Details
Original language | English |
---|---|
Pages (from-to) | 613-628 |
Number of pages | 16 |
Journal | Journal of Applied Geodesy |
Volume | 18 |
Issue number | 4 |
Early online date | 19 Jun 2024 |
Publication status | Published - 1 Oct 2024 |
Abstract
Terrestrial laser scanners (TLSs) have become indispensable for acquiring highly detailed and accurate 3D representations of the physical world. However, the acquired data is subject to systematic deviations in distance measurements due to external influences, such as distance and incidence angle. This research introduces a calibration approach by applying a deep learning model based on PointNet to predict and correct these systematic distance deviations, incorporating not only the XYZ coordinates but also additional features like intensity, incidence angle, and distances within a local neighbourhood radius of 5 cm. By predicting and subsequently correcting systematic distance deviations, the quality of TLS point clouds can be improved. Hence, our model is designed to complement and build upon the foundation of prior internal TLS calibration. A data set collected under controlled environmental conditions, containing various objects of different materials, served as the basis for training and validation the PointNet based model. In addition our analysis showcase the model's capability to accurately model systematic distance deviations, outperforming existing methods like gradient boosting trees by capturing the spatial relationships and dependencies within the data more effectively. By defining test data sets, excluded from the training process, we underscore the ongoing effectiveness of our model's distance measurement calibration, showcasing its ability to improve the accuracy of the TLS point cloud.
Keywords
- calibration, deep learning, PointNet, systematic distance deviation, terrestrial laser scanning
ASJC Scopus subject areas
- Mathematics(all)
- Modelling and Simulation
- Engineering(all)
- Engineering (miscellaneous)
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Journal of Applied Geodesy, Vol. 18, No. 4, 01.10.2024, p. 613-628.
Research output: Contribution to journal › Review article › Research › peer review
}
TY - JOUR
T1 - PointNet-based modeling of systematic distance deviations for improved TLS accuracy
AU - Hartmann, Jan
AU - Ernst, Dominik
AU - Neumann, Ingo
AU - Alkhatib, Hamza
N1 - Publisher Copyright: © 2024 Walter de Gruyter GmbH, Berlin/Boston 2024.
PY - 2024/10/1
Y1 - 2024/10/1
N2 - Terrestrial laser scanners (TLSs) have become indispensable for acquiring highly detailed and accurate 3D representations of the physical world. However, the acquired data is subject to systematic deviations in distance measurements due to external influences, such as distance and incidence angle. This research introduces a calibration approach by applying a deep learning model based on PointNet to predict and correct these systematic distance deviations, incorporating not only the XYZ coordinates but also additional features like intensity, incidence angle, and distances within a local neighbourhood radius of 5 cm. By predicting and subsequently correcting systematic distance deviations, the quality of TLS point clouds can be improved. Hence, our model is designed to complement and build upon the foundation of prior internal TLS calibration. A data set collected under controlled environmental conditions, containing various objects of different materials, served as the basis for training and validation the PointNet based model. In addition our analysis showcase the model's capability to accurately model systematic distance deviations, outperforming existing methods like gradient boosting trees by capturing the spatial relationships and dependencies within the data more effectively. By defining test data sets, excluded from the training process, we underscore the ongoing effectiveness of our model's distance measurement calibration, showcasing its ability to improve the accuracy of the TLS point cloud.
AB - Terrestrial laser scanners (TLSs) have become indispensable for acquiring highly detailed and accurate 3D representations of the physical world. However, the acquired data is subject to systematic deviations in distance measurements due to external influences, such as distance and incidence angle. This research introduces a calibration approach by applying a deep learning model based on PointNet to predict and correct these systematic distance deviations, incorporating not only the XYZ coordinates but also additional features like intensity, incidence angle, and distances within a local neighbourhood radius of 5 cm. By predicting and subsequently correcting systematic distance deviations, the quality of TLS point clouds can be improved. Hence, our model is designed to complement and build upon the foundation of prior internal TLS calibration. A data set collected under controlled environmental conditions, containing various objects of different materials, served as the basis for training and validation the PointNet based model. In addition our analysis showcase the model's capability to accurately model systematic distance deviations, outperforming existing methods like gradient boosting trees by capturing the spatial relationships and dependencies within the data more effectively. By defining test data sets, excluded from the training process, we underscore the ongoing effectiveness of our model's distance measurement calibration, showcasing its ability to improve the accuracy of the TLS point cloud.
KW - calibration
KW - deep learning
KW - PointNet
KW - systematic distance deviation
KW - terrestrial laser scanning
UR - http://www.scopus.com/inward/record.url?scp=85196501922&partnerID=8YFLogxK
U2 - 10.1515/jag-2023-0097
DO - 10.1515/jag-2023-0097
M3 - Review article
AN - SCOPUS:85196501922
VL - 18
SP - 613
EP - 628
JO - Journal of Applied Geodesy
JF - Journal of Applied Geodesy
SN - 1862-9016
IS - 4
ER -