Groupwise registration of aerial images

This paper addresses the task of time separated aerial image registration. The ability to solve this problem accurately and reliably is important for a variety of subsequent image understanding applications. The principal challenge lies in the extent and nature of transient appearance variation that...

Full description

Bibliographic Details
Main Authors: Arandjelovic, O., Pham, DucSon, Venkatesh, S.
Other Authors: Qiang Yang, Michael Wooldridge
Format: Conference Paper
Published: AAAI 2015
Subjects:
Online Access:https://www.aaai.org/ocs/index.php/IJCAI/IJCAI15/paper/view/10802
http://hdl.handle.net/20.500.11937/22175
_version_ 1848750796894633984
author Arandjelovic, O.
Pham, DucSon
Venkatesh, S.
author2 Qiang Yang, Michael Wooldridge
author_facet Qiang Yang, Michael Wooldridge
Arandjelovic, O.
Pham, DucSon
Venkatesh, S.
author_sort Arandjelovic, O.
building Curtin Institutional Repository
collection Online Access
description This paper addresses the task of time separated aerial image registration. The ability to solve this problem accurately and reliably is important for a variety of subsequent image understanding applications. The principal challenge lies in the extent and nature of transient appearance variation that a land area can undergo, such as that caused by the change in illumination conditions, seasonal variations, or the occlusion by non-persistent objects (people, cars). Our work introduces several novelties: (i) unlike all previous work on aerial image registration, we approach the problem using a set-based paradigm; (ii) we show how local, pair-wise constraints can be used to enforce a globally good registration using a constraints graph structure; (iii) we show how a simple holistic representation derived from raw aerial images can be used as a basic building block of the constraints graph in a manner which achieves both high registration accuracy and speed. We demonstrate: (i) that the proposed method outperforms the state-of-the-art for pair-wise registration already, achieving greater accuracy and reliability, while at the same time reducing the computational cost of the task; and (ii) that the increase in the number of available images in a set consistently reduces the average registration error.
first_indexed 2025-11-14T07:42:32Z
format Conference Paper
id curtin-20.500.11937-22175
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:42:32Z
publishDate 2015
publisher AAAI
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-221752019-04-30T08:20:06Z Groupwise registration of aerial images Arandjelovic, O. Pham, DucSon Venkatesh, S. Qiang Yang, Michael Wooldridge registration error aerial image registration This paper addresses the task of time separated aerial image registration. The ability to solve this problem accurately and reliably is important for a variety of subsequent image understanding applications. The principal challenge lies in the extent and nature of transient appearance variation that a land area can undergo, such as that caused by the change in illumination conditions, seasonal variations, or the occlusion by non-persistent objects (people, cars). Our work introduces several novelties: (i) unlike all previous work on aerial image registration, we approach the problem using a set-based paradigm; (ii) we show how local, pair-wise constraints can be used to enforce a globally good registration using a constraints graph structure; (iii) we show how a simple holistic representation derived from raw aerial images can be used as a basic building block of the constraints graph in a manner which achieves both high registration accuracy and speed. We demonstrate: (i) that the proposed method outperforms the state-of-the-art for pair-wise registration already, achieving greater accuracy and reliability, while at the same time reducing the computational cost of the task; and (ii) that the increase in the number of available images in a set consistently reduces the average registration error. 2015 Conference Paper http://hdl.handle.net/20.500.11937/22175 https://www.aaai.org/ocs/index.php/IJCAI/IJCAI15/paper/view/10802 AAAI unknown
spellingShingle registration error
aerial image registration
Arandjelovic, O.
Pham, DucSon
Venkatesh, S.
Groupwise registration of aerial images
title Groupwise registration of aerial images
title_full Groupwise registration of aerial images
title_fullStr Groupwise registration of aerial images
title_full_unstemmed Groupwise registration of aerial images
title_short Groupwise registration of aerial images
title_sort groupwise registration of aerial images
topic registration error
aerial image registration
url https://www.aaai.org/ocs/index.php/IJCAI/IJCAI15/paper/view/10802
http://hdl.handle.net/20.500.11937/22175