Existing methods for evaluating the performance of head trackers usually rely on publicly available face databases, which contain facial images and the ground truths of their corresponding head orientations. However, most of the existing publicly available face databases are constructed by assuming that a frontal head orientation can be determined by compelling the person under examination to look straight ahead at the camera on the first video frame. Since nobody can accurately direct one’s head toward the camera, this assumption may be unrealistic. Rather than obtaining estimation errors, we present a method for computing the covariance of estimation error rotations to evaluate the reliability of head trackers. As an uncertainty measure of estimators, the Schatten 2-norm of a square root of error covariance (or the algebraic average of relative error angles) can be used. The merit of the proposed method is that it does not disturb the person under examination by asking him to direct his head toward certain directions. Experimental results using real data validate the usefulness of our method.
Existing methods for tracking three-dimensional (3-D) eye positions with a monocular color camera mostly rely on a generic 3-D face model and a certain face database. However, the performance of these methods is susceptible to the variations of head poses. For this reason, existing methods for estimating 3-D eye position from a single two-dimensional face image may yield erroneous results. To improve the accuracy of 3-D eye position trackers using a monocular camera, we present a compensation method as a postprocessing technique. We address the problem of determining an optimal registration function for fitting 3-D data consisting of the inaccurate estimates from the eye position tracker and their corresponding ground truths. To obtain the ground truths of 3-D eye positions, we propose two different systems by combining an optical motion capture system and checkerboards, which construct the form of the hand-eye and robot-world calibration. By solving a least-squares optimization problem, we can determine the optimal registration function in an affine form. Real experiments demonstrate that the proposed method can considerably improve the accuracy of 3-D eye position trackers using a single color camera.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.