Real Time Eye Tracking for Human Computer Interaction
The ideal human-computer interaction system should function robustly with as few constraints as those found in human-to-human interaction. One of the most effective means of interaction is through the behavior of the eye. Specifically, knowledge of the viewing direction and thus the area of regard offers insight into the user's intention and mental focus, and consequently this information is vital for the next generation of user interfaces. The present technology enables the ability to capture the direction the eyes point in while the subject is a distance away from the camera. This offers the potential for intuitive human-computer interfaces, allowing for a greater interactivity, more intelligent behavior, and increased flexibility. A two-camera system is provided that detects the face from a fixed, wide-angle camera, estimates a rough location for the eye region using an eye detector based on topographic features, and directs another active pan-tilt-zoom camera to focus in on this eye region. Additionally, an eye gaze estimation approach is provided for point-of-regard (PoG) tracking on a large viewing screen. To allow for greater head pose freedom, a calibration approach facilitates finding the 3D eyeball location, eyeball radius, and fovea position. Moreover, both the iris center and iris contour points are mapped to the eyeball sphere (creating a 3D iris disk) to get the optical axis; the fovea is then rotated accordingly, and the final, visual axis gaze direction computed. This gaze estimation approach may be integrated into a two-camera system, permitting natural, non-intrusive, pose-invariant point of gaze (PoG) estimation in distance, and allowing user translational freedom without resorting to infrared or complex hardware setups such as stereo-cameras or “smart rooms.”
- Real time robust tracking of hand using two orthogonal cameras without any intrusive glove or marks.
- Accurate pointing in a cursor resolution.
- Intuitive drawing in a 3D place.
- Feasible for finger pointing in a long distance.
U.S. 8,885,882 & 9,311,527
Binghamton University RB368