paradigm for Matching UAV- and Aerial Images

Tobias Koch, Xiangyu Zhuo, Peter Reinartz, Friedrich Fraundorfer

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

This paper investigates the performance of SIFT-based image matching regarding large differences in image scaling and rotation, as this is usually the case when trying to match images captured from UAVs and airplanes. This task represents an essential step for image registration and 3d-reconstruction applications. Various real world examples presented in this paper show that SIFT, as well as A-SIFT perform poorly or even fail in this matching scenario. Even if the scale difference in the images is known and eliminated beforehand, the matching performance suffers from too few feature point detections, ambiguous feature point orientations and rejection of many correct matches when applying the ratio-test afterwards. Therefore, a new feature matching method is provided that overcomes these problems and offers thousands of matches by a novel feature point detection strategy, applying a one-to-many matching scheme and substitute the ratio-test by adding geometric constraints to achieve geometric correct matches at repetitive image regions. This method is designed for matching almost nadir-directed images with low scene depth, as this is typical in UAV and aerial image matching scenarios. We tested the proposed method on different real world image pairs. While standard SIFT failed for most of the datasets, plenty of geometrical correct matches could be found using our approach. Comparing the estimated fundamental matrices and homographies with ground-truth solutions, mean errors of few pixels can be achieved.
LanguageEnglish
Title of host publicationISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences
Pages83-90
DOIs
StatusPublished - 2016

Cite this

Koch, T., Zhuo, X., Reinartz, P., & Fraundorfer, F. (2016). A New Paradigm for Matching UAV- and Aerial Images. In ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences (pp. 83-90) https://doi.org/10.5194/isprs-annals-III-3-83-2016

A New Paradigm for Matching UAV- and Aerial Images. / Koch, Tobias; Zhuo, Xiangyu; Reinartz, Peter; Fraundorfer, Friedrich.

ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences. 2016. p. 83-90.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Koch, T, Zhuo, X, Reinartz, P & Fraundorfer, F 2016, A New Paradigm for Matching UAV- and Aerial Images. in ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences. pp. 83-90. https://doi.org/10.5194/isprs-annals-III-3-83-2016
Koch T, Zhuo X, Reinartz P, Fraundorfer F. A New Paradigm for Matching UAV- and Aerial Images. In ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences. 2016. p. 83-90 https://doi.org/10.5194/isprs-annals-III-3-83-2016
Koch, Tobias ; Zhuo, Xiangyu ; Reinartz, Peter ; Fraundorfer, Friedrich. / A New Paradigm for Matching UAV- and Aerial Images. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences. 2016. pp. 83-90
@inproceedings{f5cf1d30d26a45a5b9cef4d4a8a1c1bc,
title = "A New Paradigm for Matching UAV- and Aerial Images",
abstract = "This paper investigates the performance of SIFT-based image matching regarding large differences in image scaling and rotation, as this is usually the case when trying to match images captured from UAVs and airplanes. This task represents an essential step for image registration and 3d-reconstruction applications. Various real world examples presented in this paper show that SIFT, as well as A-SIFT perform poorly or even fail in this matching scenario. Even if the scale difference in the images is known and eliminated beforehand, the matching performance suffers from too few feature point detections, ambiguous feature point orientations and rejection of many correct matches when applying the ratio-test afterwards. Therefore, a new feature matching method is provided that overcomes these problems and offers thousands of matches by a novel feature point detection strategy, applying a one-to-many matching scheme and substitute the ratio-test by adding geometric constraints to achieve geometric correct matches at repetitive image regions. This method is designed for matching almost nadir-directed images with low scene depth, as this is typical in UAV and aerial image matching scenarios. We tested the proposed method on different real world image pairs. While standard SIFT failed for most of the datasets, plenty of geometrical correct matches could be found using our approach. Comparing the estimated fundamental matrices and homographies with ground-truth solutions, mean errors of few pixels can be achieved.",
author = "Tobias Koch and Xiangyu Zhuo and Peter Reinartz and Friedrich Fraundorfer",
year = "2016",
doi = "10.5194/isprs-annals-III-3-83-2016",
language = "English",
pages = "83--90",
booktitle = "ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences",

}

TY - GEN

T1 - A New Paradigm for Matching UAV- and Aerial Images

AU - Koch, Tobias

AU - Zhuo, Xiangyu

AU - Reinartz, Peter

AU - Fraundorfer, Friedrich

PY - 2016

Y1 - 2016

N2 - This paper investigates the performance of SIFT-based image matching regarding large differences in image scaling and rotation, as this is usually the case when trying to match images captured from UAVs and airplanes. This task represents an essential step for image registration and 3d-reconstruction applications. Various real world examples presented in this paper show that SIFT, as well as A-SIFT perform poorly or even fail in this matching scenario. Even if the scale difference in the images is known and eliminated beforehand, the matching performance suffers from too few feature point detections, ambiguous feature point orientations and rejection of many correct matches when applying the ratio-test afterwards. Therefore, a new feature matching method is provided that overcomes these problems and offers thousands of matches by a novel feature point detection strategy, applying a one-to-many matching scheme and substitute the ratio-test by adding geometric constraints to achieve geometric correct matches at repetitive image regions. This method is designed for matching almost nadir-directed images with low scene depth, as this is typical in UAV and aerial image matching scenarios. We tested the proposed method on different real world image pairs. While standard SIFT failed for most of the datasets, plenty of geometrical correct matches could be found using our approach. Comparing the estimated fundamental matrices and homographies with ground-truth solutions, mean errors of few pixels can be achieved.

AB - This paper investigates the performance of SIFT-based image matching regarding large differences in image scaling and rotation, as this is usually the case when trying to match images captured from UAVs and airplanes. This task represents an essential step for image registration and 3d-reconstruction applications. Various real world examples presented in this paper show that SIFT, as well as A-SIFT perform poorly or even fail in this matching scenario. Even if the scale difference in the images is known and eliminated beforehand, the matching performance suffers from too few feature point detections, ambiguous feature point orientations and rejection of many correct matches when applying the ratio-test afterwards. Therefore, a new feature matching method is provided that overcomes these problems and offers thousands of matches by a novel feature point detection strategy, applying a one-to-many matching scheme and substitute the ratio-test by adding geometric constraints to achieve geometric correct matches at repetitive image regions. This method is designed for matching almost nadir-directed images with low scene depth, as this is typical in UAV and aerial image matching scenarios. We tested the proposed method on different real world image pairs. While standard SIFT failed for most of the datasets, plenty of geometrical correct matches could be found using our approach. Comparing the estimated fundamental matrices and homographies with ground-truth solutions, mean errors of few pixels can be achieved.

U2 - 10.5194/isprs-annals-III-3-83-2016

DO - 10.5194/isprs-annals-III-3-83-2016

M3 - Conference contribution

SP - 83

EP - 90

BT - ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences

ER -