TY - CPAPER TI - Integrating timber stability analysis for building life cycle management and HBIM framework support AU - Chizhova, Maria AU - Pan, Junquan AU - Kempter, Gerold AU - Luhmann, Thomas AU - Eißing, Thomas AU - Hess, Mona PY - 2026 SP - 559-564 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/117402 LA - eng AB - The digital documentation of heritage architecture, particularly historic wooden roof structures, has gained significant importance in recent years. Heritage Building Information Modelling (HBIM) has emerged as a crucial field that focuses on the digital representation and management of historic buildings. However, modelling heritage structures in accordance with BIM standards poses challenges due to the complex geometries and specialized information inherent with heritage timber structure. This article presents a workflow that illustrates the integration of an automated, AI-supported analysis of wood knottiness to assess unknown strength values of aged heritage timbers within building life cycle management and supporting the BIM framework. For this purpose, an algorithm for automatic wood knottiness estimation has been developed and implemented as a smartphone-based app-prototype, which facilitates efficient data collection, automatic analysis, and seamless integration into the BIM modelling process, while minimizing potential data loss during exchange. KW - Timber stability assessment KW - Smartphone app KW - openBIM KW - HBIM KW - Data transfer ER - TY - CPAPER TI - Simulation of Stationary and Mobile Laserscanning with VRscan3D AU - Gorkovchuk, Denys AU - Horkovchuk, Julia AU - Chizhova, Maria AU - Popovas, Darius AU - Luhmann, Thomas PY - 2026 SP - 181-188 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/117401 LA - eng AB - Terrestrial and mobile laser scanning technologies have become essential tools in geoinformation, surveying, cultural heritage documentation, and construction. However, access to modern laser scanning equipment remains limited for many universities and training institutions due to high costs, logistical constraints, or disruptions caused by crises such as pandemics or military conflicts. The VRscan3D project addresses this challenge by developing a realistic virtual simulator for stationary and mobile laser scanning that supports education, training, and research. VRscan3D is based on a game-engine environment that enables immersive interaction with virtual scanning devices and realistic 3D scenes. The simulator reproduces the physical parameters of real terrestrial laser scanners. Users can define scan stations, configure scanning parameters, and generate synthetic point clouds that incorporate realistic noise, intensity behavior, and beam characteristics. The platform also supports simulation of mobile scanning systems, including handheld scanners, mobile platforms, and UAV-based systems, allowing users to explore error propagation, scanning trajectories, and operator influence on data quality. In addition to training purposes, VRscan3D enables the generation of synthetic point clouds with known ground truth for testing point cloud processing algorithms and training AI models. Ongoing research focuses on comparing simulated and real datasets to evaluate the accuracy and reliability of synthetic scanning data under dynamic conditions. KW - terrestrial laser scanning KW - simulation KW - point cloud analysis KW - AI training ER - TY - CPAPER TI - Modern online teaching formats for geodetic reconstruction methods in Ukraine AU - Horkovchuk, Iuliia AU - Gorkovchuk, Denys AU - Trehub, Mykola AU - Chizhova, Maria AU - Popovas, Darius AU - Sieberth, Till AU - Luhmann, Thomas PY - 2026 VL - XLIX-B5-2026 SP - 89-95 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9034 DO - 10.5194/isprs-archives-xlix-b5-2026-89-2026 UR - https://fis.uni-bamberg.de/handle/uniba/116690 LA - eng ER - TY - CPAPER TI - Integrating timber stability analysis for building life cycle management and HBIM framework support AU - Chizhova, Maria AU - Pan, Junquan AU - Kempter, Gerold AU - Luhmann, Thomas AU - Eißing, Thomas AU - Hess, Mona PY - 2026 VL - XLIX-B1-2026 SP - 559-564 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9034 DO - 10.5194/isprs-archives-xlix-b1-2026-559-2026 UR - https://fis.uni-bamberg.de/handle/uniba/116691 LA - eng AB - The digital documentation of heritage architecture, particularly historic wooden roof structures, has gained significant importance in recent years. Heritage Building Information Modelling (HBIM) has emerged as a crucial field that focuses on the digital representation and management of historic buildings. However, modelling heritage structures in accordance with BIM standards poses challenges due to the complex geometries and specialized information inherent with heritage timber structure. This article presents a workflow that illustrates the integration of an automated, AI-supported analysis of wood knottiness to assess unknown strength values of aged heritage timbers within building life cycle management and supporting the BIM framework. For this purpose, an algorithm for automatic wood knottiness estimation has been developed and implemented as a smartphone-based app-prototype, which facilitates efficient data collection, automatic analysis, and seamless integration into the BIM modelling process, while minimizing potential data loss during exchange. KW - Timber stability assessment KW - Smartphone app KW - openBIM KW - HBIM KW - Data transfer ER - TY - CPAPER TI - Simulation of Stationary and Mobile Laserscanning with VRscan3D AU - Gorkovchuk, Denys AU - Horkovchuk, Julia AU - Chizhova, Maria AU - Popovas, Darius AU - Luhmann, Thomas PY - 2026 VL - XLIX-B2-2026 SP - 181-188 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9034 DO - 10.5194/isprs-archives-xlix-b2-2026-181-2026 UR - https://fis.uni-bamberg.de/handle/uniba/116692 LA - eng AB - Terrestrial and mobile laser scanning technologies have become essential tools in geoinformation, surveying, cultural heritage documentation, and construction. However, access to modern laser scanning equipment remains limited for many universities and training institutions due to high costs, logistical constraints, or disruptions caused by crises such as pandemics or military conflicts. The VRscan3D project addresses this challenge by developing a realistic virtual simulator for stationary and mobile laser scanning that supports education, training, and research. VRscan3D is based on a game-engine environment that enables immersive interaction with virtual scanning devices and realistic 3D scenes. The simulator reproduces the physical parameters of real terrestrial laser scanners. Users can define scan stations, configure scanning parameters, and generate synthetic point clouds that incorporate realistic noise, intensity behavior, and beam characteristics. The platform also supports simulation of mobile scanning systems, including handheld scanners, mobile platforms, and UAV-based systems, allowing users to