In this work, a new approach to fully automatic color
image segmentation, called JSEG, is presented. First, colors
in the image are quantized to several representing
classes tha...
To navigate reliably in indoor environments, a mobile robot must know where it is. This includes both the ability of globally localizing the robot from scratch, as well as trackin...
Frank Dellaert, Wolfram Burgard, Dieter Fox, Sebas...
Facial variation divides into a number of functional subspaces. An improved method of measuring these was designed, within the space defined by an Appearance Model. Initial estima...
Nicholas Costen, Timothy F. Cootes, Gareth J. Edwa...
We are developing a system to extract geodetic, textured CAD models from thousands of initially uncontrolled, close-range ground and aerial images of urban scenes. Here we describ...
A parametric camera model and calibration procedures are developed for an outdoor active camera system with pan, tilt and zoom control. Unlike traditional methods, active camera m...
This paper addresses the problem of probabilistic recognition of activities from local spatio-temporal appearance. Joint statistics of space-time filters are employed to define hi...
We use the color cooccurrence histogram (CH) for recognizing objects in images. The color CH keeps track of the number of pairs of certain colored pixels that occur at certain sep...