Authors: Nawal Alioua; Aouatif Amine; Abdelaziz Bensrhair; Mohammed Rziza
Addresses: LRIT, Associated Unit to CNRST N. 29, Faculty of Science, University of Mohammed V-Agdal, Rabat, Morocco; LITIS, INSA-Rouen, Saint-Étienne-du-Rouvray, France ' LGS, ENSA-Kenitra, Ibn Tofail University, Morocco ' LITIS, INSA-Rouen, Saint-Étienne-du-Rouvray, France ' LRIT, Associated Unit to CNRST N. 29, Faculty of Science, University of Mohammed V-Agdal, Rabat, Morocco
Abstract: In this paper, we propose a driver head pose estimator based on steerable pyramid transform and probabilistic learning. The steerable pyramid is used to construct a head appearance template for each considered head orientation. Then, we learn the parameters of likelihood function from a training set with a probabilistic approach. To estimate the pose of a new head image, we first apply the steerable pyramid to extract its feature vector and then the maximal value of the likelihood function computed between this vector and all pose templates are retained. We perform several tests on public Pointing '04 database to optimise the parameters of steerable pyramid, which allows to make a compromise between the accuracy and processing time. Then, we apply the optimised head pose estimator on real video sequence representing a driver in diverse attention levels. We demonstrated that our system performs a good detection of driver inattention level.
Keywords: head pose estimation; driver assistance systems; active safety; driver inattention; steerable pyramid transform; probabilistic learning; image analysis; computer vision; face analysis; head orientation; feature extraction; driver attention; video sequences.
International Journal of Computational Vision and Robotics, 2015 Vol.5 No.4, pp.347 - 364
Received: 21 Mar 2014
Accepted: 03 Oct 2014
Published online: 03 Oct 2015 *