explore error propagation, scanning trajectories, and operator influence on data quality. In addition to training purposes, VRscan3D enables the generation of synthetic point clouds with known ground truth for testing point cloud processing algorithms and training AI models. Ongoing research focuses on comparing simulated and real datasets to evaluate the accuracy and reliability of synthetic scanning data under dynamic conditions. KW - terrestrial laser scanning KW - simulation KW - point cloud analysis KW - AI training ER - TY - CPAPER TI - Multi-stage mask-aware Depth Enhancement for RGB–IR–stereo Fusion on historic Timber Surfaces AU - Pan, Junquan AU - Chizhova, Maria AU - Hess, Mona AU - Luhmann, Thomas AU - Maiwald, Ferdinand PY - 2026 SP - 217-226 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/116374 LA - eng AB - This paper presents a mask-aware multi-stage depth enhancement framework for digital documentation of historical timber surfaces using RGB–Stereo-IR fusion. Accurate geometric recording of aged wood features such as wooden knots remains challenging due to uneven illumination and weak texture. The proposed pipeline, which aims to stabilise depth geometry under uneven illumination and low-texture surface conditions, integrates object detection, instance segmentation and confidence-guided depth refinement across three stages: (A) TV(total variation)-regularized mask-aware refinement, (B) confidence-weighted multi-view fusion, and (C) patch-based stereo reconstruction. Experiments on historical timber beams under varying illumination demonstrate improved depth completeness and geometric consistency, achieving a residual standard deviation below 0.6 mm in bright scenes and stable reconstruction in low-light conditions. The framework offers a practical solution for depth reconstruction of cultural heritage timber, supporting more reliable feature detection and analysis. KW - Object detection KW - Instance segmentation KW - Mask-aware depth enhancement KW - RGB-IR–Stereo fusion KW - Heritage timber KW - Damage assessment ER - TY - CPAPER TI - Multi-stage mask-aware Depth Enhancement for RGB–IR–stereo Fusion on historic Timber Surfaces AU - Pan, Junquan AU - Chizhova, Maria AU - Hess, Mona AU - Luhmann, Thomas AU - Maiwald, Ferdinand PY - 2026 VL - XI-1-2026 SP - 217-226 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9050 DO - 10.5194/isprs-annals-xi-1-2026-217-2026 UR - https://fis.uni-bamberg.de/handle/uniba/116223 LA - eng AB - This paper presents a mask-aware multi-stage depth enhancement framework for digital documentation of historical timber surfaces using RGB–Stereo-IR fusion. Accurate geometric recording of aged wood features such as wooden knots remains challenging due to uneven illumination and weak texture. The proposed pipeline, which aims to stabilise depth geometry under uneven illumination and low-texture surface conditions, integrates object detection, instance segmentation and confidence-guided depth refinement across three stages: (A) TV(total variation)-regularized mask-aware refinement, (B) confidence-weighted multi-view fusion, and (C) patch-based stereo reconstruction. Experiments on historical timber beams under varying illumination demonstrate improved depth completeness and geometric consistency, achieving a residual standard deviation below 0.6 mm in bright scenes and stable reconstruction in low-light conditions. The framework offers a practical solution for depth reconstruction of cultural heritage timber, supporting more reliable feature detection and analysis. KW - Object detection KW - Instance segmentation KW - Mask-aware depth enhancement KW - RGB-IR–Stereo fusion KW - Heritage timber KW - Damage assessment ER - TY - CHAP TI - A General Approach for the Reconstruction of Complex Buildings from 3D Point Clouds Using Bayesian Networks and Cellular Automata AU - Chizhova, Maria AU - Korovin, Dmitrii AU - Gurianov, Andrey AU - Brunn, Ansgar AU - Luhmann, Thomas AU - Stilla, Uwe PY - 2026 SP - 74-92 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/114468 LA - eng AB - Point cloud interpretation and reconstruction of 3D buildings from point clouds has already been addressed for a few decades. There are many articles which consider different methods and workflows of the automatic detection and reconstruction of geometrical objects from point clouds. Each method is suitable for a specific geometry type of object or sensor. General approaches are rare. In our work, we present an algorithm which develops the optimal process sequence of the automatic search, detection and reconstruction of buildings and building components from a point cloud. It can be used for the detection of sets of geometric objects to be reconstructed, regardless of the level of damage. In a real example, we reconstruct a complete Russian Orthodox church starting from a set of detected structural components and reconstruct missing components with high probability. KW - reconstruction KW - cellular automata KW - Bayesian networks ER - TY - JOUR TI - Matschoss 2.0 : Virtual machine collections as the missing link between museums and historic monuments AU - Érsek, Erika AU - Chizhova, Maria AU - Hascher, Michael AU - Kopanitsak, Clarissa PY - 2026 SP - 221-231 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/114229 LA - eng AB - Digital technologies allow to connect more closely collections of machines in museums and universities to machines in historic monuments. The article discusses why digital collections should be established (1), how the digital models should be produced (2) and how the virtual models could be used by historians of technology as well as trainers of machine builders (3). KW - history of technology KW - machine KW - digital collection KW - computing humanities KW - data management and retrieval KW - scanning technology ER - TY - JOUR TI - Semantic segmentation of building elements using point cloud hashing AU - Chizhova, Maria AU - Gurianov, A. AU - Hess, Mona AU - Luhmann, Thomas AU - Brunn, Ansgar AU - Stilla, U. PY - 2026 SP - 241-250 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/114248 LA - eng AB - For the interpretation of point clouds, the semantic definition of extracted segments from point clouds or images is a common problem. Usually, the semantic of geometrical pre-segmented point cloud elements are determined using probabilistic networks and scene databases. The proposed semantic segmentation method is based on the psychological human interpretation of geometric objects, especially on fundamental rules of primary comprehension. Starting from these rules the buildings could be quite well and simply classified by a human operator (e.g. architect) into different building types and structural elements (dome, nave, transept etc.), including particular building parts which are visually detected. The key part of the procedure is a novel method based on hashing where point cloud projections are transformed into binary pixel representations. A segmentation approach released