For a driver monitoring system, one of the most important problems to solve is face detection rapidly. This paper presents an efficient approach to achieve fast and accurate face detection in gray level videos. Candidates of face at different scales are selected by finding regions based on Mask Transform (MT). To obtain real one, all the face candidates are then verified by using support vector machines (SVMs) based on Multi-scale 2D Walsh-Hadamard features. Head pose is estimated on the basis of accurate face detection. At last, we analyzed the head pose by a kind of Bilateral-projection Matrix Principle Component Analysis (BMPCA) algorithm proposed. Experimental results on many videos show that the algorithm can detect driver's face rapidly and estimate the head pose accurately. The proposed method is robust to deal with illumination changes, glasses wearing and different head pose with moderate rotations. Experimental results demonstrate its effectiveness.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.