Fisheye-Based Method for GPS Localization Improvement in Unknown Semi-Obstructed Areas

Autor: Julien Moreau, Sébastien Ambellouis, Yassine Ruichek

Publikováno v: Sensors, Vol 17, Iss 1, p 119 (2017)

A precise GNSS (Global Navigation Satellite System) localization is vital for autonomous road vehicles, especially in cluttered or urban environments where satellites are occluded, preventing accurate positioning. We propose to fuse GPS (Global Posit

Externí odkaz: https://doaj.org/article/0efbf78492e84e43a088de89cf4dc793

Application of Rail Segmentation in the Monitoring of Autonomous Train's Frontal Environment

Autor: Mohamed Amine Hadded, Ankur Mahtani, Sébastien Ambellouis, Jacques Boonaert, Hazem Wannous

Publikováno v: Pattern Recognition and Artificial Intelligence Third International Conference, ICPRAI 2022
ICPRAI 2022, International Conference on Pattern Recognition and Artificial Intelligence
ICPRAI 2022, International Conference on Pattern Recognition and Artificial Intelligence, Jun 2022, Paris, France. pp185-197, ⟨10.1007/978-3-031-09037-0_16⟩
Pattern Recognition and Artificial Intelligence ISBN: 9783031090363

ICPRAI 2022, International Conference on Pattern Recognition and Artificial Intelligence, Paris, FRANCE, 01-/06/2022 - 03/06/2022; One of the key factors in achieving an autonomous vehicle is understanding and modeling the driving environment. This s

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::78fca362483f720e4556f6e9de6dded4
https://hal.science/hal-03875603/file/tex00006036.pdf

Vehicles Tracking by Combining Convolutional Neural Network Based Segmentation and Optical Flow Estimation

Autor: Sébastien Ambellouis, Jacques Boonaert, Abdelmalik Taleb Ahmed, Tuan-Hung Vu

Publikováno v: ACIVS 2020, 20th International Conference on Advanced Concepts for Intelligent Vision Systems
ACIVS 2020, 20th International Conference on Advanced Concepts for Intelligent Vision Systems, Feb 2020, Auckland, New Zealand. pp529-540, ⟨10.1007/978-3-030-40605-9_45⟩
ACIVS 2020, 20th International Conference on Advanced Concepts for Intelligent Vision Systems, Feb 2020, Auckland, France. pp529-540, ⟨10.1007/978-3-030-40605-9_45⟩
Advanced Concepts for Intelligent Vision Systems ISBN: 9783030406042
ACIVS

ACIVS 2020, 20th International Conference on Advanced Concepts for Intelligent Vision Systems, Auckland, NOUVELLE-ZELANDE, 10-/02/2020 - 14/02/2020; Object tracking is an important proxy task towards action recognition. The recent successful CNN mode

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::367d61e80b16483792d375d775c7e99d
https://hal.science/hal-02960349

Human Action Recognition from Body-Part Directional Velocity using Hidden Markov Models

Autor: Anthony Fleury, Sébastien Ambellouis, Sid Ahmed Walid Talha

Publikováno v: 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)
16th IEEE International Conference on Machine Learning and Applications (ICMLA2017)
16th IEEE International Conference on Machine Learning and Applications (ICMLA2017), Dec 2017, Cancun, Mexico. ⟨10.1109/ICMLA.2017.00-14⟩
ICMLA

International audience; This paper introduces a novel approach for early recognition of human actions using 3D skeleton joints extracted from 3D depth data. We propose a novel, frame-by-frame and real-time descriptor called Body-part Directional Velo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c54868d287f4cea2496b047356b86d42
https://hal.archives-ouvertes.fr/hal-01855162

Toward a Real Time View-invariant 3D Action Recognition

Autor: Enjie Ghorbel, Anthony Fleury, Mounir Hammouche, Sébastien Ambellouis

Publikováno v: Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP)
International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP), Feb 2016, Roma, Italy. ⟨10.5220/0005843607450754⟩
International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP). (2016).
VISIGRAPP (4: VISAPP)

International audience; In this paper we propose a novel human action recognition method, robust to viewpoint variation, which combines skeleton-and depth-based action recognition approaches. For this matter, we first build several base classifiers,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ade2c9d3c561359abe51d51836ba8434
https://hal.archives-ouvertes.fr/hal-01332468