IJCV
2000
13 years 11 months ago
2000
We address the structure-from-motionproblem in the context of head modeling from video sequences for which calibration data is not available. This task is made challenging by the ...
IJCV
2000
13 years 11 months ago
2000
A new method for tracking contours of moving objects in clutter is presented. For a given object, a model of its contours is learned from training data in the form of a subset of c...
IJCV
2000
13 years 11 months ago
2000
We propose a Bayesian framework for representing and recognizing local image motion in terms of two basic models: translational motion and motion boundaries. Motion boundaries are ...
IJCV
2000
13 years 11 months ago
2000
Linear parameterized models of optical flow, particularly affine models, have become widespread in image motion analysis. The linear model coefficients are straightforward to estim...
IJCV
2000
13 years 11 months ago
2000
An overview is given of a novel vision system for locating, recognising and tracking multiple vehicles, using a single monocular camera mounted on a moving vehicle1 . 3D model-bas...
IJCV
2000
13 years 11 months ago
2000
In this paper we show that a classic optical ow technique by Nagel and Enkelmann (1986) can be regarded as an early anisotropic di usion method with a di usion tensor. We introduc...
IJCV
2000
13 years 11 months ago
2000
IJCV
2000
13 years 11 months ago
2000
In this paper we first overview the main concepts of Statistical Learning Theory, a framework in which learning from examples can be studied in a principled way. We then briefly di...
IJCV
2000
13 years 11 months ago
2000
Optical flow provides a constraint on the motion of a deformable model. We derive and solve a dynamic system incorporating flow as a hard constraint, producing a model-based least...