Helena Laasch

Last Name

Laasch

First Name

Helena

ORCID

0009-0001-0663-8465

Organisational unit

03964 - Wieser, Andreas / Wieser, Andreas

Show all metadata

Search Results

Publications 1 - 6 of 6

Machine Learning-Based Detection of Stone Degradation using TLS, Photographs and HBIM: A Case Study on the Lausanne Cathedral
Tennenini, Camilla; Laasch, Helena; Patankar, Yamini; et al. (2025)
STONE 2025 - Proceedings of the 15th International Congress on the Deterioration and Conservation of Stone, Volume 1 & 2
Historic sandstone structures are vulnerable to environmental degradation, requiring efficient damage assessment and documentation for effective conservation. Traditional manual mapping methods are time-intensive, cost-intensive, and challenging to standardize. Herein we present a semi-automated workflow for damage classification and integration into a historic building information model (HBIM) using terrestrial laser scanning (TLS), orthophotos, and machine learning. A Random Forest model, optimised through forward feature selection and Bayesian hyperparameter tuning, classifies degradation types (contour scaling, biodeterioration, black crust formation and exfoliation) based on geometric and radiometric features. Finally, degradation information is linked to individual stone blocks in the HBIM, and degradation maps can be generated. In a case study on the Lausanne Cathedral, we achieve an overall classification accuracy of 80% using this approach. The results highlight the potential of using machine-learning techniques with TLS data for an efficient and scalable heritage condition assessment.
Finding the Best TLS Point Cloud Registration Algorithm for Long-Range Geomonitoring
Laasch, Helena; Jacquemart, Mylène; Ruttner, Pia; et al. (2023)
Ingenieurvermessung 23: Beiträge zum 20. Internationalen Ingenieurvermessungskurs Zürich
Accurate registration of TLS (Terrestrial Laser Scanner) point clouds is essential for unbiased determination of deformations in long-range geomonitoring. We evaluated the performance of several established registration methods in an ongoing geomonitoring case study. Our results showed that the ICP (Iterative Closest Point)-based methods specifically developed with geomonitoring in mind perform the best. However, when dealing with distortions in point clouds, the newly developed stripe-wise non-rigid transformation based on the F2S3 (feature to feature supervoxel-based spatial smoothing) algorithm outperformed all established methods.
Towards Assessing Sandstone Surface Moisture and Degradation Level from Radiometrically Corrected TLS Intensity Data
Laasch, Helena; Medic, Tomislav; Wieser, Andreas (2023)
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Water is a prevalent deterioration agent for historic masonry works, especially those made of clay-bearing sandstones. To preserve cultural heritage made of sandstone, it is important to monitor, and then detect the regions with water retention or stone deterioration. To that aim, we investigate the prospects of terrestrial laser scanner (TLS) intensities for quantifying moisture in sandstone. Through a series of experiments following the drying processes of sandstone samples, we verify that TLS intensities can serve as moisture proxies for remote-sensing water retention. We identify the theoretically most suitable wavelengths, systematic effects requiring mitigation, and promising mitigation strategies. However, we also observe that the intensities are significantly affected by the type of sandstone and its level of degradation. Our results indicate that it is possible to distinguish different sandstones and levels of artificial degradation by observing and analyzing TLS-intensity time series during the drying process.
Automated Inspection within Galleries of Large Dams
Laasch, Helena; Ryter, Nathalie; Steffen, Isabelle; et al. (2022)
Volunteering for the Future - Geospatial Excellence for a Better Living: XXVII FIG Congress
Dams are widely used for energy production and need to be inspected to ensure their stability and most importantly security. So far, the inspection within dam galleries is done periodically in a manual manner, thus making it time-consuming, labor-intensive, and subjective. Alternatively, automated inspections can be challenging due to the narrow galleries, sparse lighting, and texture of the concrete. This paper presents a case study on data acquisition and evaluation of three different sensors concerning data suitability for automated crack detection within such environments. The evaluated sensors in this study are Leica mapping system BLK2GO, the Lumix digital single-lens mirrorless (DSLM) camera DMC-FZ2000, and the time of-flight depth camera Helios Lucid. The measurements and data acquisition were done using a mobile robotic platform in a 220 m long dam in the Swiss Alps. This paper proposes a data evaluation pipeline for the extraction of georeferenced cracks. The processing outcomes are critically analyzed in terms of geometric and prediction accuracies, the repeatability