View Algorithm

Estimation - Ground Truth: 3.35
Estimation - Ground Truth Aligned: 1.62
Valid frames (%): 100.00
Authors: Mikel Ariz, José J. Bengoechea, Arantxa Villanueva and Rafael Cabeza
Filiation: UPNA
Link to group/authors:
Algorithm name: Posit + AAM 2D + BFM Model
Reference if published: Not Specified
Development platform: MatLab
Execution time (indicating execution platform):6,38 s
Memory requisites: Not Specified
Training requisites: Not Specified
Link to source: Not Specified
Abstract (5000 chars): This paper presents a new public database of videos for head tracking and pose estimation. Position data has been recorded with a magnetic sensor-transmitter that has previously been aligned and synchronized with a commercial webcam, and we provide reliable ground-truth for 3D rotation and translation of the head with respect to the camera. In addition to this, an automatic face annotation procedure has been developed, which provides the image position of 54 facial landmarks, with negligible error, in every video frame in the database. This image ground-truth can be used for training purposes or head tracking evaluation, among others. In order to show the usability of the database, in this paper we evaluate three head tracking approaches (two widespread methods plus the image ground-truth) and three head models (two widespread models plus each user’s real model), and combine them to provide nine different head pose estimation sets of results (plus three head tracking sets of results). These results show the validity of the presented database both for training and evaluation of head tracking and pose estimation methods, and provide an interesting comparison in performance. We hope that these results may also serve as reference to encourage other researchers to train and test their algorithms with this database, and compare their results with the ones presented in this paper.