on the example of classical Orthodox churches is suitable for other buildings and objects characterized through a particular typology in its construction (e.g. industrial objects in standardized enviroments with strict component design allowing clear semantic modelling). KW - semantic segmentation KW - hashing KW - Orthodox church KW - point clouds ER - TY - CPAPER TI - Reflectance Transformation Imaging for Detecting Knots in Heritage Timbers AU - Richter, Jan-Niklas AU - Kahmen, Oliver AU - Rofallski, Robin AU - Luhmann, Thomas AU - Chizhova, Maria AU - Albers, Simon PY - 2026 VL - XLVIII-M-9-2025 SP - 1289-1294 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/113186 LA - eng AB - Reflectance Transformation Imaging (RTI) is a common technique used in different cultural heritage applications. Images of an object or a part of an object are captured using a fixed camera position but changing lighting directions. With this technique small details can be captured, revealed by their shadows, even if the camera resolution would not resolve them. In this contribution we used RTI to support the detection of wooden knots in heritage timbers. We developed a handheld low-cost RTI dome that fits to create RTI models of wooden beams. To locate the knots in the context of their surroundings, 3D models were created via Structure from Motion (SfM) based on the RTI images. We used three different subsamples of the RTI images to optimize our workflow and analyse the possibilities of using different illumination setups. The models then were compared with a model that was created using common camera equipment. The models were compared based on geometry and colour. Our two case studies are addressed to a historic roof framework in a church in Bamberg (Germany) and, in addition, to more accessible newer wooden beams. KW - Reflectance Transformation Imaging KW - Wood Knot Detection KW - Monitoring KW - Optical Imaging KW - Timber Stability ER - TY - JOUR TI - Photogrammetric Localisation of Electromagnetic Sensors for Detecting Anomalies in Heritage Internal Wood Structures AU - Chizhova, Maria AU - Markiewicz, Jakub AU - Kot, Patryk AU - Eißing, Thomas PY - 2026 SP - 277-284 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/113172 LA - eng AB - The strength estimation of built-in historical timber requires extensive investigation of internal wooden structures and properties, which cannot be mapped using only optical surveying methods. In most cases, additional equipment is required, including invasive techniques such as drilling resistance technology and sensitive methods such as ultrasonics or electromagnetic (EM) sensor technology. Thus, the localisation of a measuring device within a whole timber structure and the uniform registration of internal and external wooden structures is missing. In this article, we investigate the capability to localise the EM sensor, which will be used in future research activities for in-depth analysis of internal timber structures. The position of the EM sensor will be captured during the 3D timber imaging using different optical methods to provide a reference between the external wood surface and digitised internal structures. The data quality is compared and evaluated according to the measurement method using geometric features and visual expertise. KW - Data Fusion KW - Electromagnetic Sensor KW - Monitoring KW - Optical Imaging KW - Timber Stability ER - TY - CPAPER TI - An End-to-End AI Pipeline for Wood Knot Detection to Enhance Structural Assessment in Historic Timber Structures AU - Pan, Junquan AU - Chizhova, Maria AU - Ebener, Frank AU - Luhmann, Thomas AU - Ledig, Christian AU - Maiwald, Ferdinand AU - Eißing, Thomas PY - 2026 SP - 267-274 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/113148 LA - eng AB - The accurate detection and assessment of wood surface defects in historic timber structures, particularly knots, is essential for effective conservation and strengthening planning. However, the application of automated visual grading methods to aged timber remains underexplored due to the irregular texture, weathering and lack of relevant datasets. In this study, we propose an end-to-end deep learning-based pipeline that integrates wood surface segmentation, perspective correction, and knot detection to estimate structural grading factors. A dedicated raw data collection of over 10,000 high-resolution images of historic timber surfaces was compiled using both DSLR cameras and mobile devices, resulting in multiple datasets with approximately 3,000 annotated samples. Three model families, YOLO, Detectron2 and DeepLabV3, were evaluated under different experimental setups. Beyond model benchmarking, we further compared the AI-derived results with expert manual measurements. The model for segmentation of timber surface achieved a mean IoU of over 0.85 and the model for detection of historical wood knots reached F1 scores of up to 0.9. The structural assessment factors estimated by the AI pipeline achieved a Pearson correlation coefficient of 0.641 compared to manual measurements, indicating a moderate level of consistency in knot factor estimation. This research highlights the potential of vision-based AI systems in supporting structural diagnosis and conservation of heritage timber elements. KW - Photogrammetry KW - Deep Learning KW - Historic Timber Structures KW - Wood Knot Detection KW - Structural Assessment ER - TY - CPAPER TI - Reflectance Transformation Imaging for Detecting Knots in Heritage Timbers AU - Richter, Jan-Niklas AU - Kahmen, Oliver AU - Rofallski, Robin AU - Luhmann, Thomas AU - Chizhova, Maria AU - Albers, Simon PY - 2025 VL - XLVIII-M-9-2025 SP - 1289-1294 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9034 DO - 10.5194/isprs-archives-xlviii-m-9-2025-1289-2025 UR - https://fis.uni-bamberg.de/handle/uniba/110641 LA - eng AB - Reflectance Transformation Imaging (RTI) is a common technique used in different cultural heritage applications. Images of an object or a part of an object are captured using a fixed camera position but changing lighting directions. With this technique small details can be captured, revealed by their shadows, even if the camera resolution would not resolve them. In this contribution we used RTI to support the detection of wooden knots in heritage timbers. We developed a handheld low-cost RTI dome that fits to create RTI models of wooden beams. To locate the knots in the context of their surroundings, 3D models were created via Structure from Motion (SfM) based on the RTI images. We used three different subsamples of the RTI images to optimize our workflow and analyse the possibilities of using different illumination setups. The models then were compared with a model that was created using common camera equipment. The models were compared based on geometry and colour. Our two case studies are addressed to a historic roof framework in a church in Bamberg (Germany) and, in addition, to more accessible newer wooden beams. KW - Reflectance