Multi-modal Land Cover Classification of Historical Aerial Images and Topographic Maps Exploiting Attention-based Feature Fusion

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Autorschaft

  • Mareike Dorozynski
  • Franz Rottensteiner
  • Frank Thiemann
  • Monika Sester
  • Thorsten Dahms
  • Michael Hovenbitzer

Externe Organisationen

  • Bundesamt für Kartographie und Geodäsie (BKG)
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)221-229
Seitenumfang9
FachzeitschriftISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Jahrgang10
AusgabenummerG-2025
PublikationsstatusVeröffentlicht - 10 Juli 2025
Veranstaltung2025 International Society for Photogrammetry and Remote Sensing (ISPRS) Geospatial Week, GSW 2025 - Dubai, Vereinigte Arabische Emirate
Dauer: 6 Apr. 202511 Apr. 2025

Abstract

Knowledge about past and present land cover is of interest for the assessment of the current status of our environment and, thus, for proper planning of the future. Information on past land cover is exclusively contained in an implicit way in historic remote sensing imagery and historic topographic maps. To make this information explicit, pixel-wise classification methods based on neural networks can be used. The method proposed in this paper aims to automatically predict land cover based on historic aerial imagery and scanned topographic maps. The proposed deep learning-based classifier extracts features at different scales from both modalities and fuses the most complex topographic map features of the smallest scale to enrich the ones derived from the aerial images. Both, the multi-modal features and those of the aerial images at larger scales, are mapped to pixel-wise predictions by means of a decoder. Comprehensive experiments show that the result of the proposed multi-modal classifier are superior compared to those of a uni-modal aerial image classifier; the multi-modal mIOU of 82.3% is 1.4% larger than the one of uni-modal classifier. This demonstrates that aerial image classification can benefit from additional information contained in topographic maps.

ASJC Scopus Sachgebiete

Zitieren

Multi-modal Land Cover Classification of Historical Aerial Images and Topographic Maps Exploiting Attention-based Feature Fusion. / Dorozynski, Mareike; Rottensteiner, Franz; Thiemann, Frank et al.
in: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Jahrgang 10, Nr. G-2025, 10.07.2025, S. 221-229.

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Dorozynski, M, Rottensteiner, F, Thiemann, F, Sester, M, Dahms, T & Hovenbitzer, M 2025, 'Multi-modal Land Cover Classification of Historical Aerial Images and Topographic Maps Exploiting Attention-based Feature Fusion', ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Jg. 10, Nr. G-2025, S. 221-229. https://doi.org/10.5194/isprs-annals-X-G-2025-221-2025
Dorozynski, M., Rottensteiner, F., Thiemann, F., Sester, M., Dahms, T., & Hovenbitzer, M. (2025). Multi-modal Land Cover Classification of Historical Aerial Images and Topographic Maps Exploiting Attention-based Feature Fusion. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 10(G-2025), 221-229. https://doi.org/10.5194/isprs-annals-X-G-2025-221-2025
Dorozynski M, Rottensteiner F, Thiemann F, Sester M, Dahms T, Hovenbitzer M. Multi-modal Land Cover Classification of Historical Aerial Images and Topographic Maps Exploiting Attention-based Feature Fusion. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2025 Jul 10;10(G-2025):221-229. doi: 10.5194/isprs-annals-X-G-2025-221-2025
Dorozynski, Mareike ; Rottensteiner, Franz ; Thiemann, Frank et al. / Multi-modal Land Cover Classification of Historical Aerial Images and Topographic Maps Exploiting Attention-based Feature Fusion. in: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2025 ; Jahrgang 10, Nr. G-2025. S. 221-229.
Download
@article{235f14f8a62445f58694a4855e20de1a,
title = "Multi-modal Land Cover Classification of Historical Aerial Images and Topographic Maps Exploiting Attention-based Feature Fusion",
abstract = "Knowledge about past and present land cover is of interest for the assessment of the current status of our environment and, thus, for proper planning of the future. Information on past land cover is exclusively contained in an implicit way in historic remote sensing imagery and historic topographic maps. To make this information explicit, pixel-wise classification methods based on neural networks can be used. The method proposed in this paper aims to automatically predict land cover based on historic aerial imagery and scanned topographic maps. The proposed deep learning-based classifier extracts features at different scales from both modalities and fuses the most complex topographic map features of the smallest scale to enrich the ones derived from the aerial images. Both, the multi-modal features and those of the aerial images at larger scales, are mapped to pixel-wise predictions by means of a decoder. Comprehensive experiments show that the result of the proposed multi-modal classifier are superior compared to those of a uni-modal aerial image classifier; the multi-modal mIOU of 82.3% is 1.4% larger than the one of uni-modal classifier. This demonstrates that aerial image classification can benefit from additional information contained in topographic maps.",
keywords = "Attention-based Fusion, Historical Geodata, Multi-modal Classification, Remote Sensing Imagery, Semantic Segmentation, Topographic Maps",
author = "Mareike Dorozynski and Franz Rottensteiner and Frank Thiemann and Monika Sester and Thorsten Dahms and Michael Hovenbitzer",
note = "Publisher Copyright: Copyright {\textcopyright} 2025 Mareike Dorozynski et al.; 2025 International Society for Photogrammetry and Remote Sensing (ISPRS) Geospatial Week, GSW 2025, GSW 2025 ; Conference date: 06-04-2025 Through 11-04-2025",
year = "2025",
month = jul,
day = "10",
doi = "10.5194/isprs-annals-X-G-2025-221-2025",
language = "English",
volume = "10",
pages = "221--229",
number = "G-2025",

