Driver Distraction Recognition Using Wearable IMU Sensor Data

Distracted driving has become a major cause of road traffic accidents. There are generally four different types distractions: manual, visual, auditory, and cognitive. Manual distractions the most common. Previous studies have used physiological indicators, vehicle behavior parameters, or machine-visual features to support research. However, these technologies not suitable for an in-vehicle environment. To address this need, study examined non-intrusive method detecting in-transit manual distractions. Wrist kinematics data from 20 drivers were collected using wearable inertial measurement units (IMU) detect common gestures made while driving: dialing hand-held cellular phone, adjusting audio climate controls, reaching object in back seat, maneuvering steering wheel stay lane. The proposed progressive classification model gesture recognition, including two time-based sequencing components Hidden Markov Model (HMM). Results show that accuracy disturbances was 95.52%. associated with recognizing reached 96.63%, model. overall advantages being sensitive perceptions motion, effectively solving problem fall-off recognition performance due excessive motion samples.