Stride detection for pedestrian trajectory reconstruction: a machine learning approach based on geometric patterns

Frédéric Chazal; Bertrand Beaufils; Marc Grelet; Bertrand Michel

doi:10.1109/IPIN.2017.8115867

Stride detection for pedestrian trajectory reconstruction: a machine learning approach based on geometric patterns

Frédéric Chazal ¹ Bertrand Beaufils ^{2, 1} Marc Grelet ² Bertrand Michel ^{3, 1, 4}

1 DATASHAPE - Understanding the Shape of Data

CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Saclay - Ile de France

2 SYSNAV

3 ECN - École Centrale de Nantes

4 LMJL - Laboratoire de Mathématiques Jean Leray

Abstract : —In this paper, a strides detection algorithm is proposed using inertial sensors worn on the ankle. This innovative approach based on geometric patterns can detect both normal walking strides and atypical strides such as small steps, side steps and backward walking that existing methods struggle to detect. It is also robust in critical situations, when for example the wearer is sitting and moving the ankle, while most algorithms in the literature would wrongly detect strides.

Type de document :

Communication dans un congrès

IPIN 2017 - 8th International Conference on Indoor Positioning and Indoor Navigation, Sep 2017, Sapporo, Japan. IEEE, Indoor Positioning and Indoor Navigation (IPIN), 2017 International Conference on, pp.1-6, 〈http://www.ipin2017.org/〉. 〈10.1109/IPIN.2017.8115867〉

Domaine :

Informatique [cs] / Intelligence artificielle [cs.AI]

Informatique [cs] / Apprentissage [cs.LG]

Mathématiques [math] / Statistiques [math.ST]

Liste complète des métadonnées

Littérature citée [22 références] Voir Masquer Télécharger

https://hal.inria.fr/hal-01664659
Contributeur : Frédéric Chazal <>
Soumis le : mardi 19 décembre 2017 - 18:54:17
Dernière modification le : jeudi 21 juin 2018 - 17:14:03

IPIN_2017_Bertrand_Beaufils_Ve...

Fichiers produits par l'(les) auteur(s)

Stride detection for pedestrian trajectory reconstruction: a machine learning approach based on geometric patterns

Fichier

Identifiants

Collections

Citation

Exporter

Métriques

199

80

Contact

Stride detection for pedestrian trajectory reconstruction: a machine learning approach based on geometric patterns

Fichier

Identifiants

Collections

Citation

Exporter

Partager

Métriques

199

80

Contact