A Multimodal People Recognition System for an Intelligent Environment

Rosario Sorbello, Salvatore M. Anzalone, Enrico Pagello, Emanuele Menegatti, Yuichiro Yoshikawa, Hiroshi Ishiguro

Risultato della ricerca: Chapter

1 Citazione (Scopus)

Abstract

In this paper, a multimodal system for recognizing people in intelligent environments is presented. Users are identified and tracked by detecting and recognizing voices and faces through cameras and microphones spread around the environment. This multimodal approach has been chosen to develop a flexible and cheap though reliable system, implemented through consumer electronics. Voice features are extracted through a short time spectrum analysis, while face features are extracted using the eigenfaces technique. The recognition task is achieved through the use of some Support Vector Machines, one per modality, that learn and classify the features of each person, while bindings between modalities are also learnt through a cross-anchoring learning rule based on the mutual exclusivity selection principle. The system has been developed using NMM, a middleware software capable of splitting the sensors processing in several software nodes, making the system scalable in the number of cameras and microphones
Lingua originaleEnglish
Titolo della pubblicazione ospiteAI*IA 2011: Artificial Intelligence Around Man and Beyond
Pagine451-456
Numero di pagine6
Volume2011
Stato di pubblicazionePublished - 2011

Serie di pubblicazioni

NomeLECTURE NOTES IN COMPUTER SCIENCE

Fingerprint

Cameras
Consumer electronics
Microphones
Middleware
Spectrum analysis
Support vector machines
Computer systems

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cita questo

Sorbello, R., Anzalone, S. M., Pagello, E., Menegatti, E., Yoshikawa, Y., & Ishiguro, H. (2011). A Multimodal People Recognition System for an Intelligent Environment. In AI*IA 2011: Artificial Intelligence Around Man and Beyond (Vol. 2011, pagg. 451-456). (LECTURE NOTES IN COMPUTER SCIENCE).

A Multimodal People Recognition System for an Intelligent Environment. / Sorbello, Rosario; Anzalone, Salvatore M.; Pagello, Enrico; Menegatti, Emanuele; Yoshikawa, Yuichiro; Ishiguro, Hiroshi.

AI*IA 2011: Artificial Intelligence Around Man and Beyond. Vol. 2011 2011. pag. 451-456 (LECTURE NOTES IN COMPUTER SCIENCE).

Risultato della ricerca: Chapter

Sorbello, R, Anzalone, SM, Pagello, E, Menegatti, E, Yoshikawa, Y & Ishiguro, H 2011, A Multimodal People Recognition System for an Intelligent Environment. in AI*IA 2011: Artificial Intelligence Around Man and Beyond. vol. 2011, LECTURE NOTES IN COMPUTER SCIENCE, pagg. 451-456.
Sorbello R, Anzalone SM, Pagello E, Menegatti E, Yoshikawa Y, Ishiguro H. A Multimodal People Recognition System for an Intelligent Environment. In AI*IA 2011: Artificial Intelligence Around Man and Beyond. Vol. 2011. 2011. pag. 451-456. (LECTURE NOTES IN COMPUTER SCIENCE).
Sorbello, Rosario ; Anzalone, Salvatore M. ; Pagello, Enrico ; Menegatti, Emanuele ; Yoshikawa, Yuichiro ; Ishiguro, Hiroshi. / A Multimodal People Recognition System for an Intelligent Environment. AI*IA 2011: Artificial Intelligence Around Man and Beyond. Vol. 2011 2011. pagg. 451-456 (LECTURE NOTES IN COMPUTER SCIENCE).
@inbook{1e2a5dca620f40398737f699f1dfeda1,
title = "A Multimodal People Recognition System for an Intelligent Environment",
abstract = "In this paper, a multimodal system for recognizing people in intelligent environments is presented. Users are identified and tracked by detecting and recognizing voices and faces through cameras and microphones spread around the environment. This multimodal approach has been chosen to develop a flexible and cheap though reliable system, implemented through consumer electronics. Voice features are extracted through a short time spectrum analysis, while face features are extracted using the eigenfaces technique. The recognition task is achieved through the use of some Support Vector Machines, one per modality, that learn and classify the features of each person, while bindings between modalities are also learnt through a cross-anchoring learning rule based on the mutual exclusivity selection principle. The system has been developed using NMM, a middleware software capable of splitting the sensors processing in several software nodes, making the system scalable in the number of cameras and microphones",
author = "Rosario Sorbello and Anzalone, {Salvatore M.} and Enrico Pagello and Emanuele Menegatti and Yuichiro Yoshikawa and Hiroshi Ishiguro",
year = "2011",
language = "English",
isbn = "978-3-642-23953-3",
volume = "2011",
series = "LECTURE NOTES IN COMPUTER SCIENCE",
pages = "451--456",
booktitle = "AI*IA 2011: Artificial Intelligence Around Man and Beyond",

}

TY - CHAP

T1 - A Multimodal People Recognition System for an Intelligent Environment

AU - Sorbello, Rosario

AU - Anzalone, Salvatore M.

AU - Pagello, Enrico

AU - Menegatti, Emanuele

AU - Yoshikawa, Yuichiro

AU - Ishiguro, Hiroshi

PY - 2011

Y1 - 2011

N2 - In this paper, a multimodal system for recognizing people in intelligent environments is presented. Users are identified and tracked by detecting and recognizing voices and faces through cameras and microphones spread around the environment. This multimodal approach has been chosen to develop a flexible and cheap though reliable system, implemented through consumer electronics. Voice features are extracted through a short time spectrum analysis, while face features are extracted using the eigenfaces technique. The recognition task is achieved through the use of some Support Vector Machines, one per modality, that learn and classify the features of each person, while bindings between modalities are also learnt through a cross-anchoring learning rule based on the mutual exclusivity selection principle. The system has been developed using NMM, a middleware software capable of splitting the sensors processing in several software nodes, making the system scalable in the number of cameras and microphones

AB - In this paper, a multimodal system for recognizing people in intelligent environments is presented. Users are identified and tracked by detecting and recognizing voices and faces through cameras and microphones spread around the environment. This multimodal approach has been chosen to develop a flexible and cheap though reliable system, implemented through consumer electronics. Voice features are extracted through a short time spectrum analysis, while face features are extracted using the eigenfaces technique. The recognition task is achieved through the use of some Support Vector Machines, one per modality, that learn and classify the features of each person, while bindings between modalities are also learnt through a cross-anchoring learning rule based on the mutual exclusivity selection principle. The system has been developed using NMM, a middleware software capable of splitting the sensors processing in several software nodes, making the system scalable in the number of cameras and microphones

UR - http://hdl.handle.net/10447/77378

UR - http://link.springer.com/content/pdf/10.1007%2F978-3-642-23954-0_46.pdf

M3 - Chapter

SN - 978-3-642-23953-3

VL - 2011

T3 - LECTURE NOTES IN COMPUTER SCIENCE

SP - 451

EP - 456

BT - AI*IA 2011: Artificial Intelligence Around Man and Beyond

ER -