Presentation

Confirmed speakers

Click on the name to display the abstract

• Dr Frédéric Bosché, The University of Edinburgh - UK

  

  Dr Frédéric Bosché

   

  The University of Edinburgh

  Address: King’s Buildings Campus, 

                   William Rankine Bldg. – Room 3.18

                   Edinburgh, UK, EH9 3FG

  Email: f.bosche@ed.ac.uk

  Phone: (+)44 131 651 3525

  Frédéric is a Reader in Construction Informatics at The University of Edinburgh. He leads the CyberBuild Lab whose research explores digital twinning solutions – integrating reality capture, data processing, information management, and visualisation technologies – to enhance construction project delivery and built environment monitoring (including historic building environment). He has led projects funded by Historic Environment Scotland (HES) on: assessing modern surveying technologies for the surveying of masonry structures; the segmentation of rubble masonry walls; and the detection and classification of masonry defects in point clouds. Frédéric is the Technical Manager of the on-going Horizon-2020 COGITO on digital twinning construction projects, the subject of this talk.

  Digital Twinning Construction Projects – Lessons Learned for the Heritage sector

  This talk will summarise the motivations and objectives of the Horizon2020 -funded COGITO project that aims to develop a digital twinning solution for the planning, execution and monitoring of construction projects. This large project (€6m with 12 partners) addresses the topics of knowledge representing and information modelling, the deployment of sensing technologies to capture the state of construction projects, and the establishment of a digital twin platform that stores the information in a structured way and orchestrates the information and work flows for planning, execution and monitoring use cases related to: production, quality control, and safety. Following a summary of the project’s results to date, the speaker will reflect on the challenges faced and the lessons learned that can be drawn that would be of relevance to developing similar solutions for the monitoring and care of heritage built assets.

• Prof. Xavier Brunetaud, University of Orléans - FR

  

  Prof. Xavier Brunetaud

  University of Orléans - FR

  Address: Orléans, France
  Email: xavier.brunetaud@univ-orleans.fr
  Phone: (+) 33 2 38 49 40 52

  Xavier BRUNETAUD is Professor at the University of Orleans, France. He is graduate in Civil Engineering from Ecole Normale Supérieure de Cachan and made his PhD in Ecole Centrale Paris on concrete durability. He teaches structural mechanics and construction materials in the Polytech Orleans Engineering School. Member of the Laboratory of Mechanics “Gabriel Lamé”, his main research field is the durability of built heritage materials, mostly historical masonry. Xavier Brunetaud has been the coordinator of several interdisciplinary research projects involving the monitoring and the diagnosis of famous monuments in the Loire Valley including the castles of Chambord and Chaumont-sur-Loire.

  The DIANE project: interdisciplinary diagnosis of the castle of Chaumont-sur-Loire.

  The objective of the DIANE research project was to develop diagnosis methodology based on interdisciplinary approaches, using altogether material science, computer science, and history. During this project, a large quantity and variety of data on the Château de Chaumont-sur-Loire were produced. First, these data concern all the 3D survey of the interiors and exteriors of the castle, with particular attention paid to documenting the different stages of the progressing work of the east wing. Second, physico-chemical characterizations in the laboratory of in situ samples have made it possible to develop diagnoses of alterations in problematic areas of the Château de Chaumont-sur-Loire, leading to the analysis of conservation solutions. The documentation of degradation mappings on orthophotos of the facades was used to train Deep Learning, now able to detect degradations directly on pictures. These elements were disseminated to the decision-making authority to take them into account when developing future strategies for the monitoring and the restoration of the monument.

