Abstract | ||
---|---|---|
In this paper we integrate spatial and temporal information, which are extracted separately from a video sequence, for indexing and retrieval purposes. We focus on two filter families that are suitable models of the human visual system for spatial and temporal information encoding. They are special cases of polynomial transforms that perform local decompositions of a signal. Spatial primitives are extracted using Hermite filters, which agree with the Gaussian derivative model of receptive field profiles. Temporal events are characterized by Laguerre filters, which preserve the causality constraint in the temporal domain. Integration of both models gives a spatio-temporal feature extractor based on early vision.. Results encourage our model for video indexing and retrieval. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11590064_5 | VISUAL |
Keywords | Field | DocType |
temporal information encoding,temporal information,suitable model,retrieval purpose,video spatio-temporal signature,video indexing,spatial primitive,temporal event,video sequence,gaussian derivative model,temporal domain,human visual system,receptive field | Computer vision,Polynomial transformation,Polynomial,Pattern recognition,Human visual system model,Image retrieval,Image processing,Search engine indexing,Gabor filter,Artificial intelligence,Hermite interpolation,Mathematics | Conference |
Volume | ISSN | ISBN |
3736 | 0302-9743 | 3-540-30488-6 |
Citations | PageRank | References |
0 | 0.34 | 9 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Carlos Joel Rivero-Moreno | 1 | 2 | 1.40 |
Stéphane Bres | 2 | 127 | 14.42 |