Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 625-632 |
| Seitenumfang | 8 |
| Fachzeitschrift | International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives |
| Jahrgang | 43 |
| Ausgabenummer | B2-2022 |
| Publikationsstatus | Veröffentlicht - 30 Mai 2022 |
| Veranstaltung | 2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission II - Nice, Frankreich Dauer: 6 Juni 2022 → 11 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
- Informatik (insg.)
- Information systems
- Sozialwissenschaften (insg.)
- Geografie, Planung und Entwicklung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
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 Fachzeitschrift › Konferenzaufsatz in Fachzeitschrift › Forschung › Peer-Review
}
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 -