Abstract: A Real-Time accident prevention system has been proposed in which the drowsy condition of the driver can be detected and appropriate action will be performed for each condition automatically. There are different ways to detect drowsiness one of them are using camera that points directly towards the driver’s face and monitors the driver’s eyes in order to detect fatigue. We have developed a drowsy driver detection system using Brain Computer Interface ,the system deals with EEG Signal obtained from the brain ,when rhythms are plotted on PC we can see the fluctuations of rhythms when subject is falling to drowsy or deep sleep in accordance with a appropriate voltage under normal condition and drowsy condition are read on software application, using these voltage under two states we have developed a warning tone for drowsy driver.