New trends in exploration and visualization are highly demanded in dealing with the massive amount of collected Earth Observation (EO) data. In this work, we propose an immersive visual analytic of EO data utilizing Virtual Reality technology. Precisely, we introduce the visualization of large scale SAR images in an immersive 3D environment and also introduce an interactive learning algorithm f...

Important perceptual judgments are often made by combining the opinions of several individuals to make a collective decision, such as when teams of physicians make diagnoses based on medical images. Although group-level decisions are generally superior to the decisions made by individuals, it remains unclear whether collective decision making is most effective when information is redundantly pr...

We address the problem of observing a moving agent. In particular, we propose a system for observing a manipulation process, where a robot hand manipulates an object. A discrete event dynamic systems (DEDS) frame work is developed for the hand/object interaction over time and a stabilizing observer is constructed. Low-level modules are developed for recognizing the "events" that causes state tr...

In this paper, the accuracy of visual tracking is enhanced by leveraging a novel measure for observation quality. We measure observation quality with mutual information, then look at the interval covered by that mutual information. As observation uncertainty the interval length is proposed. The best observation is considered the one that both maximizes the observation quality and minimizes the ...