• Prof. Andreas Kolb, University of Siegen - DE

  

  Prof. Andreas Kolb

   

  University of Siegen

  Address: Hölderlinstr. 3; 57074 Siegen; Germany

  Email: andreas.kolb@uni-siegen.de

  Phone: (+) 49 271 740 2404

  Andreas Kolb is head of the Computer Graphics and Multimedia Systems Group at the University of Siegen since 2003. His research interests are sensor data processing including scene reconstruction, sensor simulation, and image analysis. He received his PhD at the University of Erlangen. He is member of ACM/SIGGRAPH (since 2002) and Eurographics Association (since 2001). From 10/2009 until 09/2018 he was the spokesman of the Research Training Group 1564 "Imaging New Modalities", funded by the German Research Foundation (DFG). Since 11/2019, he is DFG Liaison Officer for the University of Siegen. Currently, he is Vice spokesperson of the Centre for Sensor Systems (ZESS) at the University of Siegen.

  Interactive, high quality scene reconstruction using RGB-D cameras

  The advent of affordable consumer grade RGB‐D cameras has brought about a profound advancement of visual scene reconstruction methods. Both computer graphics and computer vision researchers spend significant effort to develop entirely new algorithms to capture comprehensive shape and appearance of models. Still, there is no overall optimum regarding performance along relevant dimensions, being it high reconstruction quality or real‐time performance on commodity hardware. The first part of this talk will give an overview of fundamental approaches, data structures and techniques applied in the field of interactive scene reconstruction and common challenges under research in this field. In the second part new trends in approaching the challenges of interactive scene reconstruction are discussed.

   

• Prof. Emmanuel Maravelakis, Hellenic Mediterranean University - GR

  

  Prof. Emmanuel Maravelakis

   

  Hellenic Mediterranean University (HMU)

  Address: Chania, Greece

  Email: marvel@hmu.gr

  Phone: (+) 306937779707

  Dr. Emmanuel Maravelakis is an Associate Professor and the head of the Design, Manufacturing & Automation Laboratory (https://dma.hmu.gr/) of the Hellenic Mediterranean University (https://hmu.gr). He earned his diploma from the Electrical Engineering Department at Aristotle University and his Msc and Phd from the Technical University of Crete. Dr. Maravelakis' primary research interests are CAD/CAM systems, 3D Modeling, 3D Documentation of Cultural Heritage, and Reverse Engineering. He has coordinated 11 national and international research projects, primarily focusing on 3D applications and reverse engineering. Additionally, he has participated as a senior researcher in over 30 other projects.

  3D Modeling the cultural treasure of Greece – Case studies and challenges

  The Cultural Heritage (CH) domain has greatly benefited from the advancements in 3D modeling technology. 3D models can serve various purposes such as documentation, restoration, conservation, presentation, and research. The creation, management, and utilization of 3D models for CH require a multidisciplinary approach, attracting the interest of many researchers in recent years. To keep up with the latest technologies such as advanced photogrammetry, 3D laser scanning, and multi-sensor 3D data capturing, 3D modeling methodologies for CH need to evolve. However, several challenges must be addressed, such as accurately documenting complex 3D geometries, handling large-scale data and increased computational requirements, using cost-effective techniques for 3D data acquisition, creating 3D models for HBIM, dealing with archaeological uncertainty in virtual 3D reconstructions, automatic or semi-automatic 3D segmentation, improving texture rendering for cultural 3D assets, and effectively implementing 3D models in various applications such as VR, AR, MR, gaming, and storytelling. This presentation highlights the results and challenges of 3D documentation projects involving the cultural treasures of Greece.

• Prof. El Mustapha Mouaddib, University of Picardie Jules Verne - FR

  

  Prof. El Mustapha Mouaddib

  MIS, University of Picardie Jules Verne

  Address: 33, Rue Saint Leu. 80000. Amiens

  Email: mouaddib@u-picardie.fr

  Phone: (+) 33 3 22 82 59 05

  El Mustapha Mouaddib received the Ph.D. degree in robotics and the Habilitation degree from the Université de Picardie Jules Verne, Amiens, France, in 1256 1991 and 1999, respectively. Since 2001, he has been a Full Professor with the same university. From 1995 to 2022, he was the Head of the Robotic Perception Group, and he was involved in research projects on omnidirectional vision and structured light. Since 2010, he has been the Leader of E-Cathedral, a multidisciplinary research initiative on digital heritage. He has served as an Associate Editor for the Conference Board of IEEE ICRA and IEEE/RSJ IROS, and for the IEEE Robotics and Automation Letters (2015–2018). His main research interests include computer vision and artificial perception for mobile robotics.

