Learn More
Everyday tasks often require us to keep track of multiple objects in dynamic scenes. Past studies show that tracking becomes more difficult as objects move faster. In the present study, we show that this trade-off may not be due to increased speed itself but may, instead, be due to the increased crowding that usually accompanies increases in speed. Here, we(More)
Hand motion capturing is one of the most important parts of gesture interfaces. Many current approaches to this task generally involve a formidable nonlinear optimization problem in a large search space. Motion capturing can be achieved more cost-efficiently when considering the motion constraints of a hand. Although some constraints can be represented as(More)
Multibody structure from motion could be solved by the factorization approach. However, the noise measurements would make the segmentation daficult when analyzing the shape interaction matrix. This paper presents an orthogonal subspace decomposition and grouping technique t o approach such a problem. W e decompose the object shape spaces into signal(More)
Tracking the articulated hand motion in a video sequence is a challenging problem in which the main difficulty arises from the complexity of searching for an optimal motion estimate in a high dimensional configuration space induced by the articulated motion. Considering that the complexities of this problem may be reduced by learning the lower dimensional(More)
The emergence of new display and computing technologies have brought attention to new paradigms of human-computer interactions that are fundamentally different from using traditional mechanical input devices. Communication through visual gesture interface is a potential alternative that could provide multidimensional interactions. Though rich information is(More)
  • 1