}

Download

TY - JOUR

T1 - Multi-modal Land Cover Classification of Historical Aerial Images and Topographic Maps Exploiting Attention-based Feature Fusion

AU - Dorozynski, Mareike

AU - Rottensteiner, Franz

AU - Thiemann, Frank

AU - Sester, Monika

AU - Dahms, Thorsten

AU - Hovenbitzer, Michael

N1 - Publisher Copyright: Copyright © 2025 Mareike Dorozynski et al.

PY - 2025/7/10

Y1 - 2025/7/10

N2 - Knowledge about past and present land cover is of interest for the assessment of the current status of our environment and, thus, for proper planning of the future. Information on past land cover is exclusively contained in an implicit way in historic remote sensing imagery and historic topographic maps. To make this information explicit, pixel-wise classification methods based on neural networks can be used. The method proposed in this paper aims to automatically predict land cover based on historic aerial imagery and scanned topographic maps. The proposed deep learning-based classifier extracts features at different scales from both modalities and fuses the most complex topographic map features of the smallest scale to enrich the ones derived from the aerial images. Both, the multi-modal features and those of the aerial images at larger scales, are mapped to pixel-wise predictions by means of a decoder. Comprehensive experiments show that the result of the proposed multi-modal classifier are superior compared to those of a uni-modal aerial image classifier; the multi-modal mIOU of 82.3% is 1.4% larger than the one of uni-modal classifier. This demonstrates that aerial image classification can benefit from additional information contained in topographic maps.

AB - Knowledge about past and present land cover is of interest for the assessment of the current status of our environment and, thus, for proper planning of the future. Information on past land cover is exclusively contained in an implicit way in historic remote sensing imagery and historic topographic maps. To make this information explicit, pixel-wise classification methods based on neural networks can be used. The method proposed in this paper aims to automatically predict land cover based on historic aerial imagery and scanned topographic maps. The proposed deep learning-based classifier extracts features at different scales from both modalities and fuses the most complex topographic map features of the smallest scale to enrich the ones derived from the aerial images. Both, the multi-modal features and those of the aerial images at larger scales, are mapped to pixel-wise predictions by means of a decoder. Comprehensive experiments show that the result of the proposed multi-modal classifier are superior compared to those of a uni-modal aerial image classifier; the multi-modal mIOU of 82.3% is 1.4% larger than the one of uni-modal classifier. This demonstrates that aerial image classification can benefit from additional information contained in topographic maps.

KW - Attention-based Fusion

KW - Historical Geodata

KW - Multi-modal Classification

KW - Remote Sensing Imagery

KW - Semantic Segmentation

KW - Topographic Maps

UR - http://www.scopus.com/inward/record.url?scp=105013264735&partnerID=8YFLogxK

U2 - 10.5194/isprs-annals-X-G-2025-221-2025

DO - 10.5194/isprs-annals-X-G-2025-221-2025

M3 - Conference article

AN - SCOPUS:105013264735

VL - 10

SP - 221

EP - 229

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

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

SN - 2194-9042

IS - G-2025

T2 - 2025 International Society for Photogrammetry and Remote Sensing (ISPRS) Geospatial Week, GSW 2025

Y2 - 6 April 2025 through 11 April 2025

ER -

Von denselben Autoren