TY - JOUR A1 - Brunn, Ansgar T1 - Zwangsfreie Richtungsmessungen T1 - Force-free Angle Measurements JF - zfv – Zeitschrift für Geodäsie, Geoinformation und Landmanagement N2 - Moderne, digitale, automatisierte Tachymeter bieten einen flexiblen Einsatz und erfordern gleichzeitig flexible Rechenverfahren. Einschränkungen der tradierten Auswerteverfahren in Bezug auf die Richtungsmessungen in den Zenit und in Richtung der Nullrichtung (Nullpunkt des Teilkreises) sind dabei nicht akzeptabel. Daher wird in diesem Beitrag ein neuer, auf Richtungsvektoren basierender Umgang mit Richtungsmessungen vorgeschlagen. Der direkte Vergleich des tradierten Verfahrens mit dem neuen Ansatz zeigt das neu gewonnene Potential, letztlich aber auch die Notwendigkeit, das Geodätische Rechnen neu zu erfinden. N2 - Modern, digital, automated total stations offer flexible use and at the same time require flexible calculation methods. Limitations of the traditional evaluation methods with regard to the angle measurements into the zenith and in the zero direction (zero point of the horizontal circle) are not acceptable. Therefore, a new handling of direction measurements based on direction vectors is proposed in this paper. The direct comparison of the traditional method with the new approach shows the newly gained potential, but ultimately also the necessity to reinvent geodetic computing. Y1 - 2024 U6 - https://doi.org/10.12902/zfv-0455-2023 VL - 149 IS - 1 SP - 45 EP - 51 PB - Wißner-Verlag ER - TY - INPR A1 - Okyere, Franz A1 - Lu, Meng A1 - Brunn, Ansgar T1 - Evaluating the Quality of Open Building Datasets for Mapping Urban Inequality: A Comparative Analysis Across 5 Cities Y1 - 2025 U6 - https://doi.org/10.48550/arXiv.2508.12872 ER - TY - JOUR A1 - Vahrenhold, Jan Richard A1 - Brandmeier, Melanie A1 - Müller, Markus Sebastian T1 - MMTSCNet: Multimodal Tree Species Classification Network for Classification of Multi-Source, Single-Tree LiDAR Point Clouds JF - Remote Sensing N2 - Trees play a critical role in climate regulation, biodiversity, and carbon storage as they cover approximately 30% of the global land area. Nowadays, Machine Learning (ML)is key to automating large-scale tree species classification based on active and passive sensing systems, with a recent trend favoring data fusion approaches for higher accuracy. The use of 3D Deep Learning (DL) models has improved tree species classification by capturing structural and geometric data directly from point clouds. We propose a fully Multimodal Tree Species Classification Network (MMTSCNet) that processes Light Detection and Ranging (LiDAR) point clouds, Full-Waveform (FWF) data, derived features, and bidirectional, color-coded depth images in their native data formats without any modality transformation. We conduct several experiments as well as an ablation study to assess the impact of data fusion. Classification performance on the combination of Airborne Laser Scanning (ALS) data with FWF data scored the highest, achieving an Overall Accuracy (OA) of nearly 97%, a Mean Average F1-score (MAF) of nearly 97%, and a Kappa Coefficient of 0.96. Results for the other data subsets show that the ALS data in combination with or even without FWF data produced the best results, which was closely followed by the UAV-borne Laser Scanning (ULS) data. Additionally, it is evident that the inclusion of FWF data provided significant benefits to the classification performance, resulting in an increase in the MAF of +4.66% for the ALS data, +4.69% for the ULS data under leaf-on conditions, and +2.59% for the ULS data under leaf-off conditions. The proposed model is also compared to a state-of-the-art unimodal 3D-DL model (PointNet++) as well as a feature-based unimodal DL architecture (DSTCN). The MMTSCNet architecture outperformed the other models by several percentage points, depending on the characteristics of the input data. Y1 - 2025 U6 - https://doi.org/https://doi.org/10.3390/rs17071304 SN - 2072-4292 VL - 17 IS - 7 PB - MDPI AG ER - TY - CHAP A1 - Melnyk, Oleksandr A1 - Brunn, Ansgar T1 - Seasonal and Long-Term Water Regime Trends of Cheremsky Wetland: Analysis Based on Sentinel-2 Spectral Indices and Composite Indicator Development T2 - Remote Sensing 2025 N2 - Wetlands are critically important