In order to describe the 2D silhouette data we define a 2D model consisting of conic fields. The resulting likelihood distribution is differentiable w.r.t. the ...

In order to describe the 2D silhouette data we define a 2D model consisting of conic fields. The resulting likelihood distribution is differentiable w.r.t. the ...

In order to describe the 2D silhouette data we define a 2D model consisting of conic fields. The resulting likelihood distribution is differentiable w.r.t. the ...

Bibliographic details on Gradient-Based Hand Tracking Using Silhouette Data.

We present a gradient-based motion capture system that robustly tracks a human hand, based on abstracted visual information - silhouettes.

We present a gradient-based motion capture system that robustly tracks a human hand, based on abstracted visual information — silhouettes.

We present a gradient-based motion capture system that robustly tracks a human hand, based on abstracted visual information - silhouettes.

We propose a hybrid method that combines gradient based and stochastic optimization methods to achieve fast conver- gence and good accuracy. We present new ...

TL;DR: The algorithm for hand detection from human silhouette for video surveillance application is described, which calculates the Euclidean distance ...

This method has been applied to track articulated objects, including hands and multiple objects with motion constraints. An alternative method is that based on ...