No abstract

Automatic eye detection and tracking is an important component for advanced human-computer interface design. Accurate eye localization can help develop a successful system for face recognition and emotion identification. In this article, we propose a novel approach to detect and track eyes using geometric surface features on topographic manifold of eye images. First, in the joint spatial-intensity domain, a facial image is treated as a 3D terrain surface or image topographic manifold. In particular, eye regions exhibit certain intrinsic geometric traits on this topographic manifold, namely, the pit -labeled center and hillside -like surround regions. Applying a terrain classification procedure on the topographic manifold of facial images, each location of the manifold can be labeled to generate a terrain map. We use the distribution of terrain labels to represent the eye terrain pattern. The Bhattacharyya affinity is employed to measure the distribution similarity between two topographic manifolds. Based on the Bhattacharyya kernel, a support vector machine is applied for selecting proper eye pairs from the pit-labeled candidates. Second, given detected eyes on the first frame of a video sequence, a mutual-information-based fitting function is defined to describe the similarity between two terrain surfaces of neighboring frames. By optimizing the fitting function, eye locations are updated for subsequent frames. The distinction of the proposed approach lies in that both eye detection and eye tracking are performed on the derived topographic manifold, rather than on an original-intensity image domain. The robustness of the approach is demonstrated under various imaging conditions and with different facial appearances, using both static images and video sequences without background constraints.

No abstract

The coupling of Java3D and applet technologies has the potential to revolutionize web-based simulation visualization.Applets can enable the dynamic and distributed instantiation and elimination of viewers that until now was not possible. A visualizer based on these technologies is under development at the Air Force Research Laboratory's Information Directorate. Unlike existing visualizers that must be running at the simulation's start time, this tool allows users to come and go as they please -effectively allowing one to peer into the state of a simulation at a place, perspective, and time that is of specific interest to them.Intense 3D graphics have been difficult to program and distribute among heterogeneous environments until the inception of Java3D. Sun Microsystems' Java3D provides users the best acceleration their platform can support while the WWW provides the transmission and communication infrastructure. This paper discusses a government owned, browser-based simulation visualizer capable of displaying simulated entities to any number of distributed sites.

No abstract