@inproceedings{chizhova2026_117402,
  title = {Integrating timber stability analysis for building life cycle management and HBIM framework support},
  author = {Chizhova, Maria and Pan, Junquan and Kempter, Gerold and Luhmann, Thomas and Eißing, Thomas and Hess, Mona},
  year = {2026},
  pages = {559-564},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-117402x},
  url = {https://fis.uni-bamberg.de/handle/uniba/117402},
  language = {eng},
  abstract = {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.},
  keywords = {Timber stability assessment, Smartphone app, openBIM, HBIM, Data transfer}
}

@inproceedings{chizhova2026_116691,
  title = {Integrating timber stability analysis for building life cycle management and HBIM framework support},
  author = {Chizhova, Maria and Pan, Junquan and Kempter, Gerold and Luhmann, Thomas and Eißing, Thomas and Hess, Mona},
  year = {2026},
  volume = {XLIX-B1-2026},
  pages = {559-564},
  publisher = {Copernicus Publications},
  address = {Katlenburg-Lindau},
  issn = {2194-9034},
  doi = {10.5194/isprs-archives-xlix-b1-2026-559-2026},
  url = {https://fis.uni-bamberg.de/handle/uniba/116691},
  language = {eng},
  abstract = {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.},
  keywords = {Timber stability assessment, Smartphone app, openBIM, HBIM, Data transfer}
}

@inproceedings{pan2026_116374,
  title = {Multi-stage mask-aware Depth Enhancement for RGB–IR–stereo Fusion on historic Timber Surfaces},
  author = {Pan, Junquan and Chizhova, Maria and Hess, Mona and Luhmann, Thomas and Maiwald, Ferdinand},
  year = {2026},
  pages = {217-226},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-116374x},
  url = {https://fis.uni-bamberg.de/handle/uniba/116374},
  language = {eng},
  abstract = {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.},
  keywords = {Object detection, Instance segmentation, Mask-aware depth enhancement, RGB-IR–Stereo fusion, Heritage timber, Damage assessment}
}

@inproceedings{pan2026_116223,
  title = {Multi-stage mask-aware Depth Enhancement for RGB–IR–stereo Fusion on historic Timber Surfaces},
  author = {Pan, Junquan and Chizhova, Maria and Hess, Mona and Luhmann, Thomas and Maiwald, Ferdinand},
  year = {2026},
  volume = {XI-1-2026},
  pages = {217-226},
  publisher = {Copernicus Publications},
  address = {Katlenburg-Lindau},
  issn = {2194-9050},
  doi = {10.5194/isprs-annals-xi-1-2026-217-2026},
  url = {https://fis.uni-bamberg.de/handle/uniba/116223},
  language = {eng},
  abstract = {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.},
  keywords = {Object detection, Instance segmentation, Mask-aware depth enhancement, RGB-IR–Stereo fusion, Heritage timber, Damage assessment}
}

@inproceedings{pan2026_113148,
  title = {An End-to-End AI Pipeline for Wood Knot Detection to Enhance Structural Assessment in Historic Timber Structures},
  author = {Pan, Junquan and Chizhova, Maria and Ebener, Frank and Luhmann, Thomas and Ledig, Christian and Maiwald, Ferdinand and Eißing, Thomas},
  year = {2026},
  pages = {267-274},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-113148x},
  url = {https://fis.uni-bamberg.de/handle/uniba/113148},
  language = {eng},
  abstract = {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.},
  keywords = {Photogrammetry, Deep Learning, Historic Timber Structures, Wood Knot Detection, Structural Assessment}
}

@inproceedings{pan2025_110553,
  title = {An End-to-End AI Pipeline for Wood Knot Detection to Enhance Structural Assessment in Historic Timber Structures},
  author = {Pan, Junquan and Chizhova, Maria and Ebener, Frank and Luhmann, Thomas and Ledig, Christian and Maiwald, Ferdinand and Eißing, Thomas},
  year = {2025},
  volume = {X-M-2-2025},
  pages = {267-274},
  publisher = {Copernicus Publications},
  address = {Katlenburg-Lindau},
  issn = {2194-9050},
  doi = {10.5194/isprs-annals-x-m-2-2025-267-2025},
  url = {https://fis.uni-bamberg.de/handle/uniba/110553},
  language = {eng},
  abstract = {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.},
  keywords = {Photogrammetry, Deep Learning, Historic Timber Structures, Wood Knot Detection, Structural Assessment}
}