ecosystems, but their dynamics, especially in complex regions such as the Ukrainian Polissya, remain poorly understood. This study focuses on the Cheremsky Nature Reserve, an internationally important wetland, to assess long-term (2017–2024) seasonal (spring-summer) trends in water surface conditions. Using Sentinel-2 data and the Google Earth Engine platform, 14 spectral water indices were calculated. Their temporal trends were analyzed using Sen’s method, mutual correlations, and principal component analysis (PCA) to identify the main patterns of variability. Based on the normalized trends and weights obtained from the first two principal components, an integral composite index (CI) for spring and summer seasons was developed. The results revealed seasonal differences in the behavior of the indices and their contribution to the principal components, as well as spatial differentiation of water regime trends within the reserve. The proposed CI allows for an integrated assessment of the long-term dynamics of the wetlands, which is important for the development of conservation and management strategies. KW - remote sensing KW - Sentinel-2 KW - spectral indices KW - composite index KW - Ukrainian Polissya KW - wetland monitoring KW - water surface conditions Y1 - 2025 U6 - https://doi.org/10.3390/rs17142363 VL - 17 IS - 14 ER - TY - JOUR A1 - Melnyk, Oleksander A1 - Brunn, Ansgar T1 - Analysis of Spectral Index Interrelationships for Vegetation Condition Assessment on the Example of Wetlands in Volyn Polissya, Ukraine JF - earth N2 - The Cheremskyi Nature Reserve, situated in the Volyn region of Ukraine, constitutes a pivotal element of the European ecological network, distinguished by its distinctive mosaic of peatlands, bogs, and floodplain forests. This study utilizes Sentinel-2 satellite imagery and the Google Earth Engine (GEE) to assess the spatiotemporal patterns of various vegetation indices (NDVI, EVI, SAVI, MSAVI, GNDVI, NDRE, NDWI) from 2017 to 2024. The study aims to select the most suitable combination of vegetation spectral indices for future research. The analysis reveals significant negative trends in NDVI, SAVI, MSAVI, GNDVI, and NDRE, indicating a decline in vegetation health, while NDWI shows a positive trend, suggesting an increased vegetation water content. Correlation analysis underscores robust interrelationships among the indices, with NDVI and SAVI identified as the most significant through random forest feature importance analysis. Principal component analysis (PCA) further elucidates the primary axes of variability, emphasizing the complex interplay between vegetation greenness and moisture content. The findings underscore the utility of multi-index analyses in enhancing predictive capabilities for ecosystem monitoring and support targeted conservation strategies for the sustainable management of the Cheremskyi Nature Reserve. KW - remote sensing KW - sentinel-2 KW - vegetation indices KW - wetlands KW - peatlands KW - ecosystem monitoring Y1 - 2025 UR - https://www.mdpi.com/2673-4834/6/2/28 U6 - https://doi.org/10.3390/earth6020028 VL - 6 IS - 2 ER - TY - JOUR A1 - Schülein, Tim A1 - Christos K., Georgantopoulos A1 - Bolk, Lars A1 - Herrmann, Volker A1 - Wilhelm, Manfred T1 - Thermo-Mechanical Degradation Kinetics of a High-Density Poly(Ethylene) Using a Closed-Cavity Rheometer JF - Journal of Applied Polymer Science N2 - Mechanical recycling of polymers is an essential aspect to achieve circular economy. High shear stress, excessive temperature, and long residence time during reprocessing cause thermo-mechanical degradation of the polymer. Therefore, it is important to understand and quantify this degradation kinetics. Common ways to simulate degradation are very time and material consuming and clear insights into the respective influence of temperature and shear stress on degradation are rare. Within this publication a method is developed using a commercially available, close-cavity rheometer to emulate processing conditions in a defined way. This allows monitoring and predicting the behavior of a high-density polyethylene (HDPE) and quantify degradation kinetics and changes in the polymer topology. HDPE is selected as a model polymer due to its large production and wide range of applications. Different