Video-based recognition and prediction of a temporally extended activity can benefit from a detailed description of high-level expectations about the activity. Stochastic grammars...
Background subtraction is the first step of many video surveillance applications. What is considered background varies by application, and may include regular, systematic, or comp...
Robert Pless, John Larson, Scott Siebers, Ben West...
The biological visual system possesses the ability to compute layered surface representations, in which one surface is represented as being viewed through another. This ability is...
During tracking, lens zoom acts as a gain between scene dynamics and fixation errors, providing a trade-off between maximising resolution and minimising tracking error. Using a li...
Object detection with a learned classifier has been applied successfully to difficult tasks such as detecting faces and pedestrians. Systems using this approach usually learn the ...