In this paper we propose a new method for human action categorization by using an effective combination of a new 3D gradient descriptor with an optic flow descriptor, to represent spatio-temporal interest points. These points are used to represent video sequences using a bag of spatio-temporal visual words, following the successful results achieved in object and scene classification. We extensively test our approach on the standard KTH and Weizmann actions datasets, showing its validity and good performance. Experimental results outperform state-of-the-art methods, without requiring fine parameter tuning.
Recognizing Human Actions by Fusing Spatio-temporal Appearance and Motion Descriptors / Lamberto Ballan;Marco Bertini;Alberto Del Bimbo;Lorenzo Seidenari;Giuseppe Serra. - ELETTRONICO. - (2009), pp. 3569-3572. (Intervento presentato al convegno IEEE International Conference on Image Processing (ICIP) tenutosi a Cairo, Egypt nel November 7-12) [10.1109/ICIP.2009.5414332].
Recognizing Human Actions by Fusing Spatio-temporal Appearance and Motion Descriptors
Lamberto Ballan;Marco Bertini;Alberto Del Bimbo;Lorenzo Seidenari;Giuseppe Serra
2009
Abstract
In this paper we propose a new method for human action categorization by using an effective combination of a new 3D gradient descriptor with an optic flow descriptor, to represent spatio-temporal interest points. These points are used to represent video sequences using a bag of spatio-temporal visual words, following the successful results achieved in object and scene classification. We extensively test our approach on the standard KTH and Weizmann actions datasets, showing its validity and good performance. Experimental results outperform state-of-the-art methods, without requiring fine parameter tuning.File | Dimensione | Formato | |
---|---|---|---|
05414332.pdf
Accesso chiuso
Tipologia:
Pdf editoriale (Version of record)
Licenza:
Tutti i diritti riservati
Dimensione
592.17 kB
Formato
Adobe PDF
|
592.17 kB | Adobe PDF | Richiedi una copia |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.