treated samples are analyzed by various rheological methods. Additionally, molecular characterization is conducted. A kinetic model to predict the changes in the molecular weight as a function of in-phase shear stress, temperature and duration during treatment is presented. The calculated activation energy for the initiation reaction agrees with the activation energy for HDPE degradation from thermogravimetric analysis. This activation energy is lowered by in-phase shear stress, modified by a factor of 1.7 m3 mol−1. Y1 - 2025 U6 - https://doi.org/10.1002/app.56784 VL - 142 IS - 17 ER - TY - JOUR A1 - Herrmann, Volker T1 - Internationalisierung als mögliche Lösung für das Problem des Fachkräftemangels JF - Kautschuk Gummi Kunststoffe 77 Y1 - 2024 SP - 8 EP - 9 ER - TY - JOUR A1 - Herrmann, Volker A1 - Frosch, Stefan A1 - Schülein, Tim A1 - Grunert, Fabian A1 - Blume, Anke T1 - Sulfur Diffusion Studies Imitating Recycled Ground-Rubber-Containing Compounds JF - Polymers N2 - n-rubber properties of vulcanizates deteriorate in the presence of incorporated recycled ground rubber (GR). This behavior is partly explained by a possible diffusion of sulfur from the rubber matrix into the GR. Therefore, the sulfur concentration and, thus, the crosslink density in the matrix are reduced. This phenomenon was further investigated in this research work using two spatially resolved methods that supplement each other: the diffusion of soluble sulfur in GR-containing compounds was locally investigated via Micro X-Ray Fluorescence analysis. Viscoelastic properties were also determined spatially by the Micro Dynamic-Mechanical Indentation method. Combining the results of both methods, local concentrations of sulfur were related to local viscoelastic properties, revealing great differences in crosslink density at the interface between the GR and matrix material. In this way, it is shown that sulfur is capable of diffusing several mm, which locally doubles its concentration with respect to the sulfur content of the compound formulation. This, in turn, negatively impacts the homogeneity of crosslink density in both the matrix and GR, revealing a local increase in the elastic stiffness of 100 %. In addition, it was found that the vulcanization characteristics of the used polymers determine the amount of sulfur diffusion and, thus, the change in viscoelastic properties. Y1 - 2024 U6 - https://doi.org/10.3390/polym16223112 VL - 16 IS - 22 ER - TY - JOUR A1 - Speckenwirth, Sönke A1 - Brandmeier, Melanie A1 - Paczkowski, Sebastian T1 - TreeSeg - A Toolbox for Fully Automated Tree Crown Segmentation Based on High-Resolution Multispectral UAV Data JF - remote sensing N2 - Single-tree segmentation on multispectral UAV images shows significant potential for effective forest management such as automating forest inventories or detecting damage and diseases when using an additional classifier. We propose an automated workflow for segmentation on high-resolution data and provide our trained models in a Toolbox for ArcGIS Pro on our GitHub repository for other researchers. The database used for this study consists of multispectral UAV data (RGB, NIR and red edge bands) of a forest area in Germany consisting of a mix of tree species consisting of five deciduous trees and three conifer tree species in the matured closed canopy stage at approximately 90 years. Information of NIR and Red Edge bands are evaluated for tree segmentation using different vegetation indices (VIs) in comparison to only using RGB information. We trained Faster R-CNN, Mask R-CNN, TensorMask and SAM in several experiments and evaluated model performance on different data combinations. All models with the exception of SAM show good performance on our test data with the Faster R-CNN model trained on the red and green bands and the Normalized Difference Red Edge Index (NDRE) achieving best results with an F1-Score of 83.5% and an Intersection over Union of 65.3% on highly detailed labels. All models are provided in our TreeSeg toolbox and allow the user to apply the pre-trained models on new data. Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:863-opus-57590 VL - 16 IS - 19 PB - MDPI ER - TY - JOUR A1 - Hell, Maximilian A1 - Brandmeier, Melanie T1 - Identifying Plausible Labels from Noisy Training Data for a Land Use and Land Cover Classification Application in Amazônia Legal JF - remote sensing N2 - Most studies in the field of land use and land cover (LULC) classification in remote sensing rely on supervised classification, which requires a substantial amount of accurate label data. However, reliable data are often not immediately available, and are obtained through time-consuming manual labor. One potential solution to this problem is the use of already available classification maps, which may not be the true ground truth and may contain noise from multiple possible sources. This is also true for the classification maps of the MapBiomas project, which provides land use and land cover (LULC) maps on a yearly basis, classifying the Amazon basin into more than 24 classes based on the Landsat data. In this study, we utilize the Sentinel-2 data with a higher spatial resolution in conjunction with the MapBiomas maps to evaluate a proposed noise removal method and to improve classification results. We introduce a novel noise detection method that relies on identifying anchor points in feature space through clustering with self-organizing maps (SOM). The pixel label is relabeled using nearest neighbor rules, or can be removed if it is unknown. A challenge in this approach is the quantification of noise in such a real-world dataset. To overcome this problem, highly reliable validation sets were manually created for quantitative performance assessment. The results demonstrate a significant increase in overall accuracy compared to MapBiomas labels, from 79.85% to 89.65%. Additionally, we trained the L2HNet using both MapBiomas labels and the filtered labels from our approach. The overall accuracy for this model reached 93.75% with the filtered labels, compared to the baseline of 74.31%. This highlights the significance of noise detection and filtering in remote sensing, and emphasizes the need for further research in this area. Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:863-opus-57532 VL - 26 IS - 12 ER - TY - JOUR A1 - Brandmeier, Melanie A1 - Heßdörfer, Daniel A1 - Siebenlist, Philipp A1 - Meyer-Spelbrink, Adrian A1 - Kraus, Anja T1 - Time Series Analysis of Multisensor Data for Precision Viticulture BT - Assessing Microscale Variations in Plant Development with Respect to Irrigation and Topography JF - remote sensing N2 - In the context of climate change, vineyard monitoring to better understand spatiotemporal patterns of grapevine development is of utter importance for precision viticulture. We present a time series analysis of hyperspectral in situ and multispectral UAV data for different irrigation systems in Lower Franconia and correlate results with sensor data for soil moisture, temperature, and precipitation. Analysis of Variance (ANOVA) and a Tukey’s HSD test were performed to see whether Vegetation Indices (VIs) are significantly different with respect to irrigation systems as well as topographic position in the vineyard. Correlation between in situ measurements and UAV data for selected VIs is also investigated for upscaling analysis. We find significant differences with respect to irrigation, as well as for topographic position for most of the VIs investigated, highlighting the importance of adapted water management. Correlation between in situ and UAV data is significant only for some indices (NDVI and CIRedEdge, 𝑟2 of 0.33 and 0.49, respectively), while shallow soil moisture patterns correlate well with in situ-derived VIs such as the CIRedEdge and RG index (𝑟2 of 0.34 and 0.46). Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:863-opus-57527 VL - 16 IS - 8 PB - MDPI ER - TY - CHAP A1 - Langner, Normen A1 - Brunn, Ansgar A1 - Voellner, David T1 - Drone-based Optimization And Validation Of Numerical Simulations Of Urban Heat Islands T2 - SimBuild 2024 - Eleventh National Conference of IBPSA-USA, Denver, 2024 N2 - In this ongoing research project, advanced drone technology is employed in conjunction with simula-tion models to assess the impacts of urban climate, with a specific focus on Urban Heat Islands (UHI). The novel methodology was tested in the historical downtown areas of two German cities. Through the creation of high-resolution 3D-models of urban structures and the