DriveCare: A Real-Time Vision Based Driver Drowsiness Detection Using Multiple Convolutional Neural Networks With Kernelized Correlation Filters (MCNN-KCF)

Driver Drowsiness is one of the most significant safety issues facing the road transport industry today, and it reduces vigilance, alertness, and concentration to perform the attention-based activities such as driving. When the driver is in a fatigue state, the facial expressions are a bit different from those in the normal state. Here a new system called DriveCare, which determines the drivers' fatigue state, like duration of eyes closure, blinking, and yawning, using video images, without equipping their bodies with any devices, is introduced. A novel face-tracking algorithm called Multiple Convolutional Neural Networks with Kernelized Correlation Filters (MCNN-KCF) is used to improve the tracking accuracy. Further, a detection method is used for extracting the facial features of the driver. Then with the help of these facial features, we evaluate the Driver's state. By combining the features extracted by the eyes and mouth, DriveCare can alert the driver using a drowsiness warning tone. Different experimental results showed that the DriveCare achieved around a 95% accuracy.