Driver's distraction detection based on gaze estimation
Shweta Maralappanavar, Reena Kumari Behera, Uma Mudenagudi · 2016
Drivers easily get distracted by the activities happening around them such as texting, talking on mobile phone or talking to the neighbouring person. All these activities take driver's attention away from the road which may lead to accidents, cause harm to the driver, pedestrians and also other vehicles on the road. In this paper, a method is proposed to estimate the gaze of the driver and determine whether the driver is distracted or not. Driver's gaze direction is estimated as an indicator of his attentiveness. The driver's gaze estimation is done by detecting the gaze with the help of face, eye, pupil, eye corners and then the detected gaze is then categorized as whether the driver is distracted or not. The algorithm is developed in OpenCV and tested on a CPU platform (Intel core with 4 GB RAM). The processing time taken for the execution of a single frame is around one second. The gaze detection accuracy obtained is 75%.