This paper presents a novel approach for labeling objects based on multiple spatially-registered images of a scene. We argue that such a multi-view labeling approach is a better fi...
Scott Helmer, David Meger, Marius Muja, James J. L...
Studies support the need for high resolution imagery to identify persons in surveillance videos[13]. However, the use of telephoto lenses sacrifices a wider field of view and ther...
Many computer vision algorithms such as object tracking and event detection assume that a background model of the scene under analysis is known. However, in many practical circums...
We believe intelligence does not dwell solely in brain but emerges from active interactions with environments through perception, action, and communication. This paper give an over...
The visual surveillance task is to monitor the activity of objects in a scene. In far-field settings (i.e., wide outdoor areas), the majority of visible activities are objects movi...