Self-Supervised Velocity Field Learning for High-Resolution Traffic Monitoring with Distributed Acoustic Sensing
Yacine Khacef
(1)
,
Martijn P.A. van den Ende
(1)
,
André Ferrari
(1)
,
Cédric Richard
(1)
,
Anthony Sladen
(2)
Martijn P.A. van den Ende
- Fonction : Auteur
- PersonId : 180268
- IdHAL : martijn-van-den-ende
- ORCID : 0000-0002-0634-7078
Cédric Richard
- Fonction : Auteur
- PersonId : 750253
- IdHAL : cedric-richard
- ORCID : 0000-0003-2890-141X
Anthony Sladen
- Fonction : Auteur
- PersonId : 179774
- IdHAL : anthony-sladen
- ORCID : 0000-0003-4126-0020
- IdRef : 091987407
Résumé
Distributed Acoustic Sensing (DAS) is a technology that can be employed to record vibrations along fiber optic (telecommunication) cables, including those generated by human activities. Since the optical fiber cables are often deployed along existing traffic infrastructures, DAS has the potential to record vehicular traffic flows, which permits high-resolution traffic analysis and long-term monitoring. In this work, we propose a Machine Learning (ML) model for estimating the speed of vehicles using DAS data. A major component of the proposed model is based on Continuous Piecewise Affine (CPA) transformations, which allows us to extract the speed as a function of space and time. We demonstrate the efficiency of our approach, which is significantly faster than non-ML solutions in estimating the vehicle speed.
Format du dépôt | Fichier |
---|---|
Type de dépôt | Communication dans un congrès |
Titre |
en
Self-Supervised Velocity Field Learning for High-Resolution Traffic Monitoring with Distributed Acoustic Sensing
|
Résumé |
en
Distributed Acoustic Sensing (DAS) is a technology that can be employed to record vibrations along fiber optic (telecommunication) cables, including those generated by human activities. Since the optical fiber cables are often deployed along existing traffic infrastructures, DAS has the potential to record vehicular traffic flows, which permits high-resolution traffic analysis and long-term monitoring. In this work, we propose a Machine Learning (ML) model for estimating the speed of vehicles using DAS data. A major component of the proposed model is based on Continuous Piecewise Affine (CPA) transformations, which allows us to extract the speed as a function of space and time. We demonstrate the efficiency of our approach, which is significantly faster than non-ML solutions in estimating the vehicle speed.
|
Auteur(s) |
Yacine Khacef
1
, Martijn P.A. van den Ende
1
, André Ferrari
1
, Cédric Richard
1
, Anthony Sladen
2
1
LAGRANGE -
Joseph Louis LAGRANGE
( 179867 )
- Boulevard de l'Observatoire B.P. 4229 06304 Nice Cedex 04 - France
- France
2
GEOAZUR 7329 -
Géoazur
( 239385 )
- 250 rue Albert Einstein, Sophia Antipolis 06560 VALBONNE
- France
|
Vulgarisation |
Non
|
Comité de lecture |
Oui
|
Invité |
Non
|
Audience |
Internationale
|
Titre du congrès |
2022 56th Asilomar Conference on Signals, Systems, and Computers
|
Date début congrès |
2022-10-31
|
Date fin congrès |
2022-11-02
|
Ville |
Pacific Grove
|
Pays |
États-Unis
|
Actes |
Oui
|
Source |
2022 56th Asilomar Conference on Signals, Systems, and Computers
|
Date de publication |
2022
|
Langue du document |
Anglais
|
Page/Identifiant |
790-794
|
Projet(s) ANR |
|
Domaine(s) |
|
Éditeur commercial |
|
DOI | 10.1109/IEEECONF56349.2022.10051959 |
Origine :
Fichiers produits par l'(les) auteur(s)
Loading...