Transformation Imaging KW - Wood Knot Detection KW - Monitoring KW - Optical Imaging KW - Timber Stability ER - TY - JOUR TI - Photogrammetric Localisation of Electromagnetic Sensors for Detecting Anomalies in Heritage Internal Wood Structures AU - Chizhova, Maria AU - Markiewicz, Jakub AU - Kot, Patryk AU - Eißing, Thomas PY - 2025 JO - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences VL - XLVIII-M-9-2025 SP - 277-284 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9034 DO - 10.5194/isprs-archives-xlviii-m-9-2025-277-2025 UR - https://fis.uni-bamberg.de/handle/uniba/110642 LA - eng AB - The strength estimation of built-in historical timber requires extensive investigation of internal wooden structures and properties, which cannot be mapped using only optical surveying methods. In most cases, additional equipment is required, including invasive techniques such as drilling resistance technology and sensitive methods such as ultrasonics or electromagnetic (EM) sensor technology. Thus, the localisation of a measuring device within a whole timber structure and the uniform registration of internal and external wooden structures is missing. In this article, we investigate the capability to localise the EM sensor, which will be used in future research activities for in-depth analysis of internal timber structures. The position of the EM sensor will be captured during the 3D timber imaging using different optical methods to provide a reference between the external wood surface and digitised internal structures. The data quality is compared and evaluated according to the measurement method using geometric features and visual expertise. KW - Data Fusion KW - Electromagnetic Sensor KW - Monitoring KW - Optical Imaging KW - Timber Stability ER - TY - CPAPER TI - An End-to-End AI Pipeline for Wood Knot Detection to Enhance Structural Assessment in Historic Timber Structures AU - Pan, Junquan AU - Chizhova, Maria AU - Ebener, Frank AU - Luhmann, Thomas AU - Ledig, Christian AU - Maiwald, Ferdinand AU - Eißing, Thomas PY - 2025 VL - X-M-2-2025 SP - 267-274 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9050 DO - 10.5194/isprs-annals-x-m-2-2025-267-2025 UR - https://fis.uni-bamberg.de/handle/uniba/110553 LA - eng AB - The accurate detection and assessment of wood surface defects in historic timber structures, particularly knots, is essential for effective conservation and strengthening planning. However, the application of automated visual grading methods to aged timber remains underexplored due to the irregular texture, weathering and lack of relevant datasets. In this study, we propose an end-to-end deep learning-based pipeline that integrates wood surface segmentation, perspective correction, and knot detection to estimate structural grading factors. A dedicated raw data collection of over 10,000 high-resolution images of historic timber surfaces was compiled using both DSLR cameras and mobile devices, resulting in multiple datasets with approximately 3,000 annotated samples. Three model families, YOLO, Detectron2 and DeepLabV3, were evaluated under different experimental setups. Beyond model benchmarking, we further compared the AI-derived results with expert manual measurements. The model for segmentation of timber surface achieved a mean IoU of over 0.85 and the model for detection of historical wood knots reached F1 scores of up to 0.9. The structural assessment factors estimated by the AI pipeline achieved a Pearson correlation coefficient of 0.641 compared to manual measurements, indicating a moderate level of consistency in knot factor estimation. This research highlights the potential of vision-based AI systems in supporting structural diagnosis and conservation of heritage timber elements. KW - Photogrammetry KW - Deep Learning KW - Historic Timber Structures KW - Wood Knot Detection KW - Structural Assessment ER - TY - JOUR TI - Simulation von mobilem und dynamischem Scanning im virtuellen Simulator VRscan3D AU - Chizhova, Maria AU - Gorkovchuk, Denys AU - Luhmann, Thomas AU - Popovas, Darius PY - 2025 JO - Allgemeine Vermessungs-Nachrichten : AVN ; Zeitschrift für alle Bereiche der Geodäsie und Geoinformation VL - 132 IS - 1-2 SP - 51-58 PB - Wichmann, VDE Verl. CY - Berlin SN - 0002-5968 DO - 10.14627/avn.2025.1-2.5 UR - https://fis.uni-bamberg.de/handle/uniba/108800 LA - deu ER - TY - CHAP TI - Automatisierte Ästigkeitsschätzung zur Verbesserung der Qualitätsbewertung von historischem Holz AU - Pan, Junquan AU - Chizhova, Maria AU - Luhmann, Thomas AU - Eißing, Thomas AU - Hess, Mona PY - 2024 T2 - KI und Denkmalpflege. Potenziale nutzen, Risiken erkennen SP - 47-55 CY - Berlin SN - 978-3-00-081388-7 UR - https://fis.uni-bamberg.de/handle/uniba/108798 LA - deu ER - TY - JOUR TI - Matschoss 2.0 : Virtual machine collections as the missing link between museums and historic monuments AU - Érsek, Erika AU - Chizhova, Maria AU - Hascher, Michael AU - Kopanitsak, Clarissa PY - 2024 JO - Information technology : it VL - 66 IS - 6 SP - 221-231 PB - De Gruyter CY - Berlin SN - 1611-2776 DO - 10.1515/itit-2023-0113 UR - https://fis.uni-bamberg.de/handle/uniba/108799 LA - eng AB - Digital technologies allow to connect more closely collections of machines in museums and universities to machines in historic monuments. The article discusses why digital collections should be established (1), how the digital models should be produced (2) and how the virtual models could be used by historians of technology as well as trainers of machine builders (3). KW - history of technology KW - machine KW - digital collection KW - computing humanities KW - data management and retrieval KW - scanning technology ER - TY - CHAP TI - Simulation von mobilem und dynamischem Scanning im virtuellen Simulator VRscan3D AU - Luhmann, Thomas AU - Chizhova, Maria AU - Popovas, Darius AU - Gorkovchuk, Denys PY - 2024 T2 - Photogrammetrie - Laserscanning - Optische 3D-Messtechnik : Beiträge der Oldenburger 3D-Tage und des BIMtages 2024 SP - 304-313 PB - Wichmann CY - Berlin ; Offenbach SN - 978-3-87907-750-2 UR - https://fis.uni-bamberg.de/handle/uniba/108801 LA - deu ER - TY - CPAPER TI - Machbarkeitsstudie zur automatisierten Zustandsanalyse verbauter historischer Holzbalken AU - Pan, Junquan AU - Chizhova, Maria AU - Luhmann, Thomas AU - Eißing, Thomas PY - 2024 SP - 1-16 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/96611 LA - deu AB - In diesem Beitrag stellen wir eine Machbarkeitsstudie für die Dokumentation von Holzoberflächen mit verschiedenen Bildgebungsverfahren und erste Ergebnisse der Erkennung von Astknoten (Ästigkeit) aus Texturbildern vor. Die Machbarkeitsstudie liefert eine wissenschaftliche Grundlage für die Entwicklung eines Verfahrens zur automatischen Stabilitätsanalyse von verbautem historischem Holz anhand von erkannten Oberflächenmerkmalen. KW - Ästigkeitserkennung KW - Altholzbalken KW - YOLO KW - KI ER - TY - CPAPER TI - Machbarkeitsstudie zur automatisierten Zustandsanalyse verbauter historischer Holzbalken AU - Pan, Junquan AU - Chizhova, Maria AU - Luhmann, Thomas AU - Eißing, Thomas PY - 2024 T2 - 44. Wissenschaftlich-Technische Jahrestagung der DGPF 2024 – Publikationen der DGPF VL - 2024 IS - 32 SP - 1-16 PB - DGPF CY - Potsdam T3 - Publikationen der Deutschen Gesellschaft für Photogrammetrie, Fernerkundung und Geoinformation e.V. DO - 10.24407/KXP:1885713169 UR - https://fis.uni-bamberg.de/handle/uniba/97283 LA - deu AB - In diesem Beitrag stellen wir eine Machbarkeitsstudie für die Dokumentation von Holzoberflächen mit verschiedenen Bildgebungsverfahren und erste Ergebnisse der Erkennung von Astknoten (Ästigkeit) aus Texturbildern vor. Die Machbarkeitsstudie liefert eine wissenschaftliche Grundlage für die Entwicklung eines Verfahrens zur automatischen Stabilitätsanalyse von verbautem historischem Holz anhand von erkannten Oberflächenmerkmalen. KW - Ästigkeitserkennung KW - Altholzbalken KW - YOLO KW - KI ER - TY - CPAPER TI - Towards automatic defects analyses for 3D structural monitoring of historic timber AU - Chizhova, Maria AU - Pan, Junquan AU - Luhmann, Thomas AU - Karami, A. AU - Menna, Fabio AU - Remondino, Fabio AU - Hess, Mona AU - Eißing, Thomas PY - 2024 SP - 103-110 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/95675 LA - eng AB - Stability of historic wooden constructions is changing with time and should be inspected appropriately for risk assessment and prevention. The stability or strength values of built-in historic timber are difficult or even impossible to be derived without invasive investigation, but this is particularly problematic for the monitoring of heritage objects. Luckily there are some visible timber surface features, like knots and cracks, which can act as individual evidence to estimate the wood strength as well as to adjust its grade class indicator. In the final project, we aim to compare different approaches for 3D digital documentation of historic wood timbers and focus on automatic knot detection using AI techniques. A first feasibility study reported here provides a scientific baseline for the development of an automated method to analyse historic timber stability using 3D surveying and recognised surface features. First results about texture and resolution properties are discussed here. KW - historic wooden timber KW - feature extraction KW - machine learning KW - 3D scanning KW - structure from motion KW - multi view photometric stereo KW - reflectance transformation imaging ER - TY - CPAPER TI - Towards automatic defects analyses for 3D structural monitoring of historic timber AU - Chizhova, Maria AU - Pan, Junquan AU - Luhmann, Thomas AU - Karami, A. AU - Menna, Fabio AU - Remondino, Fabio AU - Hess, Mona AU - Eißing, Thomas PY - 2024 VL - XLVIII-2/W4-2024 SP - 103-110 PB - Copernicus GmbH CY - Katlenburg-Lindau SN - 2194-9034 DO - 10.5194/isprs-archives-xlviii-2-w4-2024-103-2024 UR - https://fis.uni-bamberg.de/handle/uniba/93607 LA - eng AB - Stability of historic wooden constructions is changing with time and should be inspected appropriately for risk assessment and prevention. The stability or strength values of built-in historic timber are difficult or even impossible to be derived without invasive investigation, but this is particularly problematic for the monitoring of heritage objects. Luckily there are some visible timber surface features, like knots and cracks, which can act as individual evidence to estimate the wood strength as well as to adjust its grade class indicator. In the final project, we aim to compare different approaches for 3D digital documentation of historic wood timbers and focus on automatic knot detection using AI techniques. A first feasibility study reported here provides a scientific baseline for the development of an automated method to analyse historic timber stability using 3D surveying and recognised surface features. First results about texture and resolution properties are discussed here. KW - historic wooden timber KW - feature extraction KW - machine learning KW - 3D scanning KW - structure from motion KW - multi view photometric stereo KW - reflectance transformation imaging ER - TY - CPAPER TI - Development of terrestrial laser scanning simulator AU - Luhmann, Thomas AU - Chizhova, Maria AU - Gorkovchuk, Denys AU - Popovas, Darius AU - Gorkovchuk, Julia AU - Hess, Mona PY - 2024 SP - 329-334 PB - Otto-Friedrich-Universität CY - Bamberg SN - 2194-9034 UR - https://fis.uni-bamberg.de/handle/uniba/92749 LA - eng AB - Within the project VRscan3D, funded by DAAD, a terrestrial laser scanner simulator has been developed as educational tool for learning and teaching laser scanning processes. The main goal of the VirScan3D project is to cover engineering digitisation and will be solved through the development of a virtual system that allows users to create realistic data in the absence of a real measuring device in a modelled real-life environment (digital twin). The implementation of the virtual laser scanner is realised within a game engine, which allows for fast and easy 3D visualisation and navigation. Real-life buildings and urban surroundings can be digitised, modelled and integrated into the simulator, thus creating a digital copy of a real-world environment. This article describes the technical realization of the simulator and its evaluation as well as usability testing results conducted by independent users from university courses. KW - simulator KW - laser scanning KW - point cloud KW - virtual reality KW - game engine ER - TY - CPAPER TI - Development of terrestrial laser scanning simulator AU - Luhmann, Thomas AU - Chizhova, Maria AU - Gorkovchuk, Denys AU - Popovas, Darius AU - Gorkovchuk, Julia AU - Hess, Mona PY - 2022 VL - XLVI-2/W1-2022 SP - 329-334 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9034 DO - 10.5194/isprs-archives-xlvi-2-w1-2022-329-2022 UR - https://fis.uni-bamberg.de/handle/uniba/92748 LA - eng AB - Within the project VRscan3D, funded by DAAD, a terrestrial laser scanner simulator has been developed as educational tool for learning and teaching laser scanning processes. The main goal of the VirScan3D project is to cover engineering digitisation and will be solved through the development of a virtual system that allows users to create realistic data in the absence of a real measuring device in a modelled real-life environment (digital twin). The implementation of the virtual laser scanner is realised within a game engine, which allows for fast and easy 3D visualisation and navigation. Real-life buildings and urban surroundings can be digitised, modelled and integrated into the simulator, thus creating a digital copy of a real-world environment. This article describes the technical realization of the simulator and its evaluation as well as usability testing results conducted by independent users from university courses. KW - simulator KW - laser scanning KW - point cloud KW - virtual reality KW - game engine ER - TY - CHAP TI - VirScan3D : Virtueller Laserscanner-Simulator zur Digitalisierung der Unterrichtsumgebung