  What can 3D do for architectural heritage? The case of Notre-Dame de Paris and Amiens cathedrals.

  Beyond traditional arguments such conservation and cultural mediation, this talk will show special using of the 3D models for two major and big architectural buildings, Notre-Dame de Paris and Amiens cathedrals. The first example, by its nature after 2019 fire, forced us to work with existant data (acquired before fire) in order to help the diagnosis of this cathedral. The second one is different in the sense that there is no urgency and we can acquire 3D data as needed. In these two examples, special tools had to be developed to be able to exploit the 3D models. This task remains a difficult problem because of the 3D models size and the needed accuracy. We will explain these developed tools and the needed collaboration with art historians which is essential to fully exploit these tools.

• Dr Belén Riveiro, University of Vigo - ES

  

  Dr Belén Riveiro

   

  University of Vigo

  Address: School of Industrial Engineering

                   Campus Universitario – Vigo

                  CP36310 - Spain

  Email: belenriveiro@uvigo.gal

  Phone: (+)34 986 130 151

  Belén Riveiro is an Associate Professor of Structural Engineering at the University of Vigo. She has been an Associate Professor in Geomatics at Newcastle University (UK), and was a postdoctoral visiting research fellow at the University of Minho (2012 and 2014), the University of Cambridge (2015) and at Delft University of Technology (2016). Her research is focused on the use of remote sensing in structural engineering for the automated modelling, inspection and material characterization using inverse analysis procedures. She has been principal Investigator in several national and international research and innovation projects and coordinator of an European action on the resilience of transport infrastructure to extreme events (H2020 SAFEWAY project).

  Applications of laser scanning in the evaluation of ageing bridges

  There is an increasing concern about the exposure of ageing infrastructure assets to extreme events and their recovery capability. Bridges are challenging structures to design and built, and become one of the most vulnerable assets within the transportation network. Digitalization is playing a key role in the adoption of innovative methods that allow optimizing maintenance expenditures. As a result, new techniques in data acquisition and monitoring are being proposed to accurately assess the health condition of in-service structures.

  This talk will present some recent examples of the research where laser scanning has been demonstrated to be a suitable technology to assess the actual condition of various types of in-service bridges, with the purpose of being used for the structural diagnosis. Automated data processing will be another key point in this talk, motivated by the Big Data nature of the datasets typically collected during the survey and monitoring of large infrastructure. A revision of methods successfully applied to the processing of the aforementioned data will be presented, complemented with real case studies where the different methodologies have been demonstrated.

• Roxane Roussel, Map Laboratory - FR

  

  Roxane Roussel

   

  UMR 3495 MAP CNRS/MC

  Address:  Campus CNRS, Bâtiment US
  31 chemin Joseph Aiguier
  13402 MARSEILLE cedex 20

  Email: roxane.roussel@map.cnrs.fr

  Roxane Roussel holds a State Diploma in Architecture from the ENSA Marseille, with a research mention, and has since worked as a study engineer at CICRP and MAP-gamsau, focusing on the annotation and semantic enrichment of heterogeneous heritage data. She is currently involved in the construction of a digital report for the Notre-Dame de Paris cathedral as a member of the MAP laboratory.

  An approach for the construction of a digital report and digital twin for the Notre-Dame cathedral after the fire

  Since the fire of the Notre-Dame de Paris cathedral that took place in 2019, the scientific community has seized this singular framework in order to gather and build data on the cathedral, as well as assisting the restoration worksite. In this context, the « digital data » working group, coordinated by Livio De Luca, works to create a « digital ecosystem » by gathering and merging existing data, generating new data, archiving, and ultimately organizing and enhancing it with semantic features. This presentation here focuses on the work carried out in order to build a complete digital report of the Notre-Dame cathedral after the fire, using the aïoli platform. The methodology included the construction of 3D point clouds for sections of the cathedral, with the use of photogrammetry, then followed by the enrichment of the projects using annotations, description sheets and joined files in order to articulate the information emerging from the researchers and professionals (architecture, archaeology, history, computer science, chemistry, physics…). Furthermore, this ongoing work enables not only cross-checking of the data but also the ability to search for numerical information and evaluate the frequency of specific observations by using one or multiple targeted keywords.

