A Method for Averting Driver's Drowsiness

(1)

International Journal of Electrical, Electronics and Computer Systems (IJEECS)

________________________________________________________________________________________________

ISSN (Online): 2347 - 2812, Volume-3, Issue -1, 2015 26

Driver -Vehicle-Interface (D-V-I): A Method for Averting Driver’s Drowsiness

1Priyanaka Sawant, ²M.Z.Shaikh

1Computer Department, Instrumentation Department, Mumbai University,

2Bharatividyapeeth College of Engineering, Kharghar, Navimumbai Email : ¹[email protected], ²[email protected]

Abstract -A Drowsy Driver Detection System has been developed, using a non-intrusive machine vision based concepts. The system uses a small monochrome security camera that points directly towards the driver’s face and monitors the driver’s eyes in order to detect fatigue. In such a case when fatigue is detected, a warning signal is issued to alert the driver. This report describes how to find the eyes, and also how to determine if the eyes are open or closed. The system deals with using information obtained for the binary version of the image to find the edges of the face, which narrows the area of where the eyes may exist.

Once the face area is found, the eyes are found by computing the horizontal averages in the area. Taking into account the knowledge that eye regions in the face present great intensity changes, the eyes are located by finding the significant intensity changes in the face. Once the eyes are located, measuring the distances between the intensity changes in the eye area determine whether the eyes are open or closed. A large distance corresponds to eye closure.

If the eyes are found closed for specified 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 works under reasonable lighting conditions.

Keywords: Image processing, Face detection, eye detection, eye tracking, template matching, OpenCV.

I. INTRODUCTION

A Road Traffic Accident (RTA) can be defined as, „An event that occurs on a way or street open to public traffic; resulting in one or more persons being injured or killed, where at least one moving vehicle is involved.

Thus RTA is a collision between vehicles; between vehicles and pedestrians; between vehicles and animals;

or between vehicles and geographical or architectural obstacles.‟ Road traffic accidents are a human tragedy.

They involve high human suffering and socioeconomic costs in terms of premature deaths, injuries, loss of productivity, and so on.

Driver fatigue is a significant factor in a large number of vehicle accidents. Recent statistics estimate that the total number of road accidents was 4,86,476, the number of persons killed in road accidents was 1,37,572 and the number of persons injured in road accidents was 4,94,893 injured persons.

The increased number of car accidents is a very serious problem. Dangerous to the driver himself, passenger and outside people as well. When it is noticed that the accidents are caused due driver's fault is painful and a critical problem to think and solve. A study indicates that the majority of the accidents are due to driver fatigue, drowsiness of drivers.

The development of technologies for detecting or preventing drowsiness at the wheel is a major challenge in the field of accident avoidance systems. Because of the hazard that drowsiness presents on the road, methods need to be developed for counteracting its affects.

The objective of this paper is to develop a prototype drowsiness detection system. The focus will be placed on designing a system that will accurately monitor the open or closed state of the driver‟s eyes in real-time. By monitoring the eyes, it is believed that the symptoms of driver fatigue can be detected early enough to avoid a car accident. Detection of fatigue involves a sequence of images of a face, and the observation of eye movements and blink patterns.

The analysis of face images is a popular research area with applications such as face recognition, virtual tools, and human identification security systems. This paper is focused on the localization of the eyes, which involves looking at the entire image of the face, and determining the position of the eyes, by a self-developed image- processing algorithm. Once the position of the eyes is located, the system is designed to determine whether the eyes are opened or closed, and detect fatigue.

II. PREVIOUS WORK

Possible techniques for detecting drowsiness in drivers can be generally divided into the following categories:

sensing of physiological characteristics, sensing of driver operation, sensing of vehicle response, monitoring the response of driver.

A. Monitoring Physiological Characteristics

Among these methods, the techniques that are best, based on accuracy are the ones based on biomedical synthesis human physiological phenomena [1]. The

(2)

International Journal of Recent Advances in Engineering & Technology (IJRAET)

________________________________________________________________________________________________

ISSN (Online): 2347-2820, Volume -3, Issue-3 2015 27

reason for the accuracy lies in the implementation of the technique. Since we would be directly monitoring drivers‟ physical and mental statistics, they are the ones we can rely on.

This technique is implemented in two ways: measuring changes in physiological signals, such as brain waves, heart rate, and eye blinking; and measuring physical changes such as sagging posture, leaning of the driver‟s head and the open/closed states of the eyes[2].

Monitoring Physiological Signals:

Though the first technique sounds to be most accurate, it carries some prominent drawbacks.It is not feasible to implement the technique since it needs the electrodes to be attached directly to driver‟s body. One can imagine how annoying and disturbing this could be while driving when driver needs to concentrate most on driving only.

Further if it needs to be used in long run, it can result into deterioration and perspiration on the sensors, diminishing their ability to monitor accurately [3][4].

