Drowsiness Detection for Drivers Using Computer Vision

Drowsiness detection system is regarded as an effective tool to reduce the number of road accidents. This project proposes a non-intrusive approach for detecting drowsiness in drivers, using Computer Vision. The algorithm is coded on OpenCV platform in Linux environment. The parameters considered to detect drowsiness are face and eye detection, blinking, eye closure and gaze. Input is captured and live fed from a camera that supports night vision as well. The algorithm is Haar trained to detect the face and the eye from the incoming frame. Once the eye is detected, further coding is done to track the eye and automatically set a dynamic threshold value. Depending on the values obtained from each of the incoming frames and deviations from the threshold values, eyelid closure/blink/gaze is detected. Warning system is designed to alert the driver. This system renders an efficient solution to road accidents and the cost of developing it into a real time system is also feasible when compared to the cost involved in the manufacture of car. Key-Words: OpenCV, Linux, Haar Classifiers