An algorithm for real-time stereo vision implementation of head pose and gaze direction measurement

Abstract

To build smart human interfaces, it is necessary for a system to know a user's intention and point of attention. Since the motion of a person's head pose and gaze direction are deeply related with his/her intention and attention, detection of such information can be utilized to build natural and intuitive interfaces.In this paper, we describe our real-time stereo face tracking and gaze detection system to measure head pose and gaze direction simultaneously. The key aspect of our system is the use of real-time stereo vision together with a simple algorithm which is suitable for real-time processing. Since the 3D coordinates of the features on a face can be directly measured in our system, we can significantly simplify the algorithm for 3D model fitting to obtain the full 3D pose of the head compared with conventional systems that use monocular camera. Consequently we achieved a non-contact, passive, real-time, robust, accurate and compact measurement system for head pose and gaze direction.

Detecting and tracking of 3D face pose for human-robot interaction

“…Feature-based approaches refer to the extraction of salient facial characteristics (eyes, nose, mouth) which are used to compute the face pose based on their spatial relations. In the past, many feature-based approaches have been proposed (e.g, [3], [4], [5], [6]). …”

Eye gaze estimation from a single image of one eye

“…The techniques include ElectroOculography [8], Limbus, Pupil and Eyelid tracking [11,7,17], Contact Lens Method, Corneal and Pupil Reflection Relationship [7], Purkinje Image Tracking [2], Artificial Neural Networks [17], Morphable Models [14] and geometry [6,10,12].…”

“…In most existing approaches [20,3,10,9], the iris contours on the image plane are simplified to be circles, so the felicitous circular geometry is utilized and iris outer boundaries (limbus) are detected using a circle edge operator. For instance, the center of the iris is detected using the circular Hough Transform in [10].…”

“…For instance, the center of the iris is detected using the circular Hough Transform in [10]. In [9], the iris is located by matching the left and right curvatures of the iris (circle) candidate with those of the iris to be detected in the edge image.…”

Active gaze tracking for human-robot interaction

“…In contrast to using fixed camera configuration [6,7,12], active vision allows the user to move around the robot's workspace without losing track of the person's eye gaze. Furthermore, since gaze is measured by finding the user's irises and facial features (e.g.…”