In this work we address the problem of analyzing video sequences and of representing meaningful space-time points of interest by using the 3D shearlet transform. We introduce a local representation based on shearlet coe cients of the video, regarded as 2D+T signal. This representation turns out to be informative to understand the local spatio-temporal characteristics, which can be easily detected by an unsupervised clustering algorithm.
Local Spatio-Temporal Representation Using the 3D Shearlet Transform (STSIP)
D. Malafronte;E. De Vito;F. Odone
2017-01-01
Abstract
In this work we address the problem of analyzing video sequences and of representing meaningful space-time points of interest by using the 3D shearlet transform. We introduce a local representation based on shearlet coe cients of the video, regarded as 2D+T signal. This representation turns out to be informative to understand the local spatio-temporal characteristics, which can be easily detected by an unsupervised clustering algorithm.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
Local Spatio-Temporal Representation using the 3D Shearlet Transform(STSTIP).pdf
accesso aperto
Tipologia:
Documento in Pre-print
Dimensione
2.03 MB
Formato
Adobe PDF
|
2.03 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
