International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 03 | Mar 2024
p-ISSN: 2395-0072
www.irjet.net
DRIVER DROWSINESS MONITORING SYSTEM WITH ACCIDENT DETECTION WARNING Divya Dharshini S1, Sanjala N M2, Sandhya A K3 , Krishnaraj R4 1UG Scholar, Department of ECE, Bannari Amman Institute of Technology, Tamil Nadu, India. 2UG Scholar, Department of ECE, Bannari Amman Institute of Technology, Tamil Nadu, India.
3UG Scholar, Department of ECE, Bannari Amman Institute of Technology, Tamil Nadu, India. 4Assistant Professor, Department of ECE, Bannari Amman Institute of Technology, Tamil Nadu, India.
-------------------------------------------------------------------------***----------------------------------------------------------------------Abstarct Nowadays, there is a significant rise in the number of accidents caused by drivers who are too sleepy. The majority of driver’s experience low energy levels as a result of their tiredness or fatigue from the amount of work they do. They therefore frequently experience drowsiness when driving. These fatigues greatly enhance the risk of accidents occurring. These models are integrated into the majority of high-end vehicles, though public transportation vehicles do nothave this technology. This project presents a holistic approach to address driver drowsiness, integrating computer vision, deep learning, and Internet of Things technologies. The system utilizes Python with OpenCV for image processing, Convolutional Neural Networks for drowsiness detection and Haar Cascade Classifier for facial feature recognition. Moreover, an embedded system featuring NodeMCU, alarm systems, relay modules, a DC motor, vibration sensor and a motor speed control mechanism is employed, enhancing the system's functionality. Additionally, alcohol sensor is integrated to check whether the driver is drunk and gives a warning alarm.
identify critical features such as eyes and head position. These features are then fed into a CNN model trained to recognize patterns associated with drowsiness, including eye closure and head nodding. Upon detection of drowsiness, the system activates an alert mechanism using the integrated IoT components.NodeMCU, serving as the IoT device, communicates with the cloud or a centralized server to transmit alert signals. The alerting mechanism incorporates an alarm system to audibly notify the driver. Taking proactive measures to prevent accidents, the integrated IoT components include a relay module that controls a DC motor. In the event of detected drowsiness, the system slows down the vehicle's speed, ensuring a safer driving environment. The vibration sensor is also incorporated to alert the driver by vibrating the seat of the driver to make him awake. Drunk and driving is also major cause for theaccident. So, additionally an alcohol sensor is integrated to check whether the driver is drunk and gives warning to the driver. To enhance user interaction and mitigate the potential for false alarms, we introduce an alarm reset button into the system. This feature enables the driver to acknowledge the alert and reset the system, providing a user-friendly experience while maintaining the system's vigilance during genuine drowsy states. The combination of computer vision, deep learning, and IoT technologies in this project forms a robust and intelligent solution to the critical issue of driver drowsiness, contributing to road safety and accident prevention.
Keywords: Computer vision, Deep learning, IoT, Alarm systems, Motor speed, Vibration sensor
1. INTRODUCTION A major risk to road safety is driver drowsiness, which raises the possibility of collisions and fatalities. Our project intends to create a complete Driver Drowsiness Detection System (DDDS) that makes use of cutting-edge technologies like computer vision, deep learning, and the Internet of Things (IoT) since we recognize how important it is to address this issue. By integrating Python-based tools like OpenCV for image processing, Convolutional Neural Networks (CNNs) for drowsiness detection, and Haar Cascade Classifier forfacial feature recognition, along with an embedded system comprising NodeMCU, alarm systems, relay modules, DC motor, vibration sensor and motor speed control, we aim to create a sophisticated solution that not only identifies drowsiness but also takes preventive measures.
2. RELATED WORKS From reference [1] the proposed idea Advanced Driver Assistance Systems (ADAS) comprise of an active safety system that detects the driver's face to identify their level of tiredness. This research describes a camera-based technique that relies on fiducial components such as the driver's lips, eye movement, and hand movements, all of which are common human responses to yawning. A front-facing camera is put on the windscreen to continuously monitor the driver, and the images are processed using a Raspberry Pi. When the driver yawns or becomes drowsy, the suggested warning system sends an auditory warning. The results show that the proposed technique is successful in detecting indicators of driver tiredness and yawning.It can distinguish
The system begins by capturing real-time facial images of the driver using a camera strategically placed within the vehicle. OpenCV is employed for preprocessing and facial feature extraction, utilizing Haar Cascade Classifier to
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 983