Deep Learning-Based Land Use Land Cover Segmentation of Historical Aerial Images

Elif Sertel; Cengiz Avci; Mustafa Erdem Kabadayi

doi:10.1109/IGARSS52108.2023.10281819

Deep Learning-Based Land Use Land Cover Segmentation of Historical Aerial Images

Elif Sertel^*, Cengiz Avci, Mustafa Erdem Kabadayi

^*Corresponding author for this work

Department of Geomatics Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

This study aims to generate a new benchmark dataset from historical panchromatic aerial photographs suitable for deep learning-based Land use/Land cover (LULC) segmentation task. This new benchmark dataset spans a wide geographic area and consists of aerial photographs from various populous areas in Turkey and Bulgaria from the 1950s, 1960s, and 1970s. We implemented U-Net++ and Deeplabv3 segmentation architectures and appropriate hyperparameters and backbone structures to determine the applicability of this dataset, specifically for accurate and fast mapping of past terrain conditions. This unique historical LULC dataset and the different combinations of deep learning experiments proposed can be applied to different geographical regions with similar panchromatic datasets.

Original language	English
Title of host publication	IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2622-2625
Number of pages	4
ISBN (Electronic)	9798350320107
DOIs	https://doi.org/10.1109/IGARSS52108.2023.10281819
Publication status	Published - 2023
Event	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena, United States Duration: 16 Jul 2023 → 21 Jul 2023

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2023-July

Conference

Conference	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Country/Territory	United States
City	Pasadena
Period	16/07/23 → 21/07/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Funding

This work was supported by the European Research Council (ERC) project: “A GeoAI-based Land Use Land Cover Segmentation Process to Analyse and Predict Rural Depopulation, Agricultural Land Abandonment, and Deforestation in Bulgaria and Turkey, 1940-2040” under the European Union’s Horizon 2020 research and innovation program Grant Agreement No. 101100837, acronym GeoAI_LULC_Seg. We would like to thank Istanbul Technical University, Scientific Research Unit (ITU-BAP) for supporting Elif Sertel with the project ID. “FHD-2023-44797”.

Funders	Funder number
Deforestation in Bulgaria and Turkey
Horizon 2020 Framework Programme	101100837
European Research Council
Istanbul Teknik Üniversitesi
Bilimsel Araştırma Projeleri Birimi, İstanbul Teknik Üniversitesi	FHD-2023-44797

Keywords

deep learning
historical aerial photographs
LULC
segmentation

Access to Document

10.1109/IGARSS52108.2023.10281819

Cite this

Sertel, E., Avci, C., & Kabadayi, M. E. (2023). Deep Learning-Based Land Use Land Cover Segmentation of Historical Aerial Images. In IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 2622-2625). (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2023-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS52108.2023.10281819

Sertel, Elif ; Avci, Cengiz ; Kabadayi, Mustafa Erdem. / Deep Learning-Based Land Use Land Cover Segmentation of Historical Aerial Images. IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 2622-2625 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{18d0c10aa38145d3b637ff10edac562d,

title = "Deep Learning-Based Land Use Land Cover Segmentation of Historical Aerial Images",

abstract = "This study aims to generate a new benchmark dataset from historical panchromatic aerial photographs suitable for deep learning-based Land use/Land cover (LULC) segmentation task. This new benchmark dataset spans a wide geographic area and consists of aerial photographs from various populous areas in Turkey and Bulgaria from the 1950s, 1960s, and 1970s. We implemented U-Net++ and Deeplabv3 segmentation architectures and appropriate hyperparameters and backbone structures to determine the applicability of this dataset, specifically for accurate and fast mapping of past terrain conditions. This unique historical LULC dataset and the different combinations of deep learning experiments proposed can be applied to different geographical regions with similar panchromatic datasets.",

keywords = "deep learning, historical aerial photographs, LULC, segmentation",

author = "Elif Sertel and Cengiz Avci and Kabadayi, {Mustafa Erdem}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 ; Conference date: 16-07-2023 Through 21-07-2023",

year = "2023",

doi = "10.1109/IGARSS52108.2023.10281819",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2622--2625",

booktitle = "IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

address = "United States",

}

Sertel, E, Avci, C & Kabadayi, ME 2023, Deep Learning-Based Land Use Land Cover Segmentation of Historical Aerial Images. in IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2023-July, Institute of Electrical and Electronics Engineers Inc., pp. 2622-2625, 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023, Pasadena, United States, 16/07/23. https://doi.org/10.1109/IGARSS52108.2023.10281819

Deep Learning-Based Land Use Land Cover Segmentation of Historical Aerial Images. / Sertel, Elif; Avci, Cengiz; Kabadayi, Mustafa Erdem.
IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. p. 2622-2625 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2023-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep Learning-Based Land Use Land Cover Segmentation of Historical Aerial Images

AU - Sertel, Elif

AU - Avci, Cengiz

AU - Kabadayi, Mustafa Erdem

PY - 2023

Y1 - 2023

N2 - This study aims to generate a new benchmark dataset from historical panchromatic aerial photographs suitable for deep learning-based Land use/Land cover (LULC) segmentation task. This new benchmark dataset spans a wide geographic area and consists of aerial photographs from various populous areas in Turkey and Bulgaria from the 1950s, 1960s, and 1970s. We implemented U-Net++ and Deeplabv3 segmentation architectures and appropriate hyperparameters and backbone structures to determine the applicability of this dataset, specifically for accurate and fast mapping of past terrain conditions. This unique historical LULC dataset and the different combinations of deep learning experiments proposed can be applied to different geographical regions with similar panchromatic datasets.

AB - This study aims to generate a new benchmark dataset from historical panchromatic aerial photographs suitable for deep learning-based Land use/Land cover (LULC) segmentation task. This new benchmark dataset spans a wide geographic area and consists of aerial photographs from various populous areas in Turkey and Bulgaria from the 1950s, 1960s, and 1970s. We implemented U-Net++ and Deeplabv3 segmentation architectures and appropriate hyperparameters and backbone structures to determine the applicability of this dataset, specifically for accurate and fast mapping of past terrain conditions. This unique historical LULC dataset and the different combinations of deep learning experiments proposed can be applied to different geographical regions with similar panchromatic datasets.

KW - deep learning

KW - historical aerial photographs

KW - LULC

KW - segmentation

UR - http://www.scopus.com/inward/record.url?scp=85178377110&partnerID=8YFLogxK

U2 - 10.1109/IGARSS52108.2023.10281819

DO - 10.1109/IGARSS52108.2023.10281819

M3 - Conference contribution

AN - SCOPUS:85178377110

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 2622

EP - 2625

BT - IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023

Y2 - 16 July 2023 through 21 July 2023

ER -

Sertel E, Avci C, Kabadayi ME. Deep Learning-Based Land Use Land Cover Segmentation of Historical Aerial Images. In IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. p. 2622-2625. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS52108.2023.10281819

Deep Learning-Based Land Use Land Cover Segmentation of Historical Aerial Images

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this