Abstract | ||
---|---|---|
Motion estimation by means of spatio-temporal energy filters –velocity tuned filters– is known to be robust to noise and aliasing and to allow an easy treatment of the aperture problem. In this paper we propose a motion representation based on the composition of spatio-temporal energy features, i.e., responses of a set of filters in phase quadrature tuned to different scales and orientations. Complex motion patterns are identified by unsupervised cluster analysis of energy features. The integration criterion reflects the degree of alignment of maxima of the features's amplitude, which is related to phase congruence. The composite-feature representation has been applied to motion segmentation with a geodesic active model both for initialization and image potential definition. We will show that the resulting method is able to handle typical problems, such as partial and total occlusions, large inter-frame displacements, moving background and noise. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11864349_30 | ACIVS |
Keywords | Field | DocType |
energy feature,complex motion pattern,composite-feature representation,phase quadrature,motion estimation,aperture problem,motion representation,spatio-temporal composite-features,spatio-temporal energy filter,motion analysis,spatio-temporal energy feature,motion segmentation | Computer vision,Pattern recognition,Segmentation,Computer science,Image processing,Image segmentation,Aliasing,Artificial intelligence,Motion analysis,Initialization,Motion estimation,In-phase and quadrature components | Conference |
Volume | ISSN | ISBN |
4179 | 0302-9743 | 3-540-44630-3 |
Citations | PageRank | References |
0 | 0.34 | 15 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Raquel Dosil | 1 | 145 | 10.37 |
Xose Manuel Pardo | 2 | 126 | 13.25 |
Xosé R. Fdez-Vidal | 3 | 93 | 5.87 |
Antón García | 4 | 0 | 0.34 |