Driver Drowsiness Detection System

Driver Drowsiness Detection System

R. Bindu, M. Alekhya, Abdul Kareem, K. Karunakar

Sreenidhi Institute of Science and  Technology

Telangana, Hyderabad

Abstract- Driver drowsiness is a serious issue that poses a significant risk to road safety. To combat this problem, researchers and engineers have developed driver drowsiness detection systems that use advanced technologies to identify signs of drowsiness in drivers. Our proposed system is based on computer vision techniques and machine learning algorithms. The system is designed to analyze the driver's facial features in real-time, such as eye movements, head pose, and yawning, to detect signs of drowsiness. The system also includes an audio alarm that can alert the driver if drowsiness is detected. To develop and train our system, we used a large dataset of annotated driver drowsiness images. This dataset was used to train our machine learning algorithms to accurately identify signs of drowsiness in the driver's facial features. Our proposed system has several advantages over existing driver drowsiness detection systems. First, it is designed to work in real-time, which is essential for timely detection and intervention. Second, our system is highly accurate, thanks to the use of advanced computer vision techniques and machine learning algorithms. Finally, our system can be easily integrated into existing driver assistance systems, making it a practical and cost-effective solution. In conclusion, we believe that our proposed driver drowsiness detection system has the potential to significantly improve road safety by reducing the number of accidents caused by drowsy drivers. By providing an early warning system that can detect signs of drowsiness in real-time, we can help prevent accidents and save lives on our roads.

Keywords: Convolutional Neural Network, Support Vector Machine (SVM), ReLU layers, Pooling layers, Keras, Dropout, Dense layer, Max pooling