analysis of material properties, the research project aims to accurately predict the cli-mate impacts of urban planning decisions.The results of the project provide planners with pre-cise insights for evaluating adaptation measures and mitigating the adverse effects of climate change in cities, ultimately improving living conditions there-in. The research undertaking also pioneers the use of high-temporal-resolution drone data for analyzing temperature patterns and considers various contribu-tions to the heat island effect for comprehensive climate-adaptive urban planning. Y1 - 2024 UR - https://publications.ibpsa.org/conference/paper/?id=simbuild2024_2132 ER - TY - JOUR A1 - Brunn, Ansgar A1 - Uhl, Anna A1 - Melnyk, Oleksandr A1 - Melnyk, Yuliia A1 - Manko, Pavlo A1 - Fesyuk, Vasyl T1 - Remote sensing monitoring of changes in forest cover in the Volyn region BT - A cross section for the first two decades of the 21st century JF - Visnyk of V. N. Karazin Kharkiv National University, series "Geology. Geography. Ecology N2 - This article highlights the significance of forest cover as an important indicator of the state of the environment. It discusses the findings of the Food and Agriculture Organization of the United Nations (FAO) Forest Resources Assessment (FRA) 2020 report, which states that the world's forest area has decreased by 178 million hectares since 1990. The case study of Volyn region shows how cloud processing and vegetation classification can help quantify forest dynamics from 2000 to 2020, allowing local authorities and decision makers to monitor and analyze trends in near real time. Overall, this work provides insights into the importance of monitoring forest dynamics and the potential for remote sensing technology to facilitate this process Y1 - 2024 U6 - https://doi.org/10.26565/2410-7360-2024-60-19 IS - 60 SP - 272 EP - 283 PB - V. N. Karazin Kharkiv National University ER - TY - JOUR A1 - Anwander, Julia A1 - Brandmeier, Melanie A1 - Paczkowski, Sebastian A1 - Neubert, Tarek A1 - Paczkowska, Marta T1 - Evaluating Different Deep Learning Approaches for Tree Health Classification Using High-Resolution Multispectral UAV Data in the Black Forest, Harz Region, and Göttinger Forest JF - Remote Sensing N2 - We present an evaluation of different deep learning and machine learning approaches for tree health classification in the Black Forest, the Harz Mountains, and the Göttinger Forest on a unique, highly accurate tree-level dataset. The multispectral UAV data were collected from eight forest plots with diverse tree species, mostly conifers. As ground truth data (GTD), nearly 1500 tree polygons with related attribute information on the health status of the trees were used. This data were collected during extensive fieldwork using a mobile application and subsequent individual tree segmentation. Extensive preprocessing included normalization, NDVI calculations, data augmentation to deal with the underrepresented classes, and splitting the data into training, validation, and test sets. We conducted several experiments using a classical machine learning approach (random forests), as well as different convolutional neural networks (CNNs)—ResNet50, ResNet101, VGG16, and Inception-v3—on different datasets and classes to evaluate the potential of these algorithms for tree health classification. Our first experiment was a binary classifier of healthy and damaged trees, which did not consider the degree of damage or tree species. The best results of a 0.99 test accuracy and an F1 score of 0.99 were obtained with ResNet50 on four band composites using the red, green, blue, and infrared bands (RGBI images), while VGG16 had the worst performance, with an F1 score of only 0.78. In a second experiment, we also distinguished between coniferous and deciduous trees. The F1 scores ranged from 0.62 to 0.99, with the highest results obtained using ResNet101 on derived vegetation indices using the red edge band of the camera (NDVIre images). Finally, in a third experiment, we aimed at evaluating the degree of damage: healthy, slightly damaged, and medium or heavily damaged trees. Again, ResNet101 had the best performance, this time on RGBI images with a test accuracy of 0.98 and an average F1 score of 0.97. These results highlight the