Pierre Charbonnier
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Pierre Charbonnier has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
- Fabrice Heitz
ICube UMR 7357, University of Strasbourg, CNRS, FMTS, 300 bd Sébastien Brant, 67412, Illkirch, France
12 shared publications - Jean-Philippe Tarel
COSYS, Gustave Eiffel University
12 shared publications - Philippe Foucher
Research Team ENDSUM, Cerema, Strasbourg, France
8 shared publications - Pierre Grussenmeyer
Université de Strasbourg, CNRS, INSA Strasbourg, ICube Laboratory UMR 7357, Photogrammetry and Geomatics Group, 67000, Strasbourg, France
8 shared publications - Samuel Guillemin
Photogrammetry and Geomatics Group, ICube Laboratory UMR 7357, INSA Strasbourg, France
7 shared publications P. Foucher
Cerema, Project-Team ENDSUM, 67100 Strasbourg, France
6 shared publications
Latest Publications
- 23 October 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (8) , 1-18
A Deep Learning Based Methodology for Assessing Road Marking Wear from Laser Imaging
- 23 October 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (8) , 1-18
A Deep Learning Based Methodology for Assessing Road Marking Wear from Laser Imaging
- Open Access
- 8 December 2022
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLVIII-2/W, 1-7
USING MACHINE LEARNING ON DEPTH MAPS AND IMAGES FOR TUNNEL EQUIPMENT SURVEYING
In this contribution, we illustrate how to use high-resolution 3D data and images to model the global shape of a tunnel and to survey its equipment, in a semi-automatic way using pattern recognition and machine learning techniques. We first implement a robust B-spline fitting algorithm, based on a parametric family of M-estimators that allows an efficient deterministic optimization strategy, to accurately model the tunnel lining using range data, despite the presence of acquisition artifacts and significant perturbations related to the equipment and some surface defects. The residual maps from the robust fit can be exploited to segment the equipment in an unsupervised manner using clustering algorithms, but at the cost of post-processing which makes the method rather ineffective for routine use. However, we deploy it to annotate data for the supervised learning of a deep learning model, namely Mask R-CNN.We comment on the first results, obtained on a still limited number of examples, and from image data only, and discuss the possibilities of improving the method, in the immediate or longer term.
- 8 December 2022
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLVIII-2/W, 1-7
Open AccessUSING MACHINE LEARNING ON DEPTH MAPS AND IMAGES FOR TUNNEL EQUIPMENT SURVEYING
In this contribution, we illustrate how to use high-resolution 3D data and images to model the global shape of a tunnel and to survey its equipment, in a semi-automatic way using pattern recognition and machine learning techniques. We first implement a robust B-spline fitting algorithm, based on a parametric family of M-estimators that allows an efficient deterministic optimization strategy, to accurately model the tunnel lining using range data, despite the presence of acquisition artifacts and significant perturbations related to the equipment and some surface defects. The residual maps from the robust fit can be exploited to segment the equipment in an unsupervised manner using clustering algorithms, but at the cost of post-processing which makes the method rather ineffective for routine use. However, we deploy it to annotate data for the supervised learning of a deep learning model, namely Mask R-CNN.We comment on the first results, obtained on a still limited number of examples, and from image data only, and discuss the possibilities of improving the method, in the immediate or longer term.
- 5 April 2022
- Published by JSTOR
- p. 221-232
DURKHEIM AND THE INDUSTRIAL REMAKING OF THE WORLD AUTONOMY WITH AND AGAINST NATURE
- 5 April 2022
- Published by JSTOR
- p. 221-232
DURKHEIM AND THE INDUSTRIAL REMAKING OF THE WORLD AUTONOMY WITH AND AGAINST NATURE
- 1 September 2021
- Published by Wiley in The Photogrammetric Record
- Vol. 36 (175) , 202-223
COMBINING PHOTOGRAMMETRIC AND BATHYMETRIC DATA TO BUILD A 3D MODEL OF A CANAL TUNNEL
- 1 September 2021
- Published by Wiley in The Photogrammetric Record
- Vol. 36 (175) , 202-223
COMBINING PHOTOGRAMMETRIC AND BATHYMETRIC DATA TO BUILD A 3D MODEL OF A CANAL TUNNEL
- Open Access
- 29 November 2019
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLII-2/W18, 39-46
SCANNING TUNNELS WITH TWO VERY HIGH-RESOLUTION LASER DEVICES AND A STACKER
In this paper, we analyse the potentialities of the LCMS (Laser Crack Measurement System) sensors for tunnel inspection. Two of these sensors have been integrated into a flexible prototype developed by Cerema, allowing data from the entire tunnel to be recorded dynamically in a few passes. Thanks to this system, we were able to acquire, in a limited time, range and intensity images of the complete vaults of four tunnel tubes, with high spatial resolution, during experimental campaigns. We present image processing methods to take advantage of this type of image. These approaches initially involve improving data visualization and reconstructing a local 3D model. We propose some preliminary approaches to correct the distance image in order to better highlight local variations in depth. These data are currently being deployed for learning neural networks for defect detection.
