Driver Drowsiness Detection Using DLIB

The main two reasons for vehicle accidents are Drowsiness and fatigue. They can be avoided by getting adequate sleep before driving, drinking coffee or an energy drink before driving, or taking a break when the indicators of tiredness appear. Complex methods, such as EEG and ECG, are used in the popular drowsiness detection approach. This method offers a high level of measurement accuracy, but it requires touch measurement and has a number of drawbacks when it comes to driver's dizziness monitoring. As a result, it is inconvenient to utilize in real-time driving. The developed system is responsible for detecting the facial area of a video image. The face region is used to narrow down the monitoring of mouth and eyes inside the face area. After the face has been discovered, a dotted map of mouth and eyes is developed by constructing eye by detection of both left and right eye as well as mouth detection. Within the face image, the parameters for detecting both mouth and eyes are created. This project is based on research and falls under the field of Machine Learning to build a system for detecting driver drowsiness in order to reduce accidents caused when driver loses conciseness from sleepiness. The report included the findings and recommendations for the project's limited execution of the various strategies. The project's implementation, on the other hand, provides a practical understanding of how the system works and what changes can be made to improve the overall system's efficiency.