01658667

Component

Emerging wearable and mobile technologies offer new opportunities in the study of driving behaviors monitoring and analysis. This paper presents a framework for the recognition of head motions and riding patterns of Powered-Two-Wheelers (PTW) riders with the use of a smart helmet. The smart helmet is a full face motorcycle helmet integrated with an intelligent system with the capability to connect with a smartphone wirelessly. It also embedded with FHD camera and an Inertial Measurement Unit (IMU) sensor providing measurements for the motion and gesture of the rider’s head. In the analysis, the motions and the corresponding data signal are assessed with the video footage. Then, the authors introduce a feature extraction methodology to extract the most discriminant features from the raw data. Furthermore, the riding pattern recognition problem is formulated as a machine-learning based classification model for the head motion identification. Finally, the performance of the methodology is presented with real data collected in PTW riding experiments. The experimental results have confirmed that the effectiveness of using smart helmets for PTW behavior analytics.

This paper was sponsored by TRB committee ANF30 Standing Committee on Motorcycles and Mopeds.

18-04004

English

14p

2018

Transportation Research Board 97th Annual Meeting

Digital/other

Figures; Photos; References; Tables

Behavior; Cameras; Data collection; Head motion range; Machine learning; Motorcycle helmets; Motorcyclists; Pattern recognition systems; Sensors; Two wheeled vehicles

Data and Information Technology; Highways; Safety and Human Factors; Vehicles and Equipment

Transportation Research Board Annual Meeting 2018 Paper #18-04004

TRIS, TRB, ATRI

Jan 8 2018 10:59AM