Sezaki & Nishiyama Laboratory
Institute of Industrial Science / Center for Spatial Information Science in The University of Tokyo
Institute of Industrial Science / Center for Spatial Information Science in The University of Tokyo
Zengyi Han, Liqiang Xu, Xuefu Dong, Yuuki Nishiyama, Kaoru Sezaki
HeadMon: Head Dynamics Enabled Riding Maneuver Prediction Inproceedings
In: IEEE International Conference on Pervasive Computing and Communications (PerCom), pp. 22–31, IEEE, Atlanta, USA, 2023, ISBN: 978-1-6654-5378-3.
Abstract | BibTeX | タグ: Head Movement, Human Activity Prediction, mobile computing | Links:
@inproceedings{percom2023_han,
title = {HeadMon: Head Dynamics Enabled Riding Maneuver Prediction},
author = {Zengyi Han and Liqiang Xu and Xuefu Dong and Yuuki Nishiyama and Kaoru Sezaki},
url = {https://www.percom.org/PerCom2023/},
doi = {10.1109/PERCOM56429.2023.10099215},
isbn = {978-1-6654-5378-3},
year = {2023},
date = {2023-03-13},
urldate = {2023-03-13},
booktitle = {IEEE International Conference on Pervasive Computing and Communications (PerCom)},
pages = {22--31},
publisher = {IEEE},
address = {Atlanta, USA},
abstract = {Although micro-mobility brings convenience to modern cities, they also cause various social problems, such as traffic accidents, casualties, and substantial economic losses. Wearing protective equipment has become the primary recommendation for safe riding. However, passive protection cannot prevent the occurrence of accidents. Thus, timely predicting the rider's maneuver is essential for active protection and providing more time to avoid potential accidents from happening. Through the qualitative study, we argue that we can use the rider's head dynamic as an information source to predict the rider's following maneuvers. We accordingly present HeadMon, a riding maneuver prediction system for safe riding. HeadMon utilizes the head dynamics of a rider by installing an inertial measurement unit on the helmet. It uses the extracted head dynamics features as the input of the deep learning architecture to achieve prediction. We implemented the HeadMon prototype on Android smartphone as a proof of concept. Through comprehensive experiments with 20 participants, the result demonstrates the excellent performance of HeadMon: not only could it achieve an overall precision of at least 85% for maneuver prediction under a 4s prediction time gap, but it also could keep a high accuracy under a low sampling rate. The low-cost feature of HeadMon allows it to be readily deployable and towards more safety riding.},
keywords = {Head Movement, Human Activity Prediction, mobile computing},
pubstate = {published},
tppubtype = {inproceedings}
}