Recognition and classification of human actions for annotation of unconstrained video sequences has proven to be challenging because of the variations in the environment, appearance of actors, modalities in which the same action is performed by different persons, speed and duration and points of view from which the event is observed. This variability reflects in the difficulty of defining effective descriptors and deriving appropriate and effective codebooks for action categorization. In this chapter, we present a novel and effective solution to classify human actions in unconstrained videos. In the formation of the codebook, we employ radius-based clustering with soft assignment in order to create a rich vocabulary that may account for the high variability of human actions. We show that our solution scores very good performance with no need of parameter tuning. We also show that a strong reduction of computation time can be obtained by applying codebook size reduction with Deep Belief Networks with little loss of accuracy.

Recognizing Human Actions by Using Effective Codebooks and Tracking / L. Ballan; L. Seidenari; G. Serra; M. Bertini; A. Del Bimbo. - STAMPA. - (2013), pp. 65-93. [10.1007/978-1-4471-5520-1_3]

Recognizing Human Actions by Using Effective Codebooks and Tracking

L. Ballan;L. Seidenari;G. Serra;M. Bertini;A. Del Bimbo
2013

Abstract

Recognition and classification of human actions for annotation of unconstrained video sequences has proven to be challenging because of the variations in the environment, appearance of actors, modalities in which the same action is performed by different persons, speed and duration and points of view from which the event is observed. This variability reflects in the difficulty of defining effective descriptors and deriving appropriate and effective codebooks for action categorization. In this chapter, we present a novel and effective solution to classify human actions in unconstrained videos. In the formation of the codebook, we employ radius-based clustering with soft assignment in order to create a rich vocabulary that may account for the high variability of human actions. We show that our solution scores very good performance with no need of parameter tuning. We also show that a strong reduction of computation time can be obtained by applying codebook size reduction with Deep Belief Networks with little loss of accuracy.
2013
9781447155195
Advanced Topics in Computer Vision
65
93
L. Ballan; L. Seidenari; G. Serra; M. Bertini; A. Del Bimbo
File in questo prodotto:
File Dimensione Formato  
icvss-book.pdf

Accesso chiuso

Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 11.38 MB
Formato Adobe PDF
11.38 MB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/821882
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? 1
social impact