In a known environment, objects may be tracked in multiple views using a set of background models. Stereo-based models can be illumination-invariant, but often have undefined valu...
Trevor Darrell, David Demirdjian, Neal Checka, Ped...
Abstract. Background subtraction is a method typically used to segment moving regions in image sequences taken from a static camera by comparing each new frame to a model of the sc...
This paper presents methodology for integrating a small, singlepoint laser range finder into a wearable augmented reality system. We first present a way of creating object-align...
Jason Wither, Christopher Coffin, Jonathan Ventura...
This paper presents a new approach for video clip retrieval based on Earth Mover’s Distance (EMD). Instead of imposing one-to-one matching constraint as in [11, 14], our approach...
Computer vision tasks often require the robust fit of a model to some data. In a robust fit, two major steps should be taken: i) robustly estimate the parameters of a model, and ii...