Road accidents happen frequently, and the main cause for this is driver’s carelessness. This carelessness occurs due to driver inattention or driver drowsiness. Detection of this driver’s carelessness and alerting the driver at right time is the main concern so as to reduce traffic accidents. In this paper, a robust method is presented based on eyes state analysis in real time which works well for noisy images as well. The main aim is to detect drowsiness or distraction of driver while driving during day as well as at night and alert the driver by issuing a warning signal. Firstly, real-time video acquisition starts by initializing the camera. Then, the eye detection is done by using Viola–Jones algorithm. Lastly, iris detection is done by using circular Hough transform technique for checking the eyes state. The proposed method has shown an accuracy of 99% during daytime and an accuracy of 96% during nighttime and 91% accuracy for noisy frames.
CITATION STYLE
Verma, S., Girdhar, A., & Jha, R. R. K. (2018). Real-time eye detection method for driver assistance system. In Advances in Intelligent Systems and Computing (Vol. 696, pp. 693–702). Springer Verlag. https://doi.org/10.1007/978-981-10-7386-1_58
Mendeley helps you to discover research relevant for your work.