Fatigue Detection using Artificial Intelligence to Prevent Accident
Each year many people lose their lives due to road accidents around the world. Major accidents are due to drowsy driving. Fatigue and micro sleep of the driver are often the root cause of serious accidents. However, initial signs of tiredness can be detected before a critical situation arises. The method used to detect drowsiness are based on behavioral aspects while some are intrusive and may distract drivers, while some require expensive sensors. Therefore, in this paper, light-weight, real-time driver’s drowsiness detection system is developed and implemented on raspberry pi. The system capture the live video and detects driver’s face in every frame by employing image processing techniques. The system is able to detect facial landmarks, computes Eye Aspect Ratio (EAR) and Eye Closure Ratio (ECR) to detect driver’s drowsiness based on adaptive thresholding. Machine learning algorithms have been used for better approach.
Keywords: Drowsiness detection, Facial Landmark Detection, EAR (Eye Aspect Ratio), ECR (Eye Closure Ratio), Fatigue Detection, Non-Intrusive Methods, Driver monitoring system.
Cite this Article: S.Kiruthiga, S. Sharukhan, R. Mugunthan, B. Mukesh Kumar. Fatigue Detection using Artificial Intelligence to Prevent Accident. Journal of Image Processing & Pattern Recognition Progress. 2020; 7(2): 1–6p.
- There are currently no refbacks.