Technical progress towards spacenet-9 - cross-modal satellite imagery registration for natural disaster responses

Ronny Hänsch; Jacob Arndt; Abhishek Potnis; Philipe Dias; Claudio Persello; Fabio Pacifici; Todd M. Bacastow

doi:10.1109/IGARSS55030.2025.11244021

Technical progress towards spacenet-9 - cross-modal satellite imagery registration for natural disaster responses

Ronny Hänsch
, Jacob Arndt
, Abhishek Potnis
, Philipe Dias
, Claudio Persello
, Fabio Pacifici
, Todd M. Bacastow

Department of Geoinformatics

Research output: Contribution to conference › Paper › peer-review

7 Downloads (Pure)

Abstract

The SpaceNet-9 challenge running in spring 2025 features a dataset for developing optical-SAR image registration algorithms that have the potential to simplify traditionally time-consuming preprocessing steps and could help accelerate analysis timelines in disaster response scenarios. Building on prior work that discusses the motivation for such a challenge, presents an initial dataset, and describes a baseline algorithm, this paper elaborates on the technical progress in improving the SpaceNet-9 challenge, the preliminary dataset to prepare the challenge, and the baseline algorithm. Specifically, we highlight the latest efforts in data annotation and quality assessment, dataset analysis, experiments in keypoint detection, and large-scale scene registration.

Original language	English
Pages	609-613
Number of pages	5
DOIs	https://doi.org/10.1109/IGARSS55030.2025.11244021
Publication status	Published - 25 Nov 2025
Event	IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2025: One Earth - Brisbane Convention & Exhibition Centre, Brisbane, Australia Duration: 3 Aug 2025 → 8 Aug 2025 https://www.2025.ieeeigarss.org/

Conference

Conference	IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2025
Abbreviated title	IGARSS 2025
Country/Territory	Australia
City	Brisbane
Period	3/08/25 → 8/08/25
Internet address	https://www.2025.ieeeigarss.org/

Keywords

2026 OA procedure
cross-modal learning
disaster response
earthquake
high-resolution optical satellite imagery
image registration
natural disaster
SAR data
computer vision

Access to Document

10.1109/IGARSS55030.2025.11244021

Technical_Progress_Towards_Spacenet-9_-_Cross-Modal_Satellite_Imagery_Registration_for_Natural_Disaster_ResponsesFinal published version, 5.76 MBLicence: Taverne

Cite this

Hänsch, R., Arndt, J., Potnis, A., Dias, P., Persello, C., Pacifici, F., & Bacastow, T. M. (2025). Technical progress towards spacenet-9 - cross-modal satellite imagery registration for natural disaster responses. 609-613. Paper presented at IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2025, Brisbane, Queensland, Australia. https://doi.org/10.1109/IGARSS55030.2025.11244021

@conference{22c5c1de27aa4f73bb96422cb816ccc5,

title = "Technical progress towards spacenet-9 - cross-modal satellite imagery registration for natural disaster responses",

abstract = "The SpaceNet-9 challenge running in spring 2025 features a dataset for developing optical-SAR image registration algorithms that have the potential to simplify traditionally time-consuming preprocessing steps and could help accelerate analysis timelines in disaster response scenarios. Building on prior work that discusses the motivation for such a challenge, presents an initial dataset, and describes a baseline algorithm, this paper elaborates on the technical progress in improving the SpaceNet-9 challenge, the preliminary dataset to prepare the challenge, and the baseline algorithm. Specifically, we highlight the latest efforts in data annotation and quality assessment, dataset analysis, experiments in keypoint detection, and large-scale scene registration.",

keywords = "2026 OA procedure, cross-modal learning, disaster response, earthquake, high-resolution optical satellite imagery, image registration, natural disaster, SAR data, computer vision",

author = "Ronny H{\"a}nsch and Jacob Arndt and Abhishek Potnis and Philipe Dias and Claudio Persello and Fabio Pacifici and Bacastow, \{Todd M.\}",

note = "Publisher Copyright: {\textcopyright}2025 IEEE.; IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2025 : One Earth, IGARSS 2025 ; Conference date: 03-08-2025 Through 08-08-2025",

year = "2025",

month = nov,

day = "25",

doi = "10.1109/IGARSS55030.2025.11244021",

language = "English",

pages = "609--613",

url = "https://www.2025.ieeeigarss.org/",

}

Hänsch, R, Arndt, J, Potnis, A, Dias, P, Persello, C, Pacifici, F & Bacastow, TM 2025, 'Technical progress towards spacenet-9 - cross-modal satellite imagery registration for natural disaster responses', Paper presented at IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2025, Brisbane, Australia, 3/08/25 - 8/08/25 pp. 609-613. https://doi.org/10.1109/IGARSS55030.2025.11244021

Technical progress towards spacenet-9 - cross-modal satellite imagery registration for natural disaster responses. / Hänsch, Ronny; Arndt, Jacob; Potnis, Abhishek et al.
2025. 609-613 Paper presented at IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2025, Brisbane, Queensland, Australia.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Technical progress towards spacenet-9 - cross-modal satellite imagery registration for natural disaster responses

AU - Hänsch, Ronny

AU - Arndt, Jacob

AU - Potnis, Abhishek

AU - Dias, Philipe

AU - Persello, Claudio

AU - Pacifici, Fabio

AU - Bacastow, Todd M.

PY - 2025/11/25

Y1 - 2025/11/25

N2 - The SpaceNet-9 challenge running in spring 2025 features a dataset for developing optical-SAR image registration algorithms that have the potential to simplify traditionally time-consuming preprocessing steps and could help accelerate analysis timelines in disaster response scenarios. Building on prior work that discusses the motivation for such a challenge, presents an initial dataset, and describes a baseline algorithm, this paper elaborates on the technical progress in improving the SpaceNet-9 challenge, the preliminary dataset to prepare the challenge, and the baseline algorithm. Specifically, we highlight the latest efforts in data annotation and quality assessment, dataset analysis, experiments in keypoint detection, and large-scale scene registration.

AB - The SpaceNet-9 challenge running in spring 2025 features a dataset for developing optical-SAR image registration algorithms that have the potential to simplify traditionally time-consuming preprocessing steps and could help accelerate analysis timelines in disaster response scenarios. Building on prior work that discusses the motivation for such a challenge, presents an initial dataset, and describes a baseline algorithm, this paper elaborates on the technical progress in improving the SpaceNet-9 challenge, the preliminary dataset to prepare the challenge, and the baseline algorithm. Specifically, we highlight the latest efforts in data annotation and quality assessment, dataset analysis, experiments in keypoint detection, and large-scale scene registration.

KW - 2026 OA procedure

KW - cross-modal learning

KW - disaster response

KW - earthquake

KW - high-resolution optical satellite imagery

KW - image registration

KW - natural disaster

KW - SAR data

KW - computer vision

U2 - 10.1109/IGARSS55030.2025.11244021

DO - 10.1109/IGARSS55030.2025.11244021

M3 - Paper

AN - SCOPUS:105033573466

SP - 609

EP - 613

T2 - IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2025

Y2 - 3 August 2025 through 8 August 2025

ER -

Technical progress towards spacenet-9 - cross-modal satellite imagery registration for natural disaster responses

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this