of the predicted cracks, as well as the economic aspects of proposed measurement solutions. For the crack detection, different methods based on convolutional neural networks (CNN) were assessed using the datasets acquired with the three sensors. The DSLM images showed the best outcome due to their highest resolution, allowing the detection of cracks wider than 1 mm. Furthermore, an approach for locating cracks within the 3D digital model of the dam was proposed. For this georeferencing task, two approaches are presented, namely the BLK2GO trajectory and the photogrammetric model obtained from the DSLM images. Ultimately, the findings indicate that using a combination of sensors outperforms stand alone solutions, i.e., a combination of the DSLM for the acquisition of images georeferenced based on the BLK2GO trajectory. This paper is a contribution toward inspection task automation within industrial environments using digital sensing and robotic
Automatic in-situ radiometric calibration for mobile laser scanning: Compensating for distance and angle of incidence effects
Laasch, Helena; Medic, Tomislav; Wieser, Andreas (2025)
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Laser scanner intensity data provide valuable insights into material properties, enabling applications such as point cloud segment ation and material probing. However, extracting meaningful information is challenging due to the influence of the measurement configuration represented by the angle of incidence (AOI) and distance. Although existing methods for radiometric calibration in terrestrial laser scanning (TLS) exist, they rely on either overlapping scans from discrete positions or on manual segmentation. This limits their applicability to mobile laser scanning (MLS), which typically produces very large datasets (requiring automation) with little or no overlap, and from continuously changing positions. This study presents an approach for adapting an automatic in-situ radiometric calibration method originally developed for TLS that applies to MLS. Building on our previous work, we introduce techniques to estimate AOI and distance influence compensation functions with little or without overlap, as well as non-discrete scan stations, and propose two strategies for AOI influence compensation - global and local. The global method computes one best-fitting AOI compensation function for the entire scan. It uses local reflectance estimation, which relies on a modified filtering technique, accommodating the unique characteristics of MLS data. The local method computes the best-fitting AOI compensation function per segment, ideally containing a single material. We use machine learning for point cloud semantic segmentation with additional instance segmentation to automatically obtain a material proxy segment. We evaluate the proposed methods on four datasets captured by two different MLS systems, demonstrating their ability to reduce measurement configuration related influences on intensities and enhance following point cloud segmentation.
Automatic in-situ radiometric calibration of TLS: compensating distance and angle of incidence effects using overlapping scans
Laasch, Helena; Medic, Tomislav; Pfeifer, Norbert; et al. (2025)
ISPRS Journal of Photogrammetry and Remote Sensing
Terrestrial laser scanners (TLS) commonly record intensity of the backscattered signal as an auxiliary measurement, which can be related to material properties and used in various applications, such as point cloud segmentation. However, retrieving the material-related information from the TLS intensities is not trivial, as this information is overlayed by other systematic influences affecting the backscattered signal. One of the major factors that needs to be accounted for is the measurement configuration, which is defined by the instrument-to-target distance and angle of incidence (AOI). By obtaining measurement-configuration independent intensity (IMCI) material probing, classification, segmentation, and similar tasks can be enhanced. Current methods for obtaining such corrected intensities require additional dedicated measurement set-ups (often in a lab and with specialized targets) and manual work to estimate the effects of distance and AOI on the recorded values. Moreover, they are optimized only for specific datasets comprising a small number of targets with different material properties. This paper presents an automated method for in-situ estimation of IMCI, eliminating the need for additional dedicated measurements or manual work. Instead, the proposed method uses overlapping point clouds from different scan stations of an arbitrary scene that are anyway collected during a scanning project. We demonstrate the generalizability of the proposed method across different scenes and instruments, show how the retrieved IMCI values can improve segmentation, and how they increase the comparability of the intensities between different instruments.

Publications 1 - 6 of 6

Helena Laasch

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results