potential of CNNs to handle high-resolution multispectral UAV data for the early detection of damaged trees when good training data are available. KW - tree health KW - classification KW - deep learning KW - CNNs KW - UAV KW - multispectral Y1 - 2024 U6 - https://doi.org/10.3390/rs16030561 VL - 16 IS - 3 SP - 561 EP - 561 ER - TY - CHAP A1 - Herrmann, Volker T1 - Überlegungen und Ergebnisse zur intrinsischen Deformation von Elastomeren mit Gummimehl T2 - 113. Tagung der Regionalgruppe Süd der Deutschen Kautschuk Gesellschaft DKG, Würzburg Y1 - 2023 ER - TY - CHAP A1 - Vetter, Mark A1 - Olberding, Helge T1 - Map Symbol Development for 3D Cartography suitable in VR-Environments T2 - Abstracts ot the International Cartographic Association Y1 - 2022 U6 - https://doi.org/10.5194/ica-abs-5-100-2022 VL - 5 ER - TY - CHAP A1 - Vetter, Mark T1 - The usage of “fog” as a visual variable in 3D-cartographic virtual reality environments T2 - Abstracts ot the International Cartographic Association Y1 - 2023 U6 - https://doi.org/10.5194/ica-abs-6-263-2023 VL - 6 ER - TY - JOUR A1 - Vetter, Mark A1 - Kasang, Christa A1 - Sousa, Arturo T1 - Fight against neglected infectious diseases in Togo with Geographic Information Systems JF - Euro-Mediterranean Journal for Environmental Integration Y1 - 2023 ER - TY - JOUR A1 - Vetter, Mark A1 - Aguilar-Alba, Mónica A1 - Garcia-Barron, Leoncio A1 - Morales, Julia A1 - Sousa, Arturo T1 - Possible syndemics in Spain during the 20th century associated with autochthonous malaria JF - Euro-Mediterranean Journal for Environmental Integration Y1 - 2023 ER - TY - CHAP A1 - Wilkening, Jan A1 - Miene, Jan Paul T1 - Bikeability and Beyond: Approaches for Measuring the Quality of Cycling T2 - Proceedings of the 18th International Conference on Location-Based Services Y1 - 2023 ER - TY - JOUR A1 - Frosch, Stefan A1 - Herrmann, Volker A1 - Grunert, F. A1 - Blume, A. T1 - Quantification of sulfur distribution on rubber surfaces by means of μ-X-ray fluorescence analysis JF - Polymer Testing N2 - A homogeneous distribution of sulfur in a rubber compound is often desired. Spatially resolved imaging techniques are useful for evaluating the distribution of this crosslinking chemical. Typical measurement methods such as SEM (scanning electron microscopy) or TEM (transmission electron microscopy) have very high resolutions. However, the sample size or the maximum area to be investigated is limited, which makes it difficult to obtain a statistically reliable determination of sulfur homogeneity across the component or sample. In this work, an alternative measurement technique is therefore presented: the μ-XRF (μ-X-ray fluorescence analysis). With the help of this method, it is possible to scan surfaces of several cm2 and to show the distribution of different chemical elements. Its measuring principle has been known for decades but has hardly been used in the rubber industry so far. The main reason for this is that its quantification process for polymeric samples is more complex than for geologic or metallic samples, which are typically been investigated with μ-XRF to date. In this paper, this issue is addressed and a solution is presented: With the help of the fundamental parameter method, the determination of sulfur homogeneity and distribution on rubber surfaces becomes possible. This opens up a variety of further possibilities for the use of μ-XRF in the rubber industry: For example, it could be used in areas of tire production, recycling of end-of-life rubber, and beyond. Y1 - 2023 U6 - https://doi.org/10.1016/j.polymertesting.2023.108237 VL - 128 IS - 108237 ER - TY - JOUR A1 - Olberding, Helge A1 - Vetter, Mark T1 - Dynamic 3D-Cartographic Symbols for VR Geovisualizations JF - KN - Journal of Cartography and Geographic Information N2 - Geovisualizations that use a virtual reality headset can have a more immersive effect on users than when only a desktop application is viewed. However, to have an overview, a VR 3D map is usually viewed from a top-down perspective. On the other hand, the first-person perspective is used when the scenario is visualized as realistically as possible, and the ultimate goal is to feel present inside the 3D city. With the help of dynamic cartographic visualization methods, such as animated