Artificial intelligence based Drowsy Driver Detection
Major studies have suggested that around 20% of all road accidents are fatigue related. Drowsy Driving can be extremely dangerous; a lot of road accidents are related to the driver falling asleep while driving and subsequently losing control of the vehicle. However, initial signs of fati
2025-06-28 16:25:10 - Adil Khan
Artificial intelligence based Drowsy Driver Detection
Project Area of Specialization Artificial IntelligenceProject SummaryMajor studies have suggested that around 20% of all road accidents are fatigue related.
Drowsy Driving can be extremely dangerous; a lot of road accidents are related to the driver
falling asleep while driving and subsequently losing control of the vehicle. However, initial
signs of fatigue and drowsiness can be detected before a critical situation arises. Driver
drowsiness detection is a car safety technology that helps to prevent accidents caused by
driver getting drowsy. In this project, we aim to design and develop driver drowsiness
detection and use image processing for detecting whether the driver is feeling fatigued and
sleepy, using image processing we detect the eyes of the person and detect for how much
time the eyes are closed of the driver if the eyes are closed for greater than 20 sec the speaker
included in the system will sound an alert thus alerting the driver and waking him up,
preventing an accident.
Driver drowsiness detection is a car safety technology which helps prevent accidents caused by the driver getting drowsy. Various studies have suggested that around 20% of all road accidents are fatigue-related, up to 50% on certain roads. Automotive safety is the study and practice of design, construction, equipment and regulation to minimize the occurrence and consequences of traffic collision involving. Road traffic safety more broadly includes roadway design. According to the world Health Organization (WHO), 80% of cars sold in the world are not compliant with main safety standards. Only 40 countries have adopted the full set of the seven most important regulations for car safety. Improvements in roadway and motor vehicle designs have steadily reduced injury and death rates in all first world countries. Nevertheless, auto collisions are the leading cause of injury-related deaths, an estimated total of 1.2 million in 2004, or 25% of the total from all causes. Of those killed by autos, nearly two-thirds are pedestrians.
Project Implementation MethodWe are going to perform this project with some enhancement and by using new techniques and our technique is Eye Blinking Based Technique and this technique is explained below.
In this project eye blinking rate and eye closure duration is measured to detect driver’s drowsiness. Because when driver felt sleepy at that time his/her eye blinking and gaze between eyelids are different from normal situations so they easily detect drowsiness. Figure 2 shows the eye blinking based drowsiness detection. In this system the position of irises and eye states are monitored through time to estimate eye blinking frequency and eye close duration. This type of system uses a remotely placed camera to acquire video and computer vision methods are then applied to sequentially localize face, eyes and eyelids positions to measure ratio of closure. Using these eyes closer and blinking ration one can detect drowsiness of driver. Such a system, mounted in a discreet corner of the car, could monitor for any signs of the head tilting, the eyes drooping, or the mouth yawning simultaneously. The following figure shows the eye blink detection.
in all developed countries, the current road infrastructure is far from optimal in a sense the number of vehicles produced and sales is not proportional with regards to road infrastructure. They are especially good for big cities. Let the government remains responsible to control the vehicle growth and poor infrastructure. Besides these road characteristics, drivers violating traffic law (extreme speeding, drinking, and traffic light offense) also held largely responsible for vehicles accidents. Even with sufficient road infrastructure and excellent driving personalities, accidents are still unavoidable.
There is a strong relationship between fatigue and safety risks in driving. Fatigue may be influenced by health and sleep-related problems. Extreme fatigue can lead to driver drowsiness which has been regarded as the culprit of road accidents and may lead to severe injuries, and a high risk of death. In this regard, drowsiness is referred as the decrement or loss of alertness that led the driver to fall asleep while driving
This thesis uses eye closure rate to determine whether a motorist in a video data is tired or awake. –> Video testing procedures are shown in Figure 3.1. Drowsiness or alertness may be determined from a 30-second video clip that is sent into the device. Because the video database we utilize has a frame rate of 30 frames per second, we can extract 900 frames from a 30-second movie. The "Right and Left Eye Region Extractor" module receives all of the frames that were extracted throughout the frame extraction procedure. In this module, pictures of the right and left eye sections of each frame are discovered and cropped from the original frames in the right and left eye regions, respectively. A picture and detection state for specific areas of the right and left eye are provided by this module. Using the Eye Region Image Modifier for Neural Networks, a gray-level image of selected right and left eye regions is converted, resized, and histogram equalized. Neural networks may now use the ocular area pictures. This thesis uses eye closure rate to determine whether a motorist in a video data is tired or awake. –> Video testing procedures are shown in Figure 3.1. Drowsiness or alertness may be determined from a 30-second video clip that is sent into the device. Because the video database we utilize has a frame rate of 30 frames per second, we can extract 900 frames from a 30-second movie. The "Right and Left Eye Region Extractor" module receives all of the frames that were extracted throughout the frame extraction procedure. In this module, pictures of the right and left eye sections of each frame are discovered and cropped from the original frames in the right and left eye regions, respectively. A picture and detection state for specific areas of the right and left eye are provided by this module. Using the Eye Region Image Modifier for Neural Networks, a gray-level image of selected right and left eye regions is converted, resized, and histogram equalized. Neural networks may now use the ocular area pictures.
Final Deliverable of the Project Hardware SystemCore Industry HealthOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Good Health and Well-Being for PeopleRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 43000 | |||
| Raspberry Pi | Equipment | 1 | 35000 | 35000 |
| Camera | Equipment | 1 | 7000 | 7000 |
| Voltage Regulator | Equipment | 1 | 1000 | 1000 |