Dr. Stéphane Bazeille Profile

Dr. Stéphane Bazeille

Lecturer at IUT de Mulhouse

SPIE Involvement:

Author | Editor

Proceedings Article | 28 July 2023 Paper

Enhanced key-point detection for plenoptic imaging

M. Al Assaad, S. Bazeille, T. Josso-Laurain, A. Dieterlen, C. Cudel

Proceedings Volume 12749, 127490T (2023) https://doi.org/10.1117/12.2692367

KEYWORDS: Cameras, Visualization, Microlens, Calibration, Interpolation, Image enhancement, Depth maps, Sensors

Read Abstract +

SPIE Journal Paper | 22 September 2021

Homography-based model with light calibration for plenoptic cameras

Mohamad Al Assaad, Stéphane Bazeille, Thomas Josso-Laurain, Alain Dieterlen, Christophe Cudel

OE, Vol. 60, Issue 09, 095103, (September 2021) https://doi.org/10.1117/12.10.1117/1.OE.60.9.095103

KEYWORDS: Cameras, Calibration, 3D modeling, Sensors, Optical engineering, Error analysis, Image sensors, 3D acquisition, Visual process modeling, Optimization (mathematics)

Read Abstract +

Proceedings Article | 16 July 2021 Paper

Interest of pseudo-focused images for key-points detection in plenoptic imaging

M. Al Assaad, S. Bazeille, T. Laurain, A. Dieterlen, C. Cudel

Proceedings Volume 11794, 1179405 (2021) https://doi.org/10.1117/12.2588954

KEYWORDS: Cameras, Convolutional neural networks, 3D image processing, 3D vision, Spatial resolution, Image analysis

Read Abstract +

Proceedings Article | 16 July 2021 Paper

Deflectometry based on light-field imaging

A. Meguenani, K. Tout, S. Kohler, S. Bazeille, J.-P. Chambard, C. Cudel

Proceedings Volume 11794, 1179408 (2021) https://doi.org/10.1117/12.2588988

KEYWORDS: Deflectometry, Cameras, Defect detection, System integration, Reflectivity, Imaging systems

Read Abstract +

Proceedings Article | 16 July 2019 Paper

A review of the dataset available for visual odometry

Martin Rebert, David Monnin, Stéphane Bazeille, Christophe Cudel

Proceedings Volume 11172, 111720W (2019) https://doi.org/10.1117/12.2521750

KEYWORDS: Cameras, Visualization, Global Positioning System, Sensors, Robotics, Laser scanners, Navigation systems, Robots, Micro unmanned aerial vehicles, Imaging systems

Read Abstract +

SPIE Journal Paper | 9 April 2019

Parallax beam: a vision-based motion estimation method robust to nearly planar scenes

Martin Rebert, David Monnin, Stéphane Bazeille, Christophe Cudel

JEI, Vol. 28, Issue 02, 023030, (April 2019) https://doi.org/10.1117/12.10.1117/1.JEI.28.2.023030

KEYWORDS: Cameras, Motion estimation, Visual process modeling, Motion models, Error analysis, Machine vision, Computer vision technology, Statistical analysis, Beam analyzers, Sensors

Read Abstract +

In computer vision, the epipolar geometry embeds the geometrical relationship between two views of a scene. This geometry is degenerated for planar scenes as they do not provide enough constraints to estimate it without ambiguity. Nearly planar scenes can provide the necessary constraints to resolve the ambiguity. But classic estimators such as the 5-point or 8-point algorithm combined with a random sampling strategy are likely to fail in this case because a large part of the scene is planar and it requires lots of trials to get a nondegenerated sample. However, the planar part can be associated with a homographic model and several links exist between the epipolar geometry and homographies. The epipolar geometry can indeed be recovered from at least two homographies or one homgraphy and two noncoplanar points. The latter fits a wider variety of scenes, as it is unsure to be able to find a second homography in the noncoplanar points. This method is called plane-and-parallax. The equivalence between the parallax and the epipolar lines allows to recover the epipole as their common intersection and the epipolar geometry. Robust implementations of the method are rarely given, and we encounter several limitations in our implementation. Noisy image features and outliers make the lines not to be concurrent in a common point. Also off-plane features are unequally influenced by the noise level. We noticed that the bigger the parallax is, the lesser the noise influence is. We, therefore, propose a model for the parallax that takes into account the noise on the features location to cope with the previous limitations. We call our method the “parallax beam.” The method is validated on the KITTI vision benchmark and on synthetic scenes with strong planar degeneracy. The results show that the parallax beam improves the estimation of the camera motion in the scene with planar degeneracy and remains usable when there is not any particular planar structure in the scene.

SPIE Journal Paper | 22 January 2019

Light-field image acquisition from a conventional camera: design of a four minilens ring device

Stéphane Bazeille, Yvan Maillot, Frédéric Cordier, Cécile Riou, Christophe Cudel

OE, Vol. 58, Issue 01, 015105, (January 2019) https://doi.org/10.1117/12.10.1117/1.OE.58.1.015105

KEYWORDS: Cameras, Image sensors, Prototyping, Image acquisition, Sensors, Lenses, Digital cameras, Optical engineering, Geometrical optics, Spatial resolution

Read Abstract +

Proceedings Article | 24 May 2018 Paper

Interest of polarimetric refocused images calibrated in depth for control by vision

L. Gendre, S. Bazeille, L. Bigué, C. Cudel

Proceedings Volume 10677, 106771W (2018) https://doi.org/10.1117/12.2306939

KEYWORDS: Cameras, Polarization, Polarimetry, Calibration, Optical filters, Sensors, Linear filtering, Image filtering, Prototyping, 3D image processing

Read Abstract +

Showing 5 of 8 publications

SPIE Conference Volume | 26 July 2019

Fourteenth International Conference on Quality Control by Artificial Vision

Conference Committee Involvement (1)

Fourteenth International Conference on Quality Control by Artificial Vision

15 May 2019 | Mulhouse, France

Keywords/Phrases

Search In:

Publication Years