Abstract—Driver in-alertness is an important cause for most accidents related to vehicle crashes. Drowsy driver detection methods can form the basis of a system to potentially reduce accidents related to driver doziness. Intel-Eye describes a real-time online driver in-alertness and shock related facial expression monitoring methods. Intel -Eye obtains visual cues such as eyelid movement; gaze movement, head movement, and facial expression that typically characterize the level of alertness of a person are extracted in real time and systematically combined to infer the fatigue level of the driver. Intel-eye distinguishes itself by the Two-Way Approach in eye gaze analysis. Shock analysis is done to identify the driver’s expression during a head on collision and signals are sent for automatic braking system. A probabilistic model is developed to model in Intel-Eye and it's used for predicting human in-alertness based on the visual cues obtained. The simultaneous use of multiple visual cues and their systematic combination yields a much more robust and accurate fatigue and shock characterization than using a single visual cue. Percent eye closure (PERCLOS) [1] is also determined. Intel-Eye system is efficient under real-life fatigue conditions i.e. human subjects with/without glasses under different illumination conditions. Intel-Eye uses the two way approach when compared to other existing systems, it’s main advantage is to analyse the shock expression and send signals to deviate the behind vehicles and avoid the collision directly by shifting movement. It is deemed to be reasonably robust, trustworthy, and precise in fatigue and shock characterization, detection and warning.

Index Terms—Image processing, probabilistic model, shock analysis, PERCLOS.

B. Bhavya and R. Alice Josephine are with the Department of Information Technology B.Tech IT, Final year, Sri SaiRam Engineering College Chennai,India (e-mail: bhavyasri42@gmail.com).

Cite: B. Bhavya and R. Alice Josephine, "Intel-Eye: An Innovative System for Accident Detection, Warning and Prevention Using Image Processing(A Two– Way Approach in Eye Gaze Analysis)," International Journal of Computer and Communication Engineering vol. 2, no. 2, pp. 189-193 , 2013.