• Dr Barthélemy Serres, University of Tours - FR

  

  Dr Barthélemy Serres

   

  Institutions:

  1. CETU ILIAD3,

  2.LIFAT Université de Tours

  Address: 64 av. Jean Portalis, 37200 TOURS

  Email: barthelemy.serres@univ-tours.fr

  Phone: (+) 33 6 27 65 90 21

  Doctor-Ing. In Computer Sciences from 2013, he worked on several research projects, from academics ones to industrials. After a research fellow position in Germany in 2014, he was back to France, in Tours, to create in 2016 with Pr. Gilles Venturini and head a new applied research lab, called ILIAD3. ILIAD3 helps various labs in the field of AI data algorithms, computer vision, 3D digital capture and visualisation and interactions projects. Barthélemy specifically worked on applied research in Digital Humanities with main outcomes which were part of exhibitions (Musée des Beaux-Arts, 2018 ; Chambord 1519-2019, 2019 ; Château de Blois, 2020  ; Azay le Rideau, 2021; Chateau de Loches 2022) and more recently the “Tour de Choeur de Chartres” (2023).

  A review of Cultural Heritage digital projects with innovations outcomes in public exhibitions setups  

  Among all various projects ILIAD3 were involved in, a large amount of them had to deal with interactions and visualisation setups integrated in public exhibition. From Reality Augmented mobile apps, to dedicated engineered devices (input devices, display devices) we designed, developed and experimented many prototypes.  In this talk, we will present the design stages, and methodology used with scientist teams in various domains such as Computer Sciences: 3D data collection, processing and application design, and Human Science, including Art History, History, Sociology. Working in a multidisciplinary environment needs every actor, from scientists, engineers to technical staff from Museum, Monuments or Castles to work together. The first part of this presentation will expose the purposes and the issues to be addressed in such projects. In the second part, we will illustrate the talk showing previous and current projects examples. We will finally discuss each methods and objectives along with public feedback and further improvements. 
   

• Dr Sylvie Treuillet, University of Orléans - FR

  

  Dr Sylvie Treuillet

   

  University of Orléans

  Address: Polytech Orléans

  12 rue de Blois, 45067 Orléans cedex 2 - France

  Email: sylvie.treuilet@univ-orleans.fr

  Phone: +33 238 494 565

  Sylvie Treuillet is an Associate Professor at the University of Orléans. She has been working as a specialist in computer vision and pattern recognition since 1994. She received MS degree in electrical engineering and obtained a PhD in computer vision at the University of Clermont-Ferrand. She has been part of several European or international projects, has supervised about fifteen doctoral theses and has published more than 100 articles on image processing, computer vision and machine learning in biomedical and industrial applications. Her recent research at the PRISME laboratory is particularly focused on the development of diagnostic tools for historic buildings based on multimodal data processing (image/3D) and deep learning. She is member of IAPR TC 19 (Computer Vision for Cultural Heritage Applications.)

  Diagnostic tools for historic buildings using deep learning from 3D survey images

  The planning of restoration operations of cultural heritage buildings requires a precise and updated diagnosis of the different areas of deterioration. At the scale of large buildings, an exhaustive survey is difficult to perform by traditional methods of visual inspection by experts. Rapid advances in computer vision and deep learning are inspiring the development of automatic damage detection approaches. The tutorial will present a new approach to automatically detect stone deterioration at the scale of a castle by deep learning techniques from existing color images acquired for 3D modeling. A first part will be devoted to an introduction to deep learning for the lay audience, followed by a practical application with a pre-trained model. In a second part, we will propose to show how to train a network from a dataset, and how to evaluate the performance of the model predictions.

Partners of the event