Efficient driver drowsiness detection at moderate levels of drowsiness

Project Title

Efficient driver drowsiness detection at moderate levels of drowsiness

Project Area of Specialization Artificial IntelligenceProject Summary

Efficient driver drowsiness detection system is one of the potential applications of intelligent vehicle systems. In recent years, driver drowsiness has been one of the major causes of road accidents and can lead to severe physical injuries, deaths and significant economic losses. So, there is a need for a reliable driver drowsiness detection system which could alert the driver before a mishap happens. There are two methods for drowsiness detection. The first one is intrusive methods and the second one is non-intrusive methods. The intrusive methods include measurement of heartbeat rate, mind wave monitoring, etc. It is most accurate, but it is not realistic, because sensing electrodes would have to be attached directly onto the user’s body, and hence it would be annoying and distracting the user while the non-intrusive methods include yawn detection, eye closure, eye blinking rate, head pose, etc. It is realistic because it does not irritate the user while driving because no sensing electrodes would be attached to the user’s body. The main aim of our project is to develop a non-intrusive system which will detect the fatigue or drowsiness of a driver and will issue a warning with the help of an alarm. In this project we will detect the eye blinking if the eyes of the person are closed for more interval of time then this will result into the warning. So, the focus will be placed on designing a system that will accurately monitor the eye movements of a driver in real-time. By monitoring the eye movements, it is believed that the symptoms of driver fatigue can be detected early enough to avoid a car accident.

Project Objectives

The main objective of the proposed system is to monitor the eye movements of the driver in real time for warning the driver drowsiness or inattention to prevent traffic accidents because of the long period of continuous driving experiences mental and physical functional disorder. The real-time monitoring of the driver is taken by a camera which is installed on the dashboard in front of the driver. An algorithm and an inference are proposed to determine the level of fatigue by measuring the eyelid blinking duration and face detection to track the eyes and warn the driver accordingly. If the eyes are found closed for 5 or 8 consecutive frames, the system draws the conclusion that the driver is falling asleep and issues a warning signal. The system is also able to detect when the eyes cannot be found and warn the driver early enough to avoid the accident. The proposed system may be evaluated for the effect of drowsiness warning under various operation conditions. Our objective to obtain the experimental results, which will propose the expert system, to work out effectively for increasing safety in driving.

Project Implementation Method

Fatigue detection is not an easy task. It requires taking into account many factors. Using a video system for this purpose can be a good solution. This system would allow for precise detection of fatigue in real time. The speed of such a system is very important because even slight delays in the operation of such a system could be fatal (excessive reaction of the system while traveling along the highway). An important issue in the design of the vision-based driver fatigue detection system is the right choice of the analyzed symptoms of fatigue. In a situation, where it is not possible to monitor all potential symptoms of fatigue, it should be limited to the detection of the most important ones such as:  closing the eyelids,  slow the eye movements, yawning and dropping a head. The basis of the fatigue detection system are the algorithms responsible for detecting facial features and their motion. There are many methods that allow detecting individual facial elements.  They are based both on the vector operations and the pattern classification. Particular methods are based on an image filtering in complex space or an image processing in the spatial-frequency domain. Some methods are very effective in detecting characteristic facial features,  but sensitive to changing lighting conditions. If the system found that numbers of frames having similar images in which the person's eyes are closed occur sequentially, then the system will play an alarm in the form of sound. Detecting the drowsiness of the driver can issue a timely warning that could help in preventing many accidents

Benefits of the Project

This system uses advanced technologies which analyze and monitor the state of the driver’s eye in real-time and for real driving conditions. A drowsy driver detection system is one of the potential applications of intelligent vehicle systems. The benefit of this system is that It will accurately monitor the eye movements of a driver in real-time. By monitoring the eye movements, it is believed that the symptoms of driver fatigue can be detected early enough to avoid a car accident and could help in preventing many lives.

Technical Details of Final Deliverable

The real-time monitoring of the driver is taken by a camera which is installed on the dashboard in front of the driver to monitoring the eye movement of the eyes in order to prevent road accidents and save their lives.

Final Deliverable of the Project HW/SW integrated systemType of Industry IT , Transportation Technologies Artificial Intelligence(AI)Sustainable Development Goals Good Health and Well-Being for People, Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	50069
Graphical Processing Unit	Equipment	1	29500	29500
Raspberry Pi	Equipment	1	8999	8999
Camera	Equipment	1	9800	9800
Printing	Equipment	3	590	1770