Monitoring Physical Status:

Due to the drawback of measuring physiological signal, one can opt for the second technique for real world driving conditions since it can be non-intrusive by using optical sensors of video cameras to detect changes. One can monitor driver‟s head position, posture or the state of eyes to monitor drowsiness [1] [3].

B. Other Methods

Driver operation and vehicle behavior can be implemented by monitoring the steering wheel movement, accelerator or brake patterns, vehicle speed, lateral acceleration, and lateral displacement. These too are non-intrusive ways of detecting drowsiness, but are limited to vehicle type and driver conditions. The final technique for detecting drowsiness is by monitoring the response of the driver. This involves periodically requesting the driver to send a response to the system to indicate alertness. The problem with this technique is that it will eventually become tiresome and annoying to the driver [1] [2] and [3].

Fig 1. Approach for Drowsiness Detection and Driver Warning

B..Drawbacks of Existing System

 Electrodes have to be attached to the body of the driver for sensing the signals

 Non-contact type sensing is also highly dependent on environmental conditions

III. PROPOSED SYSTEM

This system includes methods based on driver visual analysis using image processing techniques. Image processing is becoming one of the major methods to analysis features of human body parts nowadays. The mainly focused features are all on faces, and to be more specific, eyes are the most important features that need to detect the fatigue driving. In this paper, we used OpenCV to analysis the features we measured and build the system we need to detect fatigue driving. The reason we choose OpenCV is that this tool is user friendly and have huge library to process the features we want to analysis.

The system detects the driver fatigue based on eye tracking which comes under an active safety system. At first, an ordinary color webcam is used to capture the images of the driver for fatigue detection as shown in fig 2. The first frame is used for initial face detection and eye location. If any one of these detection procedures fails, then go to the next frame and restart the above detection processes. Otherwise, the current eye images are used as the dynamic templates for eye tracking on subsequent frames, and then the fatigue detection process is performed. If eye tracking fails, the face detection and eye location restart on the current frame.

These procedures continue until there are no more frames [10].

Fig 2.Block diagram of proposed system Fig. 2 shows the flow diagram of the proposed system that describes about Eye tracking and Driver Fatigue Detection. This system is implemented using two methods.

1. The input image, which is taken from the camera, corresponds to a driver‟s face, who can be affected by different states of drowsiness. The input image is processed to detect face and eyes applying HARR CLASSIFIER algorithm to track their position as shown in fig 3. Once the eyes are detected, iris centre

(3)

________________________________________________________________________________________________

location module is executed. It is based on integral projections. Then the eyes closure is calculated. From this parameter, PERCLOS is estimated [7].

Fig. 3. Face and eyes detection in real conditions 2. The live video is captured and stored in the database. From each of the frame the skin is extracted to detect the face of the driver alone from the frame by eliminating the objects bounding the driver and stored in a separate database. After face detection has been done the eyes are configured by giving the control points around the eyes [11][12].The eye template is then cropped and stored as shown in fi 4. With the stored template as reference we track the eyes of the driver continuously in the live video using dynamic template matching. If the eyes of the drivers are closed for a continuous number of frames then the driver is said to be in fatigue state. When driver is in fatigue stat it needs to alert the driver to save his/her life.

Fig. 4Open and closed eyes template The system alerts the driver by three different ways:

Note that the alerting here would be for all major senses of a human being. Eyes, Ear, touch (motion) being the most prominent sensors being used by any human being, the system will alert the driver on all levels. This is necessary since we are dealing with one of the most difficult situation where a person can sometimes ignore some alerts coming from one direction. Let‟s say, if driver‟s eyes are already closed, there is no point in lighting the alert signal in front of driver.

1. Sound the alarm

This would help alerting the driver as well as other passengers in the vehicle. So that everybody in the vehicle would be alert and can avoid further consequences by having alternate solutions, say, to make driver rest for some time or someone else would shift on a driver‟s seat.

2. Lighting the front and back light of the car Another signal for driver and passengers from vehicle as well as other vehicles on the road. In most of the car crashes, it has been noticed that when the fatigued driver has crashed a car, it has dashed his vehicle on another one. The alert signal would help other vehicles notify the critical state to other vehicles so that they can have options available to stay away from the route or to take any emergency action.

3. Vibrating motor is used for driver seat It can act as one of the most effective alerting mechanism apart from alarm notification. It has been observed, that a person under the effect of sleepiness can be alerted immediately through vibrations. This can act as a shocking alert for a driver to completely shake him out of the drowsiness. The response time from the driver also makes difference here. A sleepy person responds to such alert quickly than a sound alert.

We are not making any comparisons here; rather we are trying to make sure that the person is alerted on all levels so as to avoid further accident.

IV. SCOPE & APPLICATIONS

Only the imagination can limit the applications of the above proposed system.

