Human activity recognition is an important and active field of research having a wide range of application in numerous fields, including ambient assisted living. Although most of the researches are focused on the single user, the ability to recognize two-person interactions is perhaps more important for its social implications. This paper presents a two-person activity recognition system that uses skeleton data extracted from a depth camera. The human actions are encoded using a set of a few basic postures obtained with an unsupervised clustering approach. Multiclass Support Vector Machines (SVMs) are used to build models on the training set, while the X-means algorithm is employed to dynamically find the optimal number of clusters for each sample during the classification phase. The system is evaluated on the ISR-UoL and SBU datasets, reaching an overall accuracy of 0.87 and 0.88 respectively. Although the results show that the performances of the system are comparable with the state-of-the-art, recognition improvements are obtained with the activities related to health-care environments, showing promise for applications in the assisted-living realm.

Two-person Activity Recognition using Skeleton Data

MANZI, Alessandro;FIORINI, Laura;LIMOSANI, Raffaele;DARIO, Paolo;CAVALLO, Filippo
2018-01-01

Abstract

Human activity recognition is an important and active field of research having a wide range of application in numerous fields, including ambient assisted living. Although most of the researches are focused on the single user, the ability to recognize two-person interactions is perhaps more important for its social implications. This paper presents a two-person activity recognition system that uses skeleton data extracted from a depth camera. The human actions are encoded using a set of a few basic postures obtained with an unsupervised clustering approach. Multiclass Support Vector Machines (SVMs) are used to build models on the training set, while the X-means algorithm is employed to dynamically find the optimal number of clusters for each sample during the classification phase. The system is evaluated on the ISR-UoL and SBU datasets, reaching an overall accuracy of 0.87 and 0.88 respectively. Although the results show that the performances of the system are comparable with the state-of-the-art, recognition improvements are obtained with the activities related to health-care environments, showing promise for applications in the assisted-living realm.
2018
File in questo prodotto:
File Dimensione Formato  
IP032 - Two-person Activity Recognition.pdf

accesso aperto

Tipologia: Documento in Post-print/Accepted manuscript
Licenza: Dominio pubblico
Dimensione 3.2 MB
Formato Adobe PDF
3.2 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/11382/517185
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 31
social impact