- 29 November 2019
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLII-2/W18, 39-46
Open AccessSCANNING TUNNELS WITH TWO VERY HIGH-RESOLUTION LASER DEVICES AND A STACKER
In this paper, we analyse the potentialities of the LCMS (Laser Crack Measurement System) sensors for tunnel inspection. Two of these sensors have been integrated into a flexible prototype developed by Cerema, allowing data from the entire tunnel to be recorded dynamically in a few passes. Thanks to this system, we were able to acquire, in a limited time, range and intensity images of the complete vaults of four tunnel tubes, with high spatial resolution, during experimental campaigns. We present image processing methods to take advantage of this type of image. These approaches initially involve improving data visualization and reconstructing a local 3D model. We propose some preliminary approaches to correct the distance image in order to better highlight local variations in depth. These data are currently being deployed for learning neural networks for defect detection.
- Open Access
- 1 September 2018
- Published by MDPI AG in Remote Sensing
- Vol. 10 (9) , 1395
Evaluating a Static Multibeam Sonar Scanner for 3D Surveys in Confined Underwater Environments
Mechanical Sonar Scanning (MSS) is a recent technology that allows sonar to be used for static measurements in the same way as Terrestrial Laser Scanners (TLS), which makes it an attractive tool for underwater infrastructure surveys. Nevertheless, the metrological capabilities of this type of device have been little explored in the literature, particularly in narrow and shallow environments. In this paper, we report on the experimental assessment of a recent MSS, the BlueView BV5000, in a lock. The 3D sonar scans performed with the system suspended from the surface are registered using an innovative algorithm that exploits external measurements from a total station and the symmetry of the structure. We review the different errors that impair sonar data, and compare the resulting point cloud to a TLS model that was acquired the day before, while the lock was completely emptied for maintenance. After correcting a tilt angle calibration error, the maximum difference is less than 10 cm, and the standard deviation is about 3 cm. Visual inspection shows that coarse defects of the masonry, such as stone lacks or cavities, can be detected in the MSS point cloud, while details smaller than 4 cm, e.g., damaged joints, are harder to notice.
- 1 September 2018
- Published by MDPI AG in Remote Sensing
- Vol. 10 (9) , 1395
Open AccessEvaluating a Static Multibeam Sonar Scanner for 3D Surveys in Confined Underwater Environments
Mechanical Sonar Scanning (MSS) is a recent technology that allows sonar to be used for static measurements in the same way as Terrestrial Laser Scanners (TLS), which makes it an attractive tool for underwater infrastructure surveys. Nevertheless, the metrological capabilities of this type of device have been little explored in the literature, particularly in narrow and shallow environments. In this paper, we report on the experimental assessment of a recent MSS, the BlueView BV5000, in a lock. The 3D sonar scans performed with the system suspended from the surface are registered using an innovative algorithm that exploits external measurements from a total station and the symmetry of the structure. We review the different errors that impair sonar data, and compare the resulting point cloud to a TLS model that was acquired the day before, while the lock was completely emptied for maintenance. After correcting a tilt angle calibration error, the maximum difference is less than 10 cm, and the standard deviation is about 3 cm. Visual inspection shows that coarse defects of the masonry, such as stone lacks or cavities, can be detected in the MSS point cloud, while details smaller than 4 cm, e.g., damaged joints, are harder to notice.
- 1 June 2017
- Published by Cambridge University Press (CUP) in Annales. Histoire, Sciences Sociales
- Vol. 72 (2) , 199-224
A Genealogy of the Anthropocene: The End of Risk and Limits
This article aims to shed light on the emergence of the Anthropocene as a concept within the social sciences and philosophy. It frames this evolution in the wider context of a crisis of knowledge, confronted with the need to consider global climate change as both an empirical ground and an inescapable political horizon. The central hypothesis is that the organization of knowledge concerning the relationships between modernity and nature has undergone a profound shift over the last decade, necessitating a reconfiguration of the two main concepts on which this knowledge relied: risk and limits. To consider the present situation through the concept of the Anthropocene is to imply that the rationality of risk (i.e., the suspension of modern political autonomy) and the notion of a fundamental limit to material development can no longer be considered separately. In the final part of the article, this hypothesis makes it possible to discuss some aspects of our current epistemological configuration.