Though the following are some examples…

 Prevents road accidents,

 Detect drowsiness of driver,

 Alert driver through sound, etc,

V. CONCLUSION

This paper follows the non-intrusive approach to monitor driver‟s physical state. Here, the face is detected and eyes are tracked from the captured image. This approach captures the face first and crops the same in order to concentrate on eyes. Driver‟s eyes are captured beforehand so as to use as a template. It further alerts the driver if any mismatch is observed. It can happen if the driver closes eyes for longer time or if the driver has turns his head away. The system alerts the driver in three ways; one being sound alarm, second will be to flash lights and third will be to have vibrating alert to make sure that the driver is alerted properly.

REFERENCES

[1] Vision-based drowsiness detector for Real Driving conditionsI. Garc´ıa, S. Bronte, L. M.

Bergasa, J. Almaz´an, J. Yebes.

[2] T. Akerstedt, G. Kecklund, and L. H¨orte, “Night driving, season, and the risk of highway accidents.” Slee, vol. 24, pp. 401–406, 2001.

[3] J. Connor, R. Norton, S. Ameratunga, E.

Robinson, I. Civil, R. Dunn, J. Bailey, and R.

Jackson, “Driver sleepiness and risk of serious

(4)

________________________________________________________________________________________________

injury to car occupants: Population based control study.” British MedicalJournal, vol. 324, pp.1125–1129, 2002.

[4] J. Horne and L. Reyner, “Vehicle accidents related to sleep: A review.”Occupation and Environmental Medicine, vol.56, pp. 189–294, 1999.

[5] L. M. Bergasa, J. Nuevo, M. ´A. Sotelo, R.

Barea, and M. E. L. Guill´en, “Real-time system for monitoring driver vigilance,” IEEE Transactionson Intelligence Transportation Systems, vol. 7, no. 1, pp. 63–77, 2006.

[6] Y. Takei and Y. Furukawa, “Estimate of driver‟s fatigue through steeringmotion.”IEEE International Conference on Systems, Man andCybernetics., vol. 2, p. 1765– 1770, 2005.

[7] I. Garc´ıa, S. Bronte, L. Bergasa, N. Hern´andez, B.Delgado, and M. Sevillano, “Vision-based drowsiness detector for a realistic driving simulator,” in IEEE Intelligent Transportations Systems Conference(ITSC), 2010.

[8] J. F. May and C. L. Baldwin, “Driver fatigue:

The importance of identifying causal factors of fatigue when considering detection and countermeasure technologies,” Transportation Research Part F: TrafficPsychology and Behaviour, vol. 12, no. 3, pp. 218 – 224, 009.

[Online]. Available:

http://www.sciencedirect.com/science/article/B6 VN8-4VFBYG1

1/2/07087f8c3b6f88f9e9ed6996388d01ed [9] I. Daza, N. Hernandez, L. Bergasa, I. Parra, J.

Yebes, M. Gavilan, R. Quintero, D. Llorca, and M. Sotelo, “Drowsiness monitoring based on driver and driving data fusion,” in Intelligent

TransportationSystems (ITSC), 2011 14th International IEEE Conference on, oct.2011, pp.

1199 –1204.

[10] D.Jayanthi, M.Bommy, “Vision-based Real-time Driver Fatigue Detection System for Efficient Vehicle Control” International Journal of Engineering and Advanced Technology (IJEAT) ISSN: 2249 – 8958, Volume-2, Issue-1, October 2012.

[11] Jay D. Fuletra,DulariBosamiya ,“A Survey on Driver‟s Drowsiness Detection Techniques”, International Journal on Recent and Innovation Trends in Computing and Communication ISSN:

2321-8169 Volume: 1 Issue: 11.a

[12] Wen-Bing Horng, Chih-Yuan Chen,Jian-Wen Peng, Chen-Hsiang Chen . “Improvements of Driver Fatigue Detection System Based on Eye Tracking and Dynamic Template Matching“,WSEAS TRANSACTIONS on

INFORMATION SCIENCE and

APPLICATIONS.

[13] M.A. Recarte and L.M. Nunes, “Effects of Verbal and Spatial-Imagery Tasks on Eye Fixation while Driving,” Journal of Experimental Psychology: Applied, Vol.6, No.1, 2000, pp.31- 43.

[14] J.H. Yang, Z.H. Mao, L. Tijerina, T. Pilutti, J.F.

Coughlin, and E. Feron, “Detection of Driver Fatigue Caused by Sleep Deprivation,” IEEE Transactions on Systems, Man, and Cybernetics－ Part A: Systems and Humans, Vol. 39, No. 4, 2009, pp. 694-705.

[15] DRIVER FATIGUE MONITORING SYSTEM USING SUPPORT VECTOR MACHINES Matthew Sacco, Reuben A. Farrugia.

