Authors: Sarang Sunilrao Deshmukh, Nikhil Sahebrao Ghagre, Pratiksha Ganesh Dange, Prof G. N. Gaikwad
Certificate: View Certificate
Drowsy driving is a serious issue that causes a lot of accidents on the road all around the world. Due to the driver\'s inability to stay awake while driving, many accidents happen. The existing techniques utilised to do so are ineffective, and it is difficult to spot drowsy drivers. So, in order to prevent accidents, there is a need for a gadget that can recognise driver drowsiness in real-time and inform the driver. The design and development of a driver\'s anti-sleep device employing a Node MCU, an IR sensor, a gyroscope, and a buzzer are presented in this work. The proposed device can detect the driver\'s drowsiness level by analysing the driver\'s eye blinking pattern and body posture. The device triggers the buzzer to alert the driver in real-time, preventing a potential accident due to driver drowsiness. The device\'s importance lies in the fact that it can save lives and prevent injuries caused by drowsy driving. It is a cost-effective solution for detecting driver drowsiness and can be integrated into all types of vehicles. The device\'s real-time monitoring and detection system can significantly reduce the number of accidents caused by driver drowsiness. Furthermore, the proposed device is user-friendly and can be easily installed in any vehicle. It is portable and can be carried from one vehicle to another. The device can also be customized according to the driver\'s specific needs, making it highly adaptable and versatile. Overall, the proposed Driver\'s Anti-Sleep Device using Node MCU, IR Sensor, Gyroscope, and Buzzer is a highly efficient, cost-effective, and user-friendly solution for detecting driver drowsiness in real-time. The device has significant potential to reduce the number of accidents caused by drowsy driving and enhance road safety.
There is an urgent need for a trustworthy and effective driver monitoring system that can identify tiredness in real-time and notify the driver to probable accidents given the rise in traffic accidents caused by sleepy drivers. Emerging technologies like driver monitoring systems, which use cutting-edge sensors and algorithms to identify driver drowsiness, have recently been added to traditional strategies like rest breaks, caffeine consumption, and physical activity. Recent figures show that worldwide, drowsy driving is a major contributor to traffic accidents, injuries, and fatalities. For instance, in the United States, drowsy driving contributes to over 91,000 accidents and 795 fatalities each year, whereas in India, it contributed to 3.3% of accidents and 3.8% of fatalities in 2019.
Various methods have been proposed to address this issue, including regular breaks, caffeine intake, and physical activity, but these methods are not always effective, and it is difficult to identify when a driver is becoming drowsy. Therefore, there is a need for a more reliable and efficient driver monitoring system that can detect driver drowsiness in real-time and alert the driver to prevent potential accidents.
There have been intensive research works done to detect drowsiness of drivers, based on the above-mentioned gestures of body (i.e. eye motion detection and yawning detection), as we shall see in section II.
This thesis presents a novel approach to driver monitoring using a Driver's Anti-Sleep Device that integrates emerging technologies such as Node MCU, IR Sensor, Gyroscope, and Buzzer to detect driver drowsiness in real-time. The proposed device uses advanced algorithms to analyse the driver's eye blinking pattern and head position to determine the level of drowsiness. If the driver is found to be drowsy, the device triggers the Buzzer to alert the driver, preventing a potential accident.
The proposed Driver's Anti-Sleep Device is cost-effective, user-friendly, and can be easily integrated into all types of vehicles, including commercial vehicles. The device's real-time monitoring and detection system can significantly reduce the number of accidents caused by driver drowsiness, enhancing road safety. Furthermore, the device is portable and can be customized according to the driver's specific needs.
In summary, this thesis presents a significant contribution to the field of driver monitoring systems, offering a reliable and efficient solution to the problem of driver drowsiness. The proposed Driver's Anti-Sleep Device is an innovative solution that addresses the limitations of traditional approaches and stands out in the market as a cost-effective and user-friendly alternative for real-world scenarios.
II. RELATED WORK
The study in suggests using the difference image between two photographs to detect the face region. Based on the distance between the chin and the midway of the nostrils, the driver's yawn is then determined. identifies the face using the Gravity-Center template. The mouth corners are then detected using Gabor wavelets and grey projection.
LDA is then used to categorize feature vectors in order to detect yawning. shows a system that uses the Viola-Jones face detection approach to locate the face in a video frame. After that, a mouth window is removed from the face area, and lips are found using spatial fuzzy cmeans (s-FCM) clustering. takes advantage of two cameras: a low-resolution camera for the face and a high resolution one for the mouth. The driver's mouth is then recognised using haar-like traits, and yawning is determined by the ratio of mouth height to mouth breadth.
The research in also uses specific geometrical aspects of the mouth to identify yawning. In two ways, our work differs from the relevant literature.
In order to make our algorithm more resistant to changes in the subject, we start by reducing the high level of detection dependent on the facial shape. In order to have a realistic implementation within a real camera system in the car and maintain the same level of detection efficiency, we avoid the usage of complicated algorithms and classifiers. To make sure that our suggested approach is actually possible and practical for actual implementations, we have collaborated with Cognivue Corp., whose products include such in-car cameras.
