Driver Dizziness Monitoring and Alert System
Authors:-Prateek Raj, Kinshuk Aneja , Seema Kalonia , Ajay Kumar Kaushik , Sunil Maggu
Abstract- The majority of accidents that have been reported in our nation are the result of drivers becoming distracted or feeling sleepy. Major accidents are often the result of driver fatigue that often results in the driver becoming drowsy and falling asleep. Nevertheless, there are early signs of exhaustion that can be identified before a serious situation arises, therefore identifying and detecting driver fatigue remains a research problem. Most traditional tiredness detection techniques rely on behavioral characteristics; others require expensive sensors, and others are intrusive and could distract drivers. In this research, we have developed a Dlib model and Python Driver Drowsiness Detection System. This approach can lower the amount of traffic accidents, and it is also simple to adopt because it doesn't call for direct interaction between the driver and the vehicle. The system uses adaptive thres holding to determine the driver's level of tiredness and recognizes facial landmarks. It also computes the Eye Aspect Ratio (EAR). The suggested strategy has been put to the test using machine learning techniques.
