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
2 SYSNAV
3 ECN - École Centrale de Nantes
4 LMJL - Laboratoire de Mathématiques Jean Leray

—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.

Domaines: Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]; Statistiques [math.ST]

Frédéric Chazal, Bertrand Beaufils, Marc Grelet, Bertrand Michel. Stride detection for pedestrian trajectory reconstruction: a machine learning approach based on geometric patterns. IPIN 2017 - 8th International Conference on Indoor Positioning and Indoor Navigation, Sep 2017, Sapporo, Japan. pp.1-6, ⟨10.1109/IPIN.2017.8115867⟩. ⟨hal-01664659⟩