AU - Chizhova, Maria PY - 2022 T2 - Kompetenzzentrum Denkmalwissenschaften und Denkmaltechnologien 2018 – 2020 SP - 82-85 PB - University of Bamberg Press CY - Bamberg SN - 978-3-86309-864-3 DO - 10.20378/irb-56702 UR - https://fis.uni-bamberg.de/handle/uniba/56702 LA - deu AB - - KW - - ER - TY - CHAP TI - Georgische Kirchen : 3D Datenfusion von Laserscanning und Photogrammetrie AU - Chizhova, Maria PY - 2022 T2 - Kompetenzzentrum Denkmalwissenschaften und Denkmaltechnologien 2018 – 2020 SP - 78-81 PB - University of Bamberg Press CY - Bamberg SN - 978-3-86309-864-3 DO - 10.20378/irb-56701 UR - https://fis.uni-bamberg.de/handle/uniba/56701 LA - deu AB - - KW - - ER - TY - CHAP TI - Digitale Erfassung jüdischer Friedhöfe in Franken AU - Chizhova, Maria PY - 2022 T2 - Kompetenzzentrum Denkmalwissenschaften und Denkmaltechnologien 2018 – 2020 SP - 74-77 PB - University of Bamberg Press CY - Bamberg SN - 978-3-86309-864-3 DO - 10.20378/irb-56700 UR - https://fis.uni-bamberg.de/handle/uniba/56700 LA - deu AB - - KW - - ER - TY - CHAP TI - Orthodoxe Kirchen : Virtuelle 3D Rekonstruktion aus unvollständigen Punktwolken AU - Chizhova, Maria PY - 2022 T2 - Kompetenzzentrum Denkmalwissenschaften und Denkmaltechnologien 2018 – 2020 SP - 70-73 PB - University of Bamberg Press CY - Bamberg SN - 978-3-86309-864-3 DO - 10.20378/irb-56699 UR - https://fis.uni-bamberg.de/handle/uniba/56699 LA - deu AB - - KW - - ER - TY - BOOK TI - Kompetenzzentrum Denkmalwissenschaften und Denkmaltechnologien 2018 – 2020 AU - Albrecht, Stephan AU - Arera-Rütenik, Tobias AU - Basse, Eva AU - Bellendorf, Paul AU - Bischoff, Bernhard AU - Breitling, Stefan AU - Burioni, Matteo AU - Chizhova, Maria AU - Deglmann, Laura AU - Drewello, Rainer AU - Drewello, Ursula AU - Ebner, Isabell AU - Eckstein, Claudia AU - Eißing, Thomas AU - Enss, Carmen M. AU - Giese, Jürgen AU - Herold, Stephanie AU - Hess, Mona AU - Hönig, Svenja AU - Knauer, Birgit AU - Korn, Lorenz AU - Luib, Anna AU - Pristl, Martina AU - Lutteroth, Jan-Eric AU - Nöbauer, Franziska AU - Rahrig, Max AU - Salzer, Leonhard AU - Schalk, Christian AU - Schalk, Patrick AU - Schmölder, Alexandra AU - Schulz, Regine AU - Sedlmeyer, Georg-Felix AU - Selitz, Lisa Marie AU - Sonnemann, Till AU - Stackmann, Sophie AU - Stenzer, Alexander AU - Tenschert, Ruth AU - Ullmann, Martina AU - Vasilchenko, Iustyna AU - Vinken, Gerhard AU - Möllendorff, Nathalie-Josephine von AU - Wenderoth, Thomas ED - Arera-Rütenik, Tobias ED - Bellendorf, Paul ED - Breitling, Stefan ED - Drewello, Rainer ED - Hess, Mona ED - Vinken, Gerhard PY - 2022 PB - University of Bamberg Press CY - Bamberg T3 - Kompetenzzentrum Denkmalwissenschaften und Denkmaltechnologien (KDWT): Berichte des KDWT SN - 978-3-86309-864-3 DO - 10.20378/irb-54270 UR - https://fis.uni-bamberg.de/handle/uniba/54270 LA - deu AB - Das Kompetenzzentrum Denkmalwissenschaften und Denkmaltechnologien (KDWT) wurde als zentrale Forschungseinrichtung der Otto-Friedrich-Universität Bamberg im Frühjahr 2016 gegründet. In der interdisziplinären Ausrichtung zwischen Geistes-, Ingenieur- und Materialwissenschaften unter ausgeprägtem Praxisbezug in Forschung und Lehre haben sich die Mitglieder die fachübergreifende, regionale, nationale und internationale Vernetzung der Forschung zu Zukunftsthemen der Denkmalwissenschaften und Denkmaltechnologien zum Ziel gesetzt. Neben dem Ausbau des Wissens- und Technologietransfers zu universitären und außeruniversitären Forschungseinrichtungen, zu Hochschulen, zur Wirtschaft und zum Handwerk unterstützt das Kompetenzzentrum Denkmalwissenschaften und Denkmaltechnologien universitäre Lehre inhaltlich und technisch apparativ. KW - Kompetenzzentrum Denkmalwissenschaften und Denkmaltechnologien KW - Denkmalpflege KW - Bauforschung KW - Digitale Denkmaltechnologien KW - Restaurierungswissenschaft KW - Bericht ER - TY - JOUR TI - Combination of terrestrial laserscanning, UAV and close range photogrammertry for 3D reconstruction of complex churches in Georgia AU - Luhmann, T. AU - Chizhova, Maria AU - Gorkovchuk, D. AU - Hastedt, H. AU - Chachava, N. AU - Lekveishvili, N. PY - 2022 SP - 753-761 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/53783 LA - eng AB - In September 2018, photogrammetric images and terrestrial laser scans were carried out as part of a measurement campaign for the three-dimensional recording of several historic churches in Tbilisi (Georgia). The aim was the complete spatial reconstruction with a spatial resolution and accuracy of approx. 1cm under partly difficult external conditions, which required the use of different measurement techniques. The local measurement data were collected by two laser scanning campaigns (Leica BLK360 and Faro Focus 3D X330), two UAV flights and two terrestrial image sets. The photogrammetric point clouds were calculated with the SfM programs AgiSoft PhotoScan and RealityCapture taking into account the control points from the Faro laser scan. The mean residual errors from the registrations or photogrammetric evaluations are 4-12mm, depending on the selected software. The best completeness and quality of the resulting 3D model was achieved by using laserscan data and images simultaneously. KW - laserscanning, KW - photogrammetry KW - data fusion KW - 3D reconstruction KW - cultural heritage ER - TY - CPAPER TI - Virtual terrestrial laser scanner simulator in digital twin environment AU - Popovas, Darius AU - Chizhova, Maria AU - Gorkovchuk, Denys AU - Gorkovchuk, Julia AU - Hess, Mona AU - Luhmann, Thomas PY - 2021 SP - 85-92 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-49882 UR - https://fis.uni-bamberg.de/handle/uniba/49882 LA - eng AB - We are presenting a Terrestrial Laser Scanner simulator - a software device which could be a valuable educational tool for geomatics and engineering students. The main goal of the VirScan3D project is to cover engineering digitisation and will be solved through the development of a virtual system that allows users to create realistic data in the absence of a real measuring device in a modelled real life environment (digital twin). The prototype implementation of the virtual laser scanner is realised within a game engine, which allows for fast and easy 3D visualisation and navigation. Real life objects can be digitised, modelled and integrated into the simulator, thus creating a digital copy of a real world environment. Within this environment, the user can freely navigate and define suitable scanning positions or stations. At each scanning station a simulated scan is performed adapted to the technical specifications of a real scanner. The mathematical solution is based on 3D line intersection with the virtual 3D surface including noise and colour as well as an intensity simulation. As a result, 3D point clouds for each station are generated, which will be further processed for registration and modelling using standard software packages. KW - simulator KW - laser scanning KW - point cloud KW - virtual scanner KW - digital twin KW - game engine KW - e-learning ER - TY - CPAPER TI - Virtual terrestrial laser scanner simulator in digital twin environment AU - Popovas, Darius AU - Chizhova, Maria AU - Gorkovchuk, Denys AU - Gorkovchuk, Julia AU - Hess, Mona AU - Luhmann, Thomas PY - 2021 T2 - Proceedings of the joint international event 9th ARQUEOLÓGICA 2.0 & 3rd GEORES (‘GEOmatics and pREServation), Valencia (Spain). 