Bicycle Behavior Recognition Using 3-Axis Acceleration Sensor and 3-Axis Gyro Sensor Equipped with Smartphone

Yuri USAMI; Kazuaki ISHIKAWA; Toshinori TAKAYAMA; Masao YANAGISAWA; Nozomu TOGAWA

doi:10.1587/transfun.E102.A.953

Bicycle Behavior Recognition Using 3-Axis Acceleration Sensor and 3-Axis Gyro Sensor Equipped with Smartphone

Yuri USAMI, Kazuaki ISHIKAWA, Toshinori TAKAYAMA, Masao YANAGISAWA, Nozomu TOGAWA

Full Text Views

0

Cite this

Summary :

It becomes possible to prevent accidents beforehand by predicting dangerous riding behavior based on recognition of bicycle behaviors. In this paper, we propose a bicycle behavior recognition method using a three-axis acceleration sensor and three-axis gyro sensor equipped with a smartphone when it is installed on a bicycle handlebar. We focus on the periodic handlebar motions for balancing while running a bicycle and reduce the sensor noises caused by them. After that, we use machine learning for recognizing the bicycle behaviors, effectively utilizing the motion features in bicycle behavior recognition. The experimental results demonstrate that the proposed method accurately recognizes the four bicycle behaviors of stop, run straight, turn right, and turn left and its F-measure becomes around 0.9. The results indicate that, even if the smartphone is installed on the noisy bicycle handlebar, our proposed method can recognize the bicycle behaviors with almost the same accuracy as the one when a smartphone is installed on a rear axle of a bicycle on which the handlebar motion noises can be much reduced.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E102-A No.8 pp.953-965

Publication Date: 2019/08/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E102.A.953

Type of Manuscript: PAPER

Category: Intelligent Transport System

Authors

Yuri USAMI
  Waseda University
Kazuaki ISHIKAWA
  Zenrin DataCom Co., LTD.
Toshinori TAKAYAMA
  Zenrin DataCom Co., LTD.
Masao YANAGISAWA
  Waseda University
Nozomu TOGAWA
  Waseda University

Keyword

behavior recognition, smartphone, acceleration sensor, gyro sensor, bicycle

Cite this

Copy

Yuri USAMI, Kazuaki ISHIKAWA, Toshinori TAKAYAMA, Masao YANAGISAWA, Nozomu TOGAWA, "Bicycle Behavior Recognition Using 3-Axis Acceleration Sensor and 3-Axis Gyro Sensor Equipped with Smartphone" in IEICE TRANSACTIONS on Fundamentals, vol. E102-A, no. 8, pp. 953-965, August 2019, doi: 10.1587/transfun.E102.A.953.
Abstract: It becomes possible to prevent accidents beforehand by predicting dangerous riding behavior based on recognition of bicycle behaviors. In this paper, we propose a bicycle behavior recognition method using a three-axis acceleration sensor and three-axis gyro sensor equipped with a smartphone when it is installed on a bicycle handlebar. We focus on the periodic handlebar motions for balancing while running a bicycle and reduce the sensor noises caused by them. After that, we use machine learning for recognizing the bicycle behaviors, effectively utilizing the motion features in bicycle behavior recognition. The experimental results demonstrate that the proposed method accurately recognizes the four bicycle behaviors of stop, run straight, turn right, and turn left and its F-measure becomes around 0.9. The results indicate that, even if the smartphone is installed on the noisy bicycle handlebar, our proposed method can recognize the bicycle behaviors with almost the same accuracy as the one when a smartphone is installed on a rear axle of a bicycle on which the handlebar motion noises can be much reduced.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E102.A.953/_p

Copy

@ARTICLE{e102-a_8_953,
author={Yuri USAMI, Kazuaki ISHIKAWA, Toshinori TAKAYAMA, Masao YANAGISAWA, Nozomu TOGAWA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Bicycle Behavior Recognition Using 3-Axis Acceleration Sensor and 3-Axis Gyro Sensor Equipped with Smartphone},
year={2019},
volume={E102-A},
number={8},
pages={953-965},
abstract={It becomes possible to prevent accidents beforehand by predicting dangerous riding behavior based on recognition of bicycle behaviors. In this paper, we propose a bicycle behavior recognition method using a three-axis acceleration sensor and three-axis gyro sensor equipped with a smartphone when it is installed on a bicycle handlebar. We focus on the periodic handlebar motions for balancing while running a bicycle and reduce the sensor noises caused by them. After that, we use machine learning for recognizing the bicycle behaviors, effectively utilizing the motion features in bicycle behavior recognition. The experimental results demonstrate that the proposed method accurately recognizes the four bicycle behaviors of stop, run straight, turn right, and turn left and its F-measure becomes around 0.9. The results indicate that, even if the smartphone is installed on the noisy bicycle handlebar, our proposed method can recognize the bicycle behaviors with almost the same accuracy as the one when a smartphone is installed on a rear axle of a bicycle on which the handlebar motion noises can be much reduced.},
keywords={},
doi={10.1587/transfun.E102.A.953},
ISSN={1745-1337},
month={August},}

Copy

TY - JOUR
TI - Bicycle Behavior Recognition Using 3-Axis Acceleration Sensor and 3-Axis Gyro Sensor Equipped with Smartphone
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 953
EP - 965
AU - Yuri USAMI
AU - Kazuaki ISHIKAWA
AU - Toshinori TAKAYAMA
AU - Masao YANAGISAWA
AU - Nozomu TOGAWA
PY - 2019
DO - 10.1587/transfun.E102.A.953
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E102-A
IS - 8
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - August 2019
AB - It becomes possible to prevent accidents beforehand by predicting dangerous riding behavior based on recognition of bicycle behaviors. In this paper, we propose a bicycle behavior recognition method using a three-axis acceleration sensor and three-axis gyro sensor equipped with a smartphone when it is installed on a bicycle handlebar. We focus on the periodic handlebar motions for balancing while running a bicycle and reduce the sensor noises caused by them. After that, we use machine learning for recognizing the bicycle behaviors, effectively utilizing the motion features in bicycle behavior recognition. The experimental results demonstrate that the proposed method accurately recognizes the four bicycle behaviors of stop, run straight, turn right, and turn left and its F-measure becomes around 0.9. The results indicate that, even if the smartphone is installed on the noisy bicycle handlebar, our proposed method can recognize the bicycle behaviors with almost the same accuracy as the one when a smartphone is installed on a rear axle of a bicycle on which the handlebar motion noises can be much reduced.
ER -