Two-dimensional image motion is the projection of the three-dimensional motion of objects,
relative to a visual sensor, onto its image plane. Sequences of time-orderedimages allow the …

A new scintillator-based fast ion loss detector has been installed on DIII-D with the time
response (> 100 kHz) needed to study energetic ion losses induced by Alfvén eigenmodes …

Optical flow estimation is one of the oldest and still most active research domains in
computer vision. In 35 years, many methodological concepts have been introduced and …

This paper describes a method to estimate parametric motion models. Motivations for the
use of such models are, on one hand, their efficiency, which has been demonstrated in …

Seeded region growing (SRG) algorithm is very attractive for semantic image segmentation
by involving high-level knowledge of image components in the seed selection procedure …

We present a new approach to the recovering of dipole magnitudes in a distributed source
model for magnetoencephalographic (MEG) and electroencephalographic (EEG) imaging …

We address the issue of recovering and segmenting the apparent velocity field in sequences
of images. As for motion estimation, we minimize an objective function involving two robust …

This paper describes procedures for obtaining a reliable and dense optical flow from image
sequences taken by a TV camera mounted on a car moving in usual outdoor scenarios. By …

The task of multicamera surveillance is to reconstruct the paths taken by all moving objects
that are temporally visible from multiple non-overlap** cameras. We present a Bayesian …

ASSET-2: real-time motion segmentation and shape tracking Page 1 814 IEEE TRANSACTIONS
ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 17 NO. 8, AUGUST 1995 VI …