26–28 April 2021 SP - 85-92 PB - Universitat Polytecnica de Valencia CY - Valencia, Spain DO - 10.4995/Arqueologica9.2021.12091 UR - https://fis.uni-bamberg.de/handle/uniba/49964 LA - eng AB - We are presenting a Terrestrial Laser Scanner simulator - a software device which could be a valuable educational tool for geomatics and engineering students. The main goal of the VirScan3D project is to cover engineering digitisation and will be solved through the development of a virtual system that allows users to create realistic data in the absence of a real measuring device in a modelled real life environment (digital twin). The prototype implementation of the virtual laser scanner is realised within a game engine, which allows for fast and easy 3D visualisation and navigation. Real life objects can be digitised, modelled and integrated into the simulator, thus creating a digital copy of a real world environment. Within this environment, the user can freely navigate and define suitable scanning positions or stations. At each scanning station a simulated scan is performed adapted to the technical specifications of a real scanner. The mathematical solution is based on 3D line intersection with the virtual 3D surface including noise and colour as well as an intensity simulation. As a result, 3D point clouds for each station are generated, which will be further processed for registration and modelling using standard software packages. KW - simulator KW - laser scanning KW - point cloud KW - virtual scanner KW - digital twin KW - game engine KW - e-learning ER - TY - JOUR TI - Qualitative testing of an advanced terrestrial laser scanner simulator : users experience and feedback AU - Chizhova, Maria AU - Gorkovchuk, Denys AU - Kachkovskaya, Tatayana AU - Popovas, Darius AU - Gorkovchuk, Julia AU - Luhmann, Thomas AU - Hess, Mona PY - 2021 JO - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences VL - XLIII-B5-2021 SP - 29-35 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9034 DO - 10.5194/isprs-archives-XLIII-B5-2021-29-2021 UR - https://fis.uni-bamberg.de/handle/uniba/50219 LA - eng ER - TY - JOUR TI - Fusion of UAV and Terrestrial Photogrammetry with Laser Scanning for 3D Reconstruction of Historic Churches in Georgia AU - Chizhova, Maria AU - Gorkovchuk, Denys AU - Luhmann, Thomas PY - 2020 VL - 4 IS - 3 PB - MDPI CY - Basel SN - 2504-446X DO - 10.3390/drones4030053 UR - https://fis.uni-bamberg.de/handle/uniba/57942 LA - eng AB - In September 2018, photogrammetric images and terrestrial laser scans were carried out as part of a measurement campaign for the three-dimensional recording of several historic churches in Tbilisi (Georgia). The aim was the complete spatial reconstruction with a spatial resolution and accuracy of approx. 1 cm under partly difficult external conditions, which required the use of different measurement techniques. The local measurement data were collected by two laser scanning campaigns (Leica BLK360 and Faro Focus 3D X330), several UAV flights and two terrestrial image sets. The photogrammetric point clouds were calculated with the image-based modelling programs AgiSoft and RealityCapture taking into account the control points from the laser scans. The mean residual errors from the registrations or photogrammetric evaluations are 4–16 mm, depending on the selected software, size and complexity of the monument and environmental conditions. The best completeness and quality of the resulting 3D model was achieved by using laser scan data and images simultaneously. The article presents recent results obtained with RealityCapture and gives a critical analysis of accuracy and modelling quality. KW - UAV photogrammetry KW - camera calibration KW - geo-referencing KW - data fusion KW - cultural heritage KW - image-based modelling ER - TY - JOUR TI - Fusion of UAV and Terrestrial Photogrammetry with Laser Scanning for 3D Reconstruction of Historic Churches in Georgia AU - Luhmann, Thomas AU - Chizhova, Maria AU - Gorkovchuk, Denys PY - 2020 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/49762 LA - eng AB - In September 2018, photogrammetric images and terrestrial laser scans were carried out as part of a measurement campaign for the three-dimensional recording of several historic churches in Tbilisi (Georgia). The aim was the complete spatial reconstruction with a spatial resolution and accuracy of approx. 1 cm under partly difficult external conditions, which required the use of different measurement techniques. The local measurement data were collected by two laser scanning campaigns (Leica BLK360 and Faro Focus 3D X330), several UAV flights and two terrestrial image sets. The photogrammetric point clouds were calculated with the image-based modelling programs AgiSoft and RealityCapture taking into account the control points from the laser scans. The mean residual errors from the registrations or photogrammetric evaluations are 4–16 mm, depending on the selected software, size and complexity of the monument and environmental conditions. The best completeness and quality of the resulting 3D model was achieved by using laser scan data and images simultaneously. The article presents recent results obtained with RealityCapture and gives a critical analysis of accuracy and modelling quality. KW - UAV photogrammetry KW - camera calibration KW - geo-referencing KW - data fusion KW - cultural heritage KW - image-based modelling ER - TY - JOUR TI - Virtual terrestrial laser scanner simulator for digitalisation of teaching environment concept and first results AU - Chizhova, Maria AU - Popovas, Denys AU - Gorkovchuk, Darius AU - Gorkovchuk, Julia AU - Hess, Mona AU - Luhmann, Thomas PY - 2020 JO - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences VL - XLIII IS - B5 SP - 91–97 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9034 DO - 10.5194/isprs-archives-XLIII-B5-2020-91-2020 UR - https://fis.uni-bamberg.de/handle/uniba/49514 LA - eng ER - TY - JOUR TI - Application of multi-criteria decision making for the selection of sensing tools for historical gravestones AU - Pavlovski, Miroslavas AU - Chizhova, Maria AU - Hindmarch, John AU - Hess, Mona PY - 2020 JO - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences VL - XLIII IS - B2 SP - 1435–1442 PB - Copernicus Publications CY - Katlenburg-Lindau DO - 10.5194/isprs-archives-XLIII-B2-2020-1435-2020 UR - https://fis.uni-bamberg.de/handle/uniba/49513 LA - eng ER - TY - THES TI - Virtuelle 3D-Rekonstruktion von zerstörten russisch-orthodoxen Kirchen aus unvollständigen Punktwolken AU - Chizhova, Maria PY - 2019 SP - Abbildungen, Tabellen, Diagramme PB - Technische Universität CY - München UR - https://fis.uni-bamberg.de/handle/uniba/108790 LA - deu ER - TY - JOUR TI - Combination of terrestrial laserscanning, UAV and close range photogrammertry for 3D reconstruction of complex churches in Georgia AU - Luhmann, T. AU - Chizhova, Maria AU - Gorkovchuk, D. AU - Hastedt, H. AU - Chachava, N. AU - Lekveishvili, N. PY - 2019 JO - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences VL - XLII-2/W11 SP - 753-761 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9034 DO - 10.5194/isprs-archives-XLII-2-W11-753-2019 UR - https://fis.uni-bamberg.de/handle/uniba/53341 LA - eng AB - In September 2018, photogrammetric images and terrestrial laser scans were carried out as part of a measurement campaign for the three-dimensional recording of several historic churches in Tbilisi (Georgia). The aim was the complete spatial reconstruction with a spatial resolution and accuracy of approx. 