This paper describes the continuing development of a system for tracking multiple man made objects, (typically vehicles) moving in a natural open world scene, where the detected m...
A system is described that tracks moving objects in a video dataset so as to extract a representation of the objects' 3D trajectories. The system then finds hierarchical clus...
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 ...
We present a method for efficiently tracking objects represented as constellations of parts by integrating out the shape of the model. Parts-based models have been successfully ap...
Change detection by background subtraction is a common approach to detect moving foreground. The resulting difference image is usually thresholded to obtain objects based on pixel ...