III. LITERATURE SURVEY
IV. METHODOLOGY AND DISCUSSIONS
The Driver's Anti-Sleep Device is a system that uses a combination of hardware and software components to detect driver drowsiness and alert the driver in real-time. The methodology for the development of the Driver's Anti-Sleep Device is as follows:
Discussion: The Driver's Anti-Sleep Device is an innovative solution to the problem of driver drowsiness, which is a major cause of road accidents. The device is designed to be low cost, easy to use, and highly effective in detecting driver drowsiness. The hardware and software components of the device were carefully selected and integrated to ensure that the device is reliable, efficient, and accurate in detecting driver drowsiness.
The project will be developed utilizing a variety of tools and applications. The project uses an IR sensor, buzzer, vibration motor, and Node MCU. People can use the alert time to fill the driver's sleeping hours, which helps to prevent dangerous accidents. A driver who falls asleep at the wheel risks catastrophic repercussions, including accidents and potential fatalities. Since this scenario occurs far more frequently than we realize, it is crucial to find a solution. We have therefore developed a Driver Anti-sleep Device to remedy this issue.
Head movement, hand movement, awareness, and tiredness are among the important factors. "The device will instantly alert the driver if it detects any worrying circumstances. If the motorist does not demonstrate any attentiveness after five seconds, a continuous beeping sound will begin. By recognizing both open and closed eyes, the programmed seeks to precisely determine the driver's level of tiredness. The Gyroscope is mounted on the device to continuously monitor the motion of the driver. If any worrying circumstances is detected it will instantly alert the driver.
Also, all the continuously monitored data will be stored on the server in the form of graph. Data can be used to study or conclude some results to avoid such conditions. The device will also send emergency message to the contacts selected by the driver.
The drowsy detecting method is created using proteus 8 and embedded C. The main power source of the Node MCU is a lithium battery, which supplies 12 volts to the gadget. The 20 cm range of the IR sensor, which operates on a 5-volt source, is more than enough for the glass frame eye detection. The buzzer and vibration motor works 4 volts and 3 volts supply. The buzzer has the frequency of ~2300 Hz and the vibration motor has up to 12500 rpm load speed.
As for the software part, we fulfilled our goal successfully. The detection algorithm could not only work effectively and accurately at daytime, but also at night. The Eye portion extraction is smooth and in real time with no delays on the computer. In addition, there is a bonus function in the software part – detection with glasses. We experienced a few difficulties while installing the Node MCU library but were able to solve after some help from internet. It is apparent that the overall project success is not derived from one team member’s mind but the keen coloration within our group. Each part is indispensable and every team member made the great dedication on the completion of this design project. By using our Driver Sleep Detection and Alarming System, customers would be warned when his/her physical condition is not good enough for driving and thus prevents dangerous behaviours from happening. It is consistent with the safety and welfare of the public. By using Node MCU and related libraries, we try to develop and improve algorithm for eye closeness detecting. We are also using gyroscope sensor for better drowsiness detection. The IOT tools also to track data and to make communication to emergency contacts. We then apply this technology to our application in order to help drivers achieve a better and safer driving condition. We consult Professor for review advices and improve, seek online resources to help correcting errors, and properly cite the contributions of other people. We design our project using qualified components and follow proper safety rules, avoid wrong actions happening to other people.
 K. Subhashini Spurjeon, Yogesh Bahindwar, A Dedicated System for Monitoring of Driver’s Fatigue, International Journal of Innovative Research in Science, Engineering and Technology Vol. 1, Issue 2, December 2012 Copyright to IJIRSET www.ijirset.com 256  Nidhi Sharma, V. K. Banga, Drowsiness Warning System Using Artificial Intelligence, World Academy of Science, Engineering and Technology 43 2010  A. Sahayadhas , K. Sundaraj and M. Murugappan “Detecting Driver Drowsiness Based on Sensors: A Review” Sensors 2012, pp. 6937-16953.  Behnoosh Hariri, Shabnam Abtahi, Shervin Shirmohammadi, Luc Martel, A Yawning Measurement Method to Detect Driver Drowsiness.  Itenderpal singh, Prof. V.K. Banga, DEVELOPMENT OF A DROWSINESS WARNING SYSTEM USING NEURAL NETWORK, International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering (An ISO 3297: 2007 Certified Organization) Vol. 2, Issue 8, August 2013  http://umpir.ump.edu.my/1978/1/Ani_Syaza na_Jasni_(CD_5355_).pdf  http://www.ee.ryerson.ca/~phiscock/thesis/drowsy-detector/drowsy-detector.pdf  http://www.sae.org/events/gim/presentations /2012/sgambati.pdf
Copyright © 2023 Sarang Sunilrao Deshmukh, Nikhil Sahebrao Ghagre, Pratiksha Ganesh Dange, Prof G. N. Gaikwad. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.