@incollection{pan2024_108798,
  title = {Automatisierte Ästigkeitsschätzung zur Verbesserung der Qualitätsbewertung von historischem Holz},
  author = {Pan, Junquan and Chizhova, Maria and Luhmann, Thomas and Eißing, Thomas and Hess, Mona},
  year = {2024},
  booktitle = {KI und Denkmalpflege. Potenziale nutzen, Risiken erkennen},
  pages = {47-55},
  address = {Berlin},
  isbn = {978-3-00-081388-7},
  url = {https://fis.uni-bamberg.de/handle/uniba/108798},
  language = {deu}
}

@inproceedings{pan2024_96611,
  title = {Machbarkeitsstudie zur automatisierten Zustandsanalyse verbauter historischer Holzbalken},
  author = {Pan, Junquan and Chizhova, Maria and Luhmann, Thomas and Eißing, Thomas},
  year = {2024},
  pages = {1-16},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-966118},
  url = {https://fis.uni-bamberg.de/handle/uniba/96611},
  language = {deu},
  abstract = {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.},
  keywords = {Ästigkeitserkennung, Altholzbalken, YOLO, KI}
}

@inproceedings{pan2024_97283,
  title = {Machbarkeitsstudie zur automatisierten Zustandsanalyse verbauter historischer Holzbalken},
  author = {Pan, Junquan and Chizhova, Maria and Luhmann, Thomas and Eißing, Thomas},
  year = {2024},
  booktitle = {44. Wissenschaftlich-Technische Jahrestagung der DGPF 2024 – Publikationen der DGPF},
  volume = {2024},
  number = {32},
  pages = {1-16},
  publisher = {DGPF},
  address = {Potsdam},
  series = {Publikationen der Deutschen Gesellschaft für Photogrammetrie, Fernerkundung und Geoinformation e.V.},
  doi = {10.24407/KXP:1885713169},
  url = {https://fis.uni-bamberg.de/handle/uniba/97283},
  language = {deu},
  abstract = {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.},
  keywords = {Ästigkeitserkennung, Altholzbalken, YOLO, KI}
}

@inproceedings{chizhova2024_95675,
  title = {Towards automatic defects analyses for 3D structural monitoring of historic timber},
  author = {Chizhova, Maria and Pan, Junquan and Luhmann, Thomas and Karami, A. and Menna, Fabio and Remondino, Fabio and Hess, Mona and Eißing, Thomas},
  year = {2024},
  pages = {103-110},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-956752},
  url = {https://fis.uni-bamberg.de/handle/uniba/95675},
  language = {eng},
  abstract = {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.},
  keywords = {historic wooden timber, feature extraction, machine learning, 3D scanning, structure from motion, multi view photometric stereo, reflectance transformation imaging}
}

@inproceedings{chizhova2024_93607,
  title = {Towards automatic defects analyses for 3D structural monitoring of historic timber},
  author = {Chizhova, Maria and Pan, Junquan and Luhmann, Thomas and Karami, A. and Menna, Fabio and Remondino, Fabio and Hess, Mona and Eißing, Thomas},
  year = {2024},
  volume = {XLVIII-2/W4-2024},
  pages = {103-110},
  publisher = {Copernicus GmbH},
  address = {Katlenburg-Lindau},
  issn = {2194-9034},
  doi = {10.5194/isprs-archives-xlviii-2-w4-2024-103-2024},
  url = {https://fis.uni-bamberg.de/handle/uniba/93607},
  language = {eng},
  abstract = {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.},
  keywords = {historic wooden timber, feature extraction, machine learning, 3D scanning, structure from motion, multi view photometric stereo, reflectance transformation imaging}
}