symbols appearing or a dynamic change of selected or complete visualization, it is possible to convey targeted information while being inside the 3D. For this purpose, techniques and ideas from cartography and video games were utilized and combined. The combination resulted in dynamically changeable symbol objects, which can be placed automatically using tables or building information, and dynamically changeable post-processing methods. Users can interactively select a predefined set of visualization methods and show/hide dynamic cartographic symbols in the running application via an interface. The study aims to develop cartographic visualization methods that can be technically used within a game engine for VR applications to improve spatial perception. KW - 3D KW - Cartographic symbols KW - Geovisualization KW - Interactive KW - NPR KW - Virtual reality Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:863-opus-53072 SN - 2524-4965 VL - 73 IS - 4 SP - 265 EP - 275 ER - TY - JOUR A1 - Hart, Lukas A1 - Knoblach, Stefan A1 - Möser, Michael T1 - Automated pipeline reconstruction using deep learning & instance segmentation JF - ISPRS Open Journal of Photogrammetry and Remote Sensing N2 - BIM is a powerful tool for the construction industry as well as for various other industries, so that its use has increased massively in recent years. Laser scanners are usually used for the measurement, which, in addition to the high acquisition costs, also cause problems on reflective surfaces. The use of photogrammetric techniques for BIM in industrial plants, on the other hand, is less widespread and less automated. CAD software (for point cloud evaluation) contains at best automated reconstruction algorithms for pipes. Fittings, flanges or elbows require a manual reconstruction. We present a method for automated processing of photogrammetric images for modeling pipelines in industrial plants. For this purpose we use instance segmentation and reconstruct the components of the pipeline directly based on the edges of the segmented objects in the images. Hardware costs can be kept low by using photogrammetry instead of laser scanning. Besides the autmatic extraction and reconstruction of pipes, we have also implemented this for elbows and flanges. For object recognition, we fine-tuned different instance segmentation models using our own training data, while also testing various data augmentation techniques. The average precision varies depending on the object type. The best results were achieved with Mask R–CNN. Here, the average precision was about 40%. The results of the automated reconstruction were examined with regard to the accuracy on a test object in the laboratory. The deviations from the reference geometry were in the range of a few millimeters and were comparable to manual reconstruction. In addition, further tests were carried out with images from a plant. Provided that the objects were correctly and completely recognized, a satisfactory reconstruction is possible with the help of our method. Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:863-opus-53620 VL - 9 PB - Elsevier ER - TY - CHAP A1 - Hell, Maximilian A1 - Brandmeier, Melanie A1 - Nüchter, Andreas ED - Kersten, Thomas P. ED - Tilly, Nora T1 - Transferability of Deep Learning Models for Land Use/Land Cover Classification T2 - 43. Wissenschaftlich-Technische Jahrestagung der DGPF in München. 22.-23. März 2023 in München - Publikationen der DGPF Y1 - 2023 U6 - https://doi.org/10.24407/KXP:1841078182 VL - 31 SP - 142 EP - 149 ER - TY - CHAP A1 - Vetter, Mark ED - Edler, Dennis ED - Jenal, Corinna ED - Kühne, Olaf T1 - Technical Potentials for the Visualization in Virtual Reality T2 - Modern Approaches to the Visualization of Landscapes Y1 - 2020 SN - 978-3-658-30955-8 978-3-658-30956-5 U6 - https://doi.org/10.1007/978-3-658-30956-5_17 SP - 307 EP - 317 ER - TY - JOUR A1 - Sousa, Arturo A1 - Aguilar-Alba, Mónica A1 - Vetter, Mark A1 - García-Barrón, Leoncio A1 - Morales, Julia T1 - Drivers of autochthonous and imported malaria in Spain and their relationship with meteorological variables JF - Euro-Mediterranean Journal for Environmental Integration Y1 - 2021 U6 - https://doi.org/10.1007/s41207-021-00245-8 SN - 2365-6433 SN - 2365-7448 VL - 6 IS - 1 SP - 33 EP - 33 ER -