This paper proposes to model an action as the output of a sequence of atomic Linear Time Invariant (LTI) systems. The sequence of LTI systems generating the action is modeled as a Markov chain, where a Hidden Markov Model (HMM) is used to model the transition from one atomic LTI system to another. In turn, the LTI systems are represented in terms of their Hankel matrices. For classification purposes, the parameters of a set of HMMs (one for each action class) are learned via a discriminative approach. This work proposes a novel method to learn the atomic LTI systems from training data, and analyzes in detail the action representation in terms of a sequence of Hankel matrices. Extensive evaluation of the proposed approach on two publicly available datasets demonstrates that the proposed method attains state-of-the-art accuracy in action classification from the 3D locations of body joints (skeleton).

Lo Presti, L., La Cascia, M., Sclaroff, S., Camps, O. (2015). Hankelet-based dynamical systems modeling for 3D action recognition. IMAGE AND VISION COMPUTING, 44, 29-43 [10.1016/j.imavis.2015.09.007].

Hankelet-based dynamical systems modeling for 3D action recognition

LO PRESTI, Liliana
;
LA CASCIA, Marco;
2015-01-01

Abstract

This paper proposes to model an action as the output of a sequence of atomic Linear Time Invariant (LTI) systems. The sequence of LTI systems generating the action is modeled as a Markov chain, where a Hidden Markov Model (HMM) is used to model the transition from one atomic LTI system to another. In turn, the LTI systems are represented in terms of their Hankel matrices. For classification purposes, the parameters of a set of HMMs (one for each action class) are learned via a discriminative approach. This work proposes a novel method to learn the atomic LTI systems from training data, and analyzes in detail the action representation in terms of a sequence of Hankel matrices. Extensive evaluation of the proposed approach on two publicly available datasets demonstrates that the proposed method attains state-of-the-art accuracy in action classification from the 3D locations of body joints (skeleton).
Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioni
Lo Presti, L., La Cascia, M., Sclaroff, S., Camps, O. (2015). Hankelet-based dynamical systems modeling for 3D action recognition. IMAGE AND VISION COMPUTING, 44, 29-43 [10.1016/j.imavis.2015.09.007].
File in questo prodotto:
File Dimensione Formato  
IMAVIS3436.pdf

Solo gestori archvio

Descrizione: Articolo principale
Tipologia: Versione Editoriale
Dimensione 4.45 MB
Formato Adobe PDF
4.45 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
S0262885615001134.pdf

accesso aperto

Tipologia: Pre-print
Dimensione 1.64 MB
Formato Adobe PDF
1.64 MB Adobe PDF Visualizza/Apri

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

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10447/153971
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 24
  • ???jsp.display-item.citation.isi??? 20
social impact