BUILDING CHANGE DETECTION IN AIRBORNE LASER SCANNING AND DENSE IMAGE MATCHING POINT CLOUDS USING A RESIDUAL NEURAL NETWORK

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Autoren

Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)625-632
Seitenumfang8
FachzeitschriftInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Jahrgang43
AusgabenummerB2-2022
PublikationsstatusVeröffentlicht - 30 Mai 2022
Veranstaltung2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission II - Nice, Frankreich
Dauer: 6 Juni 202211 Juni 2022

Abstract

National Mapping Agencies (NMAs) acquire nation-wide point cloud data from Airborne Laser Scanning (ALS) sensors as well as using Dense Image Matching (DIM) on aerial images. As these datasets are often captured years apart, they contain implicit information about changes in the real world. While detecting changes within point clouds is not a new topic per se, detecting changes in point clouds from different sensors, which consequently have different point densities, point distributions and characteristics, is still an on-going problem. As such, we approach this task using a residual neural network, which detects building changes using height and class information on a raster level. In the experiments, we show that this approach is capable of detecting building changes automatically and reliably independent of the given point clouds and for various building sizes achieving mean F1-Scores of 80.5% and 79.8% for ALS-ALS and ALS-DIM point clouds on an object-level and F1-Scores of 91.1% and 86.3% on a raster-level, respectively.

ASJC Scopus Sachgebiete

Zitieren

BUILDING CHANGE DETECTION IN AIRBORNE LASER SCANNING AND DENSE IMAGE MATCHING POINT CLOUDS USING A RESIDUAL NEURAL NETWORK. / Politz, F.; Sester, M.
in: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Jahrgang 43, Nr. B2-2022, 30.05.2022, S. 625-632.

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Politz, F & Sester, M 2022, 'BUILDING CHANGE DETECTION IN AIRBORNE LASER SCANNING AND DENSE IMAGE MATCHING POINT CLOUDS USING A RESIDUAL NEURAL NETWORK', International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Jg. 43, Nr. B2-2022, S. 625-632. https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-625-2022
Politz, F., & Sester, M. (2022). BUILDING CHANGE DETECTION IN AIRBORNE LASER SCANNING AND DENSE IMAGE MATCHING POINT CLOUDS USING A RESIDUAL NEURAL NETWORK. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, 43(B2-2022), 625-632. https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-625-2022
Politz F, Sester M. BUILDING CHANGE DETECTION IN AIRBORNE LASER SCANNING AND DENSE IMAGE MATCHING POINT CLOUDS USING A RESIDUAL NEURAL NETWORK. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. 2022 Mai 30;43(B2-2022):625-632. doi: 10.5194/isprs-archives-XLIII-B2-2022-625-2022
Politz, F. ; Sester, M. / BUILDING CHANGE DETECTION IN AIRBORNE LASER SCANNING AND DENSE IMAGE MATCHING POINT CLOUDS USING A RESIDUAL NEURAL NETWORK. in: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. 2022 ; Jahrgang 43, Nr. B2-2022. S. 625-632.
Download
@article{ae71b22497c14ed0a56165b42fd56321,
title = "BUILDING CHANGE DETECTION IN AIRBORNE LASER SCANNING AND DENSE IMAGE MATCHING POINT CLOUDS USING A RESIDUAL NEURAL NETWORK",
abstract = "National Mapping Agencies (NMAs) acquire nation-wide point cloud data from Airborne Laser Scanning (ALS) sensors as well as using Dense Image Matching (DIM) on aerial images. As these datasets are often captured years apart, they contain implicit information about changes in the real world. While detecting changes within point clouds is not a new topic per se, detecting changes in point clouds from different sensors, which consequently have different point densities, point distributions and characteristics, is still an on-going problem. As such, we approach this task using a residual neural network, which detects building changes using height and class information on a raster level. In the experiments, we show that this approach is capable of detecting building changes automatically and reliably independent of the given point clouds and for various building sizes achieving mean F1-Scores of 80.5% and 79.8% for ALS-ALS and ALS-DIM point clouds on an object-level and F1-Scores of 91.1% and 86.3% on a raster-level, respectively. ",
keywords = "Airborne Laser Scanning, Building Change Detection, Deep Learning, Dense Image Matching, density-independent, Jensen- Shannon-distance, Point Cloud Processing",
author = "F. Politz and M. Sester",
year = "2022",
month = may,
day = "30",
doi = "10.5194/isprs-archives-XLIII-B2-2022-625-2022",
language = "English",
volume = "43",
pages = "625--632",
number = "B2-2022",
note = "2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission II ; Conference date: 06-06-2022 Through 11-06-2022",

}

Download

TY - JOUR

T1 - BUILDING CHANGE DETECTION IN AIRBORNE LASER SCANNING AND DENSE IMAGE MATCHING POINT CLOUDS USING A RESIDUAL NEURAL NETWORK

AU - Politz, F.

AU - Sester, M.

PY - 2022/5/30

Y1 - 2022/5/30

N2 - National Mapping Agencies (NMAs) acquire nation-wide point cloud data from Airborne Laser Scanning (ALS) sensors as well as using Dense Image Matching (DIM) on aerial images. As these datasets are often captured years apart, they contain implicit information about changes in the real world. While detecting changes within point clouds is not a new topic per se, detecting changes in point clouds from different sensors, which consequently have different point densities, point distributions and characteristics, is still an on-going problem. As such, we approach this task using a residual neural network, which detects building changes using height and class information on a raster level. In the experiments, we show that this approach is capable of detecting building changes automatically and reliably independent of the given point clouds and for various building sizes achieving mean F1-Scores of 80.5% and 79.8% for ALS-ALS and ALS-DIM point clouds on an object-level and F1-Scores of 91.1% and 86.3% on a raster-level, respectively.

AB - National Mapping Agencies (NMAs) acquire nation-wide point cloud data from Airborne Laser Scanning (ALS) sensors as well as using Dense Image Matching (DIM) on aerial images. As these datasets are often captured years apart, they contain implicit information about changes in the real world. While detecting changes within point clouds is not a new topic per se, detecting changes in point clouds from different sensors, which consequently have different point densities, point distributions and characteristics, is still an on-going problem. As such, we approach this task using a residual neural network, which detects building changes using height and class information on a raster level. In the experiments, we show that this approach is capable of detecting building changes automatically and reliably independent of the given point clouds and for various building sizes achieving mean F1-Scores of 80.5% and 79.8% for ALS-ALS and ALS-DIM point clouds on an object-level and F1-Scores of 91.1% and 86.3% on a raster-level, respectively.

KW - Airborne Laser Scanning

KW - Building Change Detection

KW - Deep Learning

KW - Dense Image Matching

KW - density-independent

KW - Jensen- Shannon-distance

KW - Point Cloud Processing

UR - http://www.scopus.com/inward/record.url?scp=85132030476&partnerID=8YFLogxK

U2 - 10.5194/isprs-archives-XLIII-B2-2022-625-2022

DO - 10.5194/isprs-archives-XLIII-B2-2022-625-2022

M3 - Conference article

AN - SCOPUS:85132030476

VL - 43

SP - 625

EP - 632

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

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

SN - 1682-1750

IS - B2-2022

T2 - 2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission II

Y2 - 6 June 2022 through 11 June 2022

ER -

Von denselben Autoren