Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 493-500 |
| Seitenumfang | 8 |
| Fachzeitschrift | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Jahrgang | 5 |
| Ausgabenummer | 2 |
| Publikationsstatus | Veröffentlicht - 3 Aug. 2020 |
| Veranstaltung | 2020 24th ISPRS Congress on Technical Commission II - Nice, Virtual, Frankreich Dauer: 31 Aug. 2020 → 2 Sept. 2020 |
Abstract
Automated recognition of terrain structures is a major research problem in many application areas. These structures can be investigated in raster products such as Digital Elevation Models (DEMs) generated from Airborne Laser Scanning (ALS) data. Following the success of deep learning and computer vision techniques on color images, researchers have focused on the application of such techniques in their respective fields. One example is detection of structures in DEM data. DEM data can be used to train deep learning models, but recently, Du et al. (2019) proposed a multi-modal deep learning approach (hereafter referred to as MM) proving that combination of geomorphological information help improve the performance of deep learning models. They reported that combining DEM, slope, and RGB-shaded relief gives the best result among other combinations consisting of curvature, flow accumulation, topographic wetness index, and grey-shaded relief. In this work, we approve and build on top of this approach. First, we use MM and show that combinations of other information such as sky view factors, (simple) local relief models, openness, and local dominance improve model performance even further. Secondly, based on the recently proposed HR-Net (Sun et al., 2019), we build a tinier, Multi-Modal High Resolution network called MM-HR, that outperforms MM. MM-HR learns with fewer parameters (4 millions), and gives an accuracy of 84:2 percent on ZISM50m data compared to 79:2 percent accuracy by MM which learns with more parameters (11 millions). On the dataset of archaeological mining structures from Harz, the top accuracy by MM-HR is 91:7 percent compared to 90:2 by MM.
ASJC Scopus Sachgebiete
- Erdkunde und Planetologie (insg.)
- Erdkunde und Planetologie (sonstige)
- Umweltwissenschaften (insg.)
- Umweltwissenschaften (sonstige)
- Physik und Astronomie (insg.)
- Instrumentierung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Jahrgang 5, Nr. 2, 03.08.2020, S. 493-500.
Publikation: Beitrag in Fachzeitschrift › Konferenzaufsatz in Fachzeitschrift › Forschung › Peer-Review
}
TY - JOUR
T1 - Detection of Terrain Structures in Airborne Laser Scanning Data Using Deep Learning
AU - Kazimi, Bashir
AU - Thiemann, F.
AU - Sester, M.
N1 - Funding information: The project is funded by the Ministry of Science in Lower Saxony. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X Pascal GPU used for this research.
PY - 2020/8/3
Y1 - 2020/8/3
N2 - Automated recognition of terrain structures is a major research problem in many application areas. These structures can be investigated in raster products such as Digital Elevation Models (DEMs) generated from Airborne Laser Scanning (ALS) data. Following the success of deep learning and computer vision techniques on color images, researchers have focused on the application of such techniques in their respective fields. One example is detection of structures in DEM data. DEM data can be used to train deep learning models, but recently, Du et al. (2019) proposed a multi-modal deep learning approach (hereafter referred to as MM) proving that combination of geomorphological information help improve the performance of deep learning models. They reported that combining DEM, slope, and RGB-shaded relief gives the best result among other combinations consisting of curvature, flow accumulation, topographic wetness index, and grey-shaded relief. In this work, we approve and build on top of this approach. First, we use MM and show that combinations of other information such as sky view factors, (simple) local relief models, openness, and local dominance improve model performance even further. Secondly, based on the recently proposed HR-Net (Sun et al., 2019), we build a tinier, Multi-Modal High Resolution network called MM-HR, that outperforms MM. MM-HR learns with fewer parameters (4 millions), and gives an accuracy of 84:2 percent on ZISM50m data compared to 79:2 percent accuracy by MM which learns with more parameters (11 millions). On the dataset of archaeological mining structures from Harz, the top accuracy by MM-HR is 91:7 percent compared to 90:2 by MM.
AB - Automated recognition of terrain structures is a major research problem in many application areas. These structures can be investigated in raster products such as Digital Elevation Models (DEMs) generated from Airborne Laser Scanning (ALS) data. Following the success of deep learning and computer vision techniques on color images, researchers have focused on the application of such techniques in their respective fields. One example is detection of structures in DEM data. DEM data can be used to train deep learning models, but recently, Du et al. (2019) proposed a multi-modal deep learning approach (hereafter referred to as MM) proving that combination of geomorphological information help improve the performance of deep learning models. They reported that combining DEM, slope, and RGB-shaded relief gives the best result among other combinations consisting of curvature, flow accumulation, topographic wetness index, and grey-shaded relief. In this work, we approve and build on top of this approach. First, we use MM and show that combinations of other information such as sky view factors, (simple) local relief models, openness, and local dominance improve model performance even further. Secondly, based on the recently proposed HR-Net (Sun et al., 2019), we build a tinier, Multi-Modal High Resolution network called MM-HR, that outperforms MM. MM-HR learns with fewer parameters (4 millions), and gives an accuracy of 84:2 percent on ZISM50m data compared to 79:2 percent accuracy by MM which learns with more parameters (11 millions). On the dataset of archaeological mining structures from Harz, the top accuracy by MM-HR is 91:7 percent compared to 90:2 by MM.
KW - Airborne Laser Scanning
KW - Deep Learning
KW - Digital Elevation Models
KW - Multi-Modal Data Fusion
UR - http://www.scopus.com/inward/record.url?scp=85091068039&partnerID=8YFLogxK
U2 - 10.5194/isprs-annals-V-2-2020-493-2020
DO - 10.5194/isprs-annals-V-2-2020-493-2020
M3 - Conference article
AN - SCOPUS:85091068039
VL - 5
SP - 493
EP - 500
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 - 2
T2 - 2020 24th ISPRS Congress on Technical Commission II
Y2 - 31 August 2020 through 2 September 2020
ER -