An Innovative and Real-time approach with alert to monitor the Highway Hypnosis/White line fever affected drivers
Despite the sophisticated technology that could prevent accidents of vehicles on highways, many lives are claimed due to drowsiness of drivers. According to the data reported by the NHTSA(National highway traffic safety administration) of USA, 846 succumb to death and there were about 83,000 cases registered due to drowsy driving which has become a major threat to life nowadays. Drowsiness is the feeling of being sleepy or being inactive towards activities and this causes a sleeping sensation which leads to closure of eyelids while driving resulting in major accidents. There are systems in action that could detect physical awakeness of driver, but detecting the drowsiness and deviation of the driver is a challenging problem in the field of transportation. Many factors could influence the drivers to fall asleep during their journeys and the chances of falling asleep or getting drowsy increases in night times than in the dawn and journeys did alone are even more dangerous. People tend to fall asleep more on high-speed, long deserted roads. However, those who live in urban areas are more likely to doze off while driving compared to people in rural or suburban areas (24% vs. 17%). Due to drowsy or fatigued driving, The USA National Highway Traffic Safety Administration(NHTSA) estimates that 100,000 police-reported crashes are the direct result of drowsy driving, which results in an estimated 1,550 deaths, 71,000 injuries, and $12.5 billion in monetary losses[1]. So, we introduce a system which is capable of monitoring the person's consciousness and the acceleration pattern, steering angle of the vehicle in parallel in order to detect the deviation and drowsiness of the driver and alerts the driver accordingly. The process of drowsiness and deviation detection of the driver has been done using Image Processing, machine learning techniques. Our proposed system alerts the driver by comparing acceleration pattern to the Eye Aspect Ratio(EAR) for drowsiness. It also monitors his facial movements, change in steering angle to detect whether a driver has deviated or not. ...learn more
Project status: Published/In Market
Overview / Usage
Problem Statement:
To design a system that could monitor and alert the user suffering from highway hypnosis or white line fever. We used IoT, Sensors, Data Analytics and Software to build this product
Methodology / Approach
Proposed System makes use of image processing techniques and machine learning algorithms to detect and recognize whether the driver is deviated or feeling drowsy while driving and it consists of an Onboard Diagnostics(OBD) device that could fetch data about the acceleration and steering angle pattern of the vehicle during the journey. It is essential to combinedly monitor both EAR(Eye Aspect Ratio), steering angle and acceleration pattern because of the statistics obtained from NHTSA and Solomon curve (Figure 1). It is even more dangerous when he starts coming to a saturation speed where the driver will be unaware of the horns, traffic signals and pedestrians. We use machine learning to train the machine at what speed the drivers usually feels drowsy and makes the machine more efficient at that speed. As we know, a car can be used by different drivers so we use machine learning to map the driver face to their respective acceleration pattern which can be used in the increase of efficiency in detecting the deviation and drowsiness of the driver.
Technologies Used
Arduino, Microcontrollers, IoT, Sensors, Data Analytics
Repository
Collaborators
There are no people to show.