1cm under partly difficult external conditions, which required the use of different measurement techniques. The local measurement data were collected by two laser scanning campaigns (Leica BLK360 and Faro Focus 3D X330), two UAV flights and two terrestrial image sets. The photogrammetric point clouds were calculated with the SfM programs AgiSoft PhotoScan and RealityCapture taking into account the control points from the Faro laser scan. The mean residual errors from the registrations or photogrammetric evaluations are 4-12mm, depending on the selected software. The best completeness and quality of the resulting 3D model was achieved by using laserscan data and images simultaneously. KW - laserscanning, KW - photogrammetry KW - data fusion KW - 3D reconstruction KW - cultural heritage ER - TY - JOUR TI - Semantic segmentation of building elements using point cloud hashing AU - Chizhova, Maria AU - Gurianov, A. AU - Hess, Mona AU - Luhmann, Thomas AU - Brunn, Ansgar AU - Stilla, U. PY - 2018 JO - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences VL - XLII IS - 2 SP - 241-250 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9034 DO - 10.5194/isprs-archives-xlii-2-241-2018 UR - https://fis.uni-bamberg.de/handle/uniba/108789 LA - eng AB - For the interpretation of point clouds, the semantic definition of extracted segments from point clouds or images is a common problem. Usually, the semantic of geometrical pre-segmented point cloud elements are determined using probabilistic networks and scene databases. The proposed semantic segmentation method is based on the psychological human interpretation of geometric objects, especially on fundamental rules of primary comprehension. Starting from these rules the buildings could be quite well and simply classified by a human operator (e.g. architect) into different building types and structural elements (dome, nave, transept etc.), including particular building parts which are visually detected. The key part of the procedure is a novel method based on hashing where point cloud projections are transformed into binary pixel representations. A segmentation approach released on the example of classical Orthodox churches is suitable for other buildings and objects characterized through a particular typology in its construction (e.g. industrial objects in standardized enviroments with strict component design allowing clear semantic modelling). KW - semantic segmentation KW - hashing KW - Orthodox church KW - point clouds ER - TY - CHAP TI - A General Approach for the Reconstruction of Complex Buildings from 3D Point Clouds Using Bayesian Networks and Cellular Automata AU - Chizhova, Maria AU - Korovin, Dmitrii AU - Gurianov, Andrey AU - Brunn, Ansgar AU - Luhmann, Thomas AU - Stilla, Uwe PY - 2018 T2 - Latest Developments in Reality-Based 3D Surveying and Modelling SP - 74-92 PB - MDPI CY - Basel SN - 9783038426851 DO - 10.3390/books978-3-03842-685-1-4 UR - https://fis.uni-bamberg.de/handle/uniba/108791 LA - eng AB - Point cloud interpretation and reconstruction of 3D buildings from point clouds has already been addressed for a few decades. There are many articles which consider different methods and workflows of the automatic detection and reconstruction of geometrical objects from point clouds. Each method is suitable for a specific geometry type of object or sensor. General approaches are rare. In our work, we present an algorithm which develops the optimal process sequence of the automatic search, detection and reconstruction of buildings and building components from a point cloud. It can be used for the detection of sets of geometric objects to be reconstructed, regardless of the level of damage. In a real example, we reconstruct a complete Russian Orthodox church starting from a set of detected structural components and reconstruct missing components with high probability. KW - reconstruction KW - cellular automata KW - Bayesian networks ER - TY - CPAPER TI - Automatically Extraction and Reconstruction of Cupola Geometries of Orthodox Churches from Precision Point Clouds AU - Chizhova, Maria AU - Korovin, Dmitrii AU - Gurianov, Andrey AU - Brodovskii, Maxim AU - Brunn, Ansgar AU - Stilla, Uwe AU - Luhmann, Thomas PY - 2017 VL - 26 SP - 434-443 PB - Geschäftsstelle der DGPF CY - Münster SN - 0942-2870 UR - https://fis.uni-bamberg.de/handle/uniba/108792 LA - eng ER - TY - CPAPER TI - Wavelet-basierte Erkennung architektonischer Formen aus präzisen Punktwolken AU - Chizhova, Maria AU - Gurianov, Andrey AU - Brunn, Ansgar AU - Stilla, Uwe AU - Luhmann, Thomas PY - 2017 T2 - Photogrammetrie, Laserscanning, optische 3D-Messtechnik : Beiträge der Oldenburger 3D-Tage 2017 SP - 129-141 PB - Wichmann CY - Berlin SN - 978-3-87907-625-3 UR - https://fis.uni-bamberg.de/handle/uniba/108793 LA - deu ER - TY - JOUR TI - Probablistic Reconstruction Of Orthodox Churches from Precisionpoint Clouds Using Bayesian Networks And Cellular Automata AU - Chizhova, Maria AU - Korovin, D. AU - Gurianov, A. AU - Brodovskii, M. AU - Brunn, A. AU - Stilla, U. AU - Luhmann, T. PY - 2017 JO - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences VL - XLII IS - 2/W3 SP - 187–194 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9034 DO - 10.5194/isprs-archives-xlii-2-w3-187-2017 UR - https://fis.uni-bamberg.de/handle/uniba/49646 LA - eng ER - TY - CPAPER TI - Recognizing separate structural elements of churches using neural networks AU - Brodovskii, Maxim AU - Korovin, Dmitrii AU - Chizhova, Maria AU - Brunn, Ansgar AU - Stilla, Uwe PY - 2016 SP - 153-164 PB - Geschäftsstelle der DGPF CY - Münster SN - 0942-2870 UR - https://fis.uni-bamberg.de/handle/uniba/108795 LA - eng ER - TY - JOUR TI - PROBABILISTIC FEASIBILITY OF THE RECONSTRUCTION PROCESS OF RUSSIAN-ORTHODOX CHURCHES AU - Chizhova, Maria AU - Brunn, A. AU - Stilla, U. PY - 2016 JO - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences VL - XLI IS - B5 SP - 221--227 PB - Copernicus Publications CY - Katlenburg-Lindau SN - 2194-9034 DO - 10.5194/isprs-archives-xli-b5-221-2016 UR - https://fis.uni-bamberg.de/handle/uniba/49645 LA - eng ER -