We present a data-driven, unsupervised method for unusual
scene detection from static webcams. Such time-lapse
data is usually captured with very low or varying framerate.
This ...
Michael D. Breitenstein, Helmut Grabner, Luc Van G...
The demand for realistic human characters is driven by interactive application developers worldwide. The look of 3D models in real time graphics is efficiently improved by powerfu...
Florian Struck, Christian-A. Bohn, Sebastian Schmi...
We propose a method for create a background model in non-stationary scenes. Each pixel has a dynamic Gaussian mixture model. Our approach can automatically change the number of Ga...
We present an approach to visual tracking based on dividing a
target into multiple regions, or fragments. The target is represented
by a Gaussian mixture model in a joint feature...
The detection and tracking of three-dimensional human body models has progressed rapidly but successful approaches typically rely on accurate foreground silhouettes obtained using...