International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 02 Issue: 01 | April-2015 www.irjet.net p-ISSN: 2395-0072 © 2015, IRJET.NET- All Rights Reserved Page 345 Driver Drowsiness Detection to Reduce the Major Road Accidents in Automotive Vehicles Srinivasu Batchu 1 , S. Praveen Kumar 2 1 P.G scholar, Embedded System & Technology, SRM University, Chennai, Tamilnadu, India 2 Assistant Professor, ECE department, SRM University, Chennai, Tamilnadu, India ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - Driver errors and carelessness contribute most of the road accidents occurring nowadays. The major driver errors are caused by drowsiness, drunken and reckless behavior of the driver. This paper focuses on a driver drowsiness detection system in Intelligent Transportation System, which focuses on abnormal behavior exhibited by the driver using Raspberry pi single board computer. In the proposed system a non- intrusive driver drowsiness monitoring system has been developed using computer vision techniques. Based on the simulation results, it was found that the system has been able to detect drowsiness in spite of driver wearing spectacles as well as the darkness level inside the vehicle. Moreover the system is capable of detecting drowsiness within time duration of about two seconds. The detected abnormal behavior is corrected through alarms in real time. Key Words: Raspberry pi, Eye tracking, Yawning, Image processing, Driver Drowsiness, Harr classifier. 1. INTRODUCTION Automotive population is increasing exponentially in the country. The biggest problem regarding the increased traffic is the rising number of road accidents. Road accidents are undoubtedly a global menace in our country. The Global Status Report on Road Safety published by the World Health Organization (WHO) identified the major causes of road accidents are due to driver errors and carelessness. Driver sleepiness, alcoholism and carelessness are the key players in the accident scenario. The fatalities and associated expenses as a result of road accidents are very serious problems. The related dangers resulted have been recognized as a serious threat to many families in every country. All these factors led to the development of Intelligent Transportation Systems (ITS). Taking into account of these factors, the driver’s behavioral state is a major challenge for designing advanced driver assistance systems. The major driver errors are caused by drowsiness, drunken and reckless behavior of the driver. The real time detection of these behaviors is a serious issue regarding the design of advanced safety systems in automobiles. 2. Background Several works have been done in the field of driver abnormality monitoring and detection systems using a wide range of methods. Among the possible methods, the best techniques are the ones based on human physiological phenomena .These techniques can be implemented by measuring brain waves (EEG), heart rate (ECG) and open/closed state of the eyes. The former two methods, though being more accurate are not realistic since sensing electrodes to be attached directly onto the driver’s body and hence be annoying and distracting the driver. The latter technique based on eye closure is well suited for real world driving conditions, since it can detect the open/closed state of the eyes non-intrusively using a camera. Eye tracking based drowsiness detection systems have been done by analyzing the duration of eye closure and developing an algorithm to detect the driver’s drowsiness in advance and to warn the driver by in- vehicle alarms. 3. System architecture The proposed system comprises of three phases. 1 .Capturing: Eye Camera mounted on the dashboard is used for capturing the facial image of the driver. 2. Detection: The analysis of the captured image is done to detect the open/closed state of the eyes. The driver’s current driving behavior style is deduced using inbuilt HARR classifier cascades in OpenCV. 3. Correction: This phase is responsible for doing the corrective actions required for that particular detected abnormal behavior. The corrective actions include in- vehicle alarms and displays. The Raspberry pi single board computer which is connected serially to the PC performs the necessary corrective actions.