In this paper we propose a novel approach for gesture modeling. We aim at decomposing a gesture into sub-trajectories that are the output of a sequence of atomic linear time invariant (LTI) systems, and we use a Hidden Markov Model to model the transitions from the LTI system to another. For this purpose, we represent the human body motion in a temporal window as a set of body joint trajectories that we assume are the output of an LTI system. We describe the set of trajectories in a temporal window by the corresponding Hankel matrix (Hanklet), which embeds the observability matrix of the LTI system that produced it. We train a set of HMMs (one for each gesture class) with a discriminative approach. To account for the sharing of body motion templates we allow the HMMs to share the same state space. We demonstrate by means of experiments on two publicly available datasets that, even with just considering the trajectories of the 3D joints, our method achieves state-of-the-art accuracy while competing well with methods that employ more complex models and feature representations.

Lo Presti, L., La Cascia, M., Sclaroff, S., Camps, O. (2015). Gesture Modeling by Hanklet-based Hidden Markov Model. In Springer Lecture Notes in Computer Science (LNCS) [10.1007/978-3-319-16811-1_35].

Gesture Modeling by Hanklet-based Hidden Markov Model

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

Abstract

In this paper we propose a novel approach for gesture modeling. We aim at decomposing a gesture into sub-trajectories that are the output of a sequence of atomic linear time invariant (LTI) systems, and we use a Hidden Markov Model to model the transitions from the LTI system to another. For this purpose, we represent the human body motion in a temporal window as a set of body joint trajectories that we assume are the output of an LTI system. We describe the set of trajectories in a temporal window by the corresponding Hankel matrix (Hanklet), which embeds the observability matrix of the LTI system that produced it. We train a set of HMMs (one for each gesture class) with a discriminative approach. To account for the sharing of body motion templates we allow the HMMs to share the same state space. We demonstrate by means of experiments on two publicly available datasets that, even with just considering the trajectories of the 3D joints, our method achieves state-of-the-art accuracy while competing well with methods that employ more complex models and feature representations.
nov-2014
Asian Conference on Computer Vision (ACCV 2014)
Singapore
2015
17
Online
http://www.dicgim.unipa.it/~cvip/pdf/ACCV2014.pdf
Lo Presti, L., La Cascia, M., Sclaroff, S., Camps, O. (2015). Gesture Modeling by Hanklet-based Hidden Markov Model. In Springer Lecture Notes in Computer Science (LNCS) [10.1007/978-3-319-16811-1_35].
Proceedings (atti dei congressi)
Lo Presti, L; La Cascia, M; Sclaroff, S; Camps, O
File in questo prodotto:
File Dimensione Formato  
ACCV_2014.pdf

Solo gestori archvio

Descrizione: Articolo principale
Dimensione 4.15 MB
Formato Adobe PDF
4.15 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/10447/128000
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 29
  • ???jsp.display-item.citation.isi??? 15
social impact