- 1 June 2017
- Published by Cambridge University Press (CUP) in Annales. Histoire, Sciences Sociales
- Vol. 72 (2) , 199-224
A Genealogy of the Anthropocene: The End of Risk and Limits
This article aims to shed light on the emergence of the Anthropocene as a concept within the social sciences and philosophy. It frames this evolution in the wider context of a crisis of knowledge, confronted with the need to consider global climate change as both an empirical ground and an inescapable political horizon. The central hypothesis is that the organization of knowledge concerning the relationships between modernity and nature has undergone a profound shift over the last decade, necessitating a reconfiguration of the two main concepts on which this knowledge relied: risk and limits. To consider the present situation through the concept of the Anthropocene is to imply that the rationality of risk (i.e., the suspension of modern political autonomy) and the notion of a fundamental limit to material development can no longer be considered separately. In the final part of the article, this hypothesis makes it possible to discuss some aspects of our current epistemological configuration.
- Open Access
- 23 February 2017
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLII-2/W3, 495-501
DYNAMIC 3D MODELING OF A CANAL-TUNNEL USING PHOTOGRAMMETRIC AND BATHYMETRIC DATA
Keywords: 3D modeling, multibeam echosounder, photogrammetry, inspection, underwater This contribution introduces an original method for dynamically surveying the vault and underwater parts of a canal-tunnel for 3D modeling. The recording system, embedded on a barge, is composed of cameras that provide images of the above-water part of the tunnel, and a sonar that acquires underwater 3D profiles. In this contribution we propose to fully exploit the capacities of photogrammetry to deal with the issue of geo-referencing data in the absence of global positioning system (GPS) data. More specifically, we use it both for reconstructing the vault and side walls of the tunnel in 3D and for estimating the trajectory of the boat, which is necessary to rearrange sonar profiles to form the 3D model of the canal. We report on a first experimentation carried out inside a canal-tunnel and show promising preliminary results that illustrate the potentialities of the proposed approach.
- 23 February 2017
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLII-2/W3, 495-501
Open AccessDYNAMIC 3D MODELING OF A CANAL-TUNNEL USING PHOTOGRAMMETRIC AND BATHYMETRIC DATA
Keywords: 3D modeling, multibeam echosounder, photogrammetry, inspection, underwater This contribution introduces an original method for dynamically surveying the vault and underwater parts of a canal-tunnel for 3D modeling. The recording system, embedded on a barge, is composed of cameras that provide images of the above-water part of the tunnel, and a sonar that acquires underwater 3D profiles. In this contribution we propose to fully exploit the capacities of photogrammetry to deal with the issue of geo-referencing data in the absence of global positioning system (GPS) data. More specifically, we use it both for reconstructing the vault and side walls of the tunnel in 3D and for estimating the trajectory of the boat, which is necessary to rearrange sonar profiles to form the 3D model of the canal. We report on a first experimentation carried out inside a canal-tunnel and show promising preliminary results that illustrate the potentialities of the proposed approach.
- 4 July 2016
- Published by IOP Publishing in Inverse Problems
- Vol. 32 (9) , 095002
Introducing shape constraints into object-based traveltime tomography
Traveltime tomography is a difficult, ill-posed reconstruction problem due to the nonlinearity of the forward model and the limited number of measurements usually available. In such an adverse situation, pixel-based regularization methods are generally unable to provide satisfactory reconstructions. In this paper we propose a novel object-based reconstruction method that introduces prior information about the shape of the structures to be reconstructed, which yields high quality geoacoustic inversion. The proposed method approaches the forward model by a series of linear problems, leading to a sequence of minimizations during which the shape prior is introduced. The method is demonstrated on synthetic and real data, collected on a specific bench dedicated to non-destructive testing of civil engineering structures.
- 4 July 2016
- Published by IOP Publishing in Inverse Problems
- Vol. 32 (9) , 095002
Introducing shape constraints into object-based traveltime tomography
Traveltime tomography is a difficult, ill-posed reconstruction problem due to the nonlinearity of the forward model and the limited number of measurements usually available. In such an adverse situation, pixel-based regularization methods are generally unable to provide satisfactory reconstructions. In this paper we propose a novel object-based reconstruction method that introduces prior information about the shape of the structures to be reconstructed, which yields high quality geoacoustic inversion. The proposed method approaches the forward model by a series of linear problems, leading to a sequence of minimizations during which the shape prior is introduced. The method is demonstrated on synthetic and real data, collected on a specific bench dedicated to non-destructive testing of civil engineering structures.
- Open Access
- 15 June 2016
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLI-B5, 541-548
ASSESSMENT OF A STATIC MULTIBEAM SONAR SCANNER FOR 3D SURVEYING IN CONFINED SUBAQUATIC ENVIRONMENTS
- 15 June 2016
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLI-B5, 541-548
Open AccessASSESSMENT OF A STATIC MULTIBEAM SONAR SCANNER FOR 3D SURVEYING IN CONFINED SUBAQUATIC ENVIRONMENTS