PROTOTYPE FOR DRIVER DROWSINESS DETECTION SYSTEM
Santosh Botagi
Department of CSE
Nitte Meenakshi Institute of Technology
Bengaluru, India
1nt18cs146.santosh@nmit.ac.in
Md Azroddin
Department of CSE
Nitte Meenakshi Institute of Technology
Bengaluru, India
1nt18cs095.mdazroddin@nmit.ac.in
Gurukiran K M
Department of CSE
Nitte Meenakshi Institute of Technology
Bengaluru, India
1nt18cs047.gurukiran@nmit.ac.in
Dr. Vani V
Department of CSE
Nitte Meenakshi Institute of Technology
Bengaluru, India
vani.v@nmit.ac.in
Dhrithi V G
Department of CSE
Nitte Meenakshi Institute of Technology
Bengaluru, India
1nt18cs039.dhrithi@nmit.ac.in
Abstract—Driver drowsiness and fatigue are one of the major reasons for road accidents that occur globally. Car accidents can be avoided by implementing a system with an alarm to alert drowsy drivers in order to focus on the road and help them to stay focused. In this paper, a prototype for Driver Drowsiness Detection System is proposed to reduce fatalities and to overall contribute in increasing the transportational safety on road; this proposed method uses Python, dlib and OpenCV to build a real-time framework that uses a computerized camera to monitor and process the driver’s eye and yawn. The proposed system acknowledges whether the driver is sleepy and it gives a caution alert, when his eyes and yawn are discovered close together for a particular measure of casing.
Keywords—driver drowsiness, face detection, yawn detection, openCV, python, fatigue, drowsy, alarm.
I. INTRODUCTION
Drowsiness is a process in which one level of consciousness is reduced due to lack of sleep or fatigue and it may cause the driver to fall asleep quietly. When the driver is suffering from drowsiness he loses control of the car, so he might be suddenly deviated from the road and hit an obstacle or a car to overturn. Driver drowsiness accounts for almost twenty one percent of fatal accidents,. sixty percent of drivers or about a hundred sixty million people have driven a vehicle while feeling drowsy. In the past year, sixty percent of adult drivers have driven a vehicle while falling asleep at the wheel. In this context, it is important to use new technologies to design and build systems that are able to monitor drivers and to measure their level of attention during the entire process of driving.
The main objective of this paper is to propose a system which makes use of face detection, yawn detection, eye tracking and also head movement detection of the driver with the help of a camera and processes the video frames and detects the opening and closing of eyes and mouth, and with set threshold for monitoring the same, an acoustic alert is fired, if the threshold is crossed, thereby saving many lives on the road.
The remainder of this paper is organized as follows: Section 2 provides an overview of Related Works, Section 3 elaborates on the Working of our Proposed System, Section 4 presents the Results and Section 5 contains the Conclusions and discussions.
II. RELATED WORKS
Mohammad Amin Assari et al.[1] developed a hardware-based system for driver drowsiness detection using facial expressions. The implemented hardware is based on infrared light. Using infrared light has provided benefits such as simplicity of used methods, independent from environment lighting conditions.In the proposed method, after determining the face region using the background subtraction technique, the facial components are obtained by horizontal projection and template matching. In the tracking phase using template matching elements found in the previous step are followed up and eventually the incidence of sleepiness was investigated using determination of the facial state from the changes of the facial components[1]. Based on the previous investigation, three changes, eyebrows raising up, eyes closing and yawning for a certain period are considered as starting symptoms in the driver’s drowsiness and the system will warn. The results indicate that the system in the presence of glasses or beard and mustache on the driver’s face will produce appropriate response, too.
Ashish Kumar et al.[2] proposes a low-cost, real-time driver drowsiness monitoring system, based on visual behavior and machine learning. In the system visual behavioral features such as eye aspect ratio, mouth aspect ratio, and nose length ratio have been measured and are taken into consideration by capturing frames from a streaming video frame that is captured from a webcam. Then using the data they have used classifiers such as Naives-Bayes, FLDA and SVM. Since the accuracy is more they have collected and used FLDA and SVM algorithms to increase the accuracy of the system.
Amin Aziz Suhaiman et al.[3] have developed a system that makes use of image processing techniques to detect the driver drowsiness level by calculating the eye aspect ratio, mouth aspect ratio and other parameters that are required for capturing the drowsiness levels. The data that is gathered on the eye aspect ratio makes the base for detecting the driver’s drowsiness levels and an acoustic alert is issued when the driver is found to be sleepy.
Roopalakshmi et al.[4] introduces a drowsiness detection framework based on shape predictor algorithm, that detects the eyes, and also counts the eye blink rate followed by drowsiness detection at real time. In the proposed system, the details about the eye status is obtained through image processing algorithms, which offer a non-invasive approach to detect drowsiness without any annoyance and interference. In future, the detection of yawning of the driver can also be implemented using the same framework for detecting further details about the drowsiness of the driver.
Jun-Juh Yan et al. [5] developed a real-time, gray-scale simulation system to detect driver drowsiness by image processing. In testing and results, and based on the fatigue model, the system can help monitor the drivers’ physical state, and remind drivers if they are tired, which they themselves may not have noticed. [6] The biggest difference between commercially available products and the system proposed in this study is the use of gray-scale images, which means that detection of skin color is not required. Although the proposed system features additional calculation steps, it requires less memory and could be applied in different environmental conditions. For example, it could be used even when the driver is wearing glasses or a respiratory mask.
III. OVERVIEW OF THE PROPOSED SYSTEM
The detection methods are categorized as subjective and objective detection, objective detection as it monitors the driver’s physiological state and driving- behavior characteristics in real time. Furthermore, objective detection is categorized into two: contact and non-contact[7]. Compared with the contact method, non-contact is cheaper and more convenient because systems that do not require Computer Vision technology or sophisticated cameras allow the use of the device in more cars.
prototype-for-driver-drowsiness-detection-system
FREE DOWNLOAD
@ engpaper.com published paper
PUBLICATION PROCEDURE WITH US ENGPAPER.COM
ENGPAPER.COM PUBLISHED PAPERS