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.
|Data di pubblicazione:||2013|
|Titolo:||Recognizing Human Actions by using Effective Codebooks and Tracking|
|Autore/i:||Lamberto Ballan; Lorenzo Seidenari; Giuseppe Serra; Marco Bertini; and Alberto Del Bimbo|
|Titolo del libro:||Advanced Topics in Computer Vision|
|Citazione:||Recognizing Human Actions by using Effective Codebooks and Tracking / Lamberto Ballan; Lorenzo Seidenari; Giuseppe Serra; Marco Bertini; and Alberto Del Bimbo. - STAMPA. - (2013), pp. 65-93.|
File in questo prodotto:
I documenti presenti in Iris Unimore sono rilasciati con licenza Creative Commons Attribuzione - Non commerciale - Non opere derivate 3.0 Italia, salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris