INTRODUCTION/OBJECTIVE: Our project aim is, to create a sensor package that can be used to…
Sleep-deprived driving is a worldwide problem that puts thousands of lives at stake. In the USA, it is one of the major causes of motor vehicle accidents that results in about 1,550 deaths, 71,000 injuries, and $12.5 billion in losses every year. This project aims to minimise the hazard of drivers falling asleep behind the wheel by monitoring the driver with a camera which would facilitate a level of fatigue detection method. Using sophisticated software, it will detect whether the driver’s eyes are open or closed, obtain a blinking rate, and from this, identify the level of fatigue. This information would then be fed to a smartphone application which would suggest resting places to the driver if necessary, or even activate an alarm to wake the driver. A successful implementation of the project will increase road safety, and potentially save lives.
Sleep related vehicle accidents (SRVAs) are not only more common than is generally realised, but are more liable to result in death and serious injury owing to the relatively high speed of the vehicles on impact. Apart from the human misery caused, the financial cost of these accidents can be considerable, especially if lorries are involved.
It is not possible to calculate the exact number of sleep related accidents as drivers falling asleep are unlikely to recollect having done so  not to say that some drivers are killed or seriously injured and therefore unavailable to provide information about such causal factors , but according to the National Sleep Foundation’s 2005 Sleep in America poll, 60% of adult drivers – about 168 million people – say they have driven a vehicle while feeling drowsy in the past year, and more than one-third, (37% or 103 million people), have actually fallen asleep at the wheel. In fact, of those who have nodded off, 13% say they have done so at least once a month. Four percent – approximately eleven million drivers – admit they have had an accident or near accident because they dozed off or were too tired to drive.
To complement, another research shows that driver fatigue may be a contributory factor in up to 20% of road accidents, and up to one quarter of fatal and serious accidents.  It is relevant to add that these types of crashes are about 50% more likely to result in death or serious injury as they tend to be high speed impacts because a driver who has fallen asleep cannot brake or swerve to avoid or reduce the impact.
Sleepiness reduces reaction time (a critical element of safe driving). It also reduces vigilance, alertness and concentration so that the ability to perform attention-based activities (such as driving) is impaired. The speed at which information is processed is also reduced by sleepiness. The quality of decision-making may also be affected.  Furthermore, sleep laboratory studies show that people who fall asleep typically deny having been asleep if awoken within a minute or two. This was showed many years ago, and again more recently  that 2–4 minutes of sleep had to elapse before more than 50% of people acknowledged that they were asleep. These investigators noted that, “subjective sleep onset appears to be a relatively lengthy period during which perception of state is blurred and uncertain”. As a driver cannot remain asleep for more than a few seconds without having an accident, this may account for why such recollection is poor in drivers having had SRVAs.
Therefore, it is of great significance to come up with counter measurements that could help prevent the occurrence of so many losses, human and monetary. One of the solutions would be, and which we <team name> propose, is not just to detect and tell to the driver explicitly when he/she is endangering lives by falling asleep on the wheel but also by helping guiding this person to a safe stop, where the person would be able to rest and regain from sleepiness.
Our Solution would utilise an embedded system located behind the rear-view mirror of the car. From here some infra red LEDs would emitt low energy IR light onto the driver, the system would then use an IR camera to pick up the red eye of generated by the IR rays from the drivers eyes. An interference filter located on the car mirror would block any visible light from affecting the camera sensor.
The system would then use blob detection software to monitor the users red eye, this means that the system can track the frequency and time length of the users blinking to determine if they are becomming drowsey and can interface with the users smartphone to bring up suggestions of the nearest places for the driver to rest. Should the driver fall asleep then the system would detect the loss of the red eye for a period of time longer than a blink and then issue an audiable sound to awaken the driver and then suggest the nearest rest stop to their location via their phone.
There are some products currently on the market to prevent drivers from falling asleep at the wheelwhile driving however one common theme to their use is that they all rely on the driver wearing the device (e.g on their ear, similar to a bluetooth headset). The problem with this is that the products effectiveness is dependent on the user consciously puuting the device on this could mean that the user may forget to, for instance when starting a long journey in the middle of the day when they are not tired, meaning that as they travel further into the night they may not put the device on rendering it useless. To overcome this limitation we have decided to place the product already in the car (within the rear-view mirror) meaning that the user only has to install the product once and it is there all the time.
Marek Bialy, Jessica Tiemi Takeuchi, Aleksandar Angelov, Charlie Owens and Ilina Zdravkova