On board monitoring of the alertness level of an automotive driver has been achallenging research in transportation safety and management. In this paper, wepropose a robust real time embedded platform to monitor the loss of attentionof the driver during day as well as night driving conditions. The PERcentage ofeye CLOSure (PERCLOS) has been used as the indicator of the alertness level. Inthis approach, the face is detected using Haar like features and tracked usinga Kalman Filter. The Eyes are detected using Principal Component Analysis (PCA)during day time and the block Local Binary Pattern (LBP) features during night.Finally the eye state is classified as open or closed using Support VectorMachines(SVM). In plane and off plane rotations of the drivers face have beencompensated using Affine and Perspective Transformation respectively.Compensation in illumination variation is carried out using Bi HistogramEqualization (BHE). The algorithm has been cross validated using brain signalsand finally been implemented on a Single Board Computer (SBC) having Intel Atomprocessor, 1 GB RAM, 1.66 GHz clock, x86 architecture, Windows Embedded XPoperating system. The system is found to be robust under actual drivingconditions.
展开▼
