Crowd emotion detection using dynamic probabilistic models

M.W. Baig, E. I. Barakova, L. Marcenaro, G.M.W. Rauterberg, C. S. Regazzoni

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

9 Citations (Scopus)
1 Downloads (Pure)

Abstract

Detecting emotions of a crowd to control the situation is an area of emerging interest. The purpose of this paper is to present a novel idea to detect the emotions of the crowd. Emotions are defined as evolving quantities arising from the reaction to contextual situations in a set of dynamic pattern of events. These events depend on internal and external interaction states in an already mapped space. The emotions of multiple people constituting a crowd in any surveillance environment are estimated by their social and collective behaviors using sensor signals e.g., a camera, which captures and tracks their motion. The feature space is constructed based on local features to model the contextual situations and the different interactions corresponding to different emergent behaviors are modeled using bio-inspired dynamic model. The changes in emotions correspond to behavioral changes which are produced to regulate behaviors under different encountered situations. Proposed algorithm involves the probabilistic signal processing modelling techniques for analysis of different types of collective behaviors based on interactions among people and classification models to estimate emotions as positive or negative. The evaluations are performed on simulated data show the proposed algorithm effectively recognizes the emotions of the crowd under specific situations. © 2014 Springer International Publishing Switzerland.

Original languageEnglish
Title of host publication From Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castellón, Spain, July 22-25, 2014. Proceedings
EditorsA.P. del Pobil, E. Chinellato, E. Martinez-Martin, J. Hallam, E. Cervera, A. Morales
Place of PublicationBerlin
PublisherSpringer
Pages328-337
Number of pages10
ISBN (Print)978-3-319-08863-1
DOIs
Publication statusPublished - 2014
Eventconference; From Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castellón, Spain, July 22-25, 2014. Proceedings -
Duration: 1 Jan 2014 → …

Publication series

NameLecture Notes in Artificial Intelligence
Volume8575
ISSN (Print)03029743
ISSN (Electronic)16113349

Conference

Conferenceconference; From Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castellón, Spain, July 22-25, 2014. Proceedings
Period1/01/14 → …
OtherFrom Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castellón, Spain, July 22-25, 2014. Proceedings

Fingerprint

Probabilistic Model
Dynamic Model
Dynamic models
Signal processing
Cameras
Collective Behavior
Sensors
Interaction
Emergent Behavior
Social Behavior
Local Features
Emotion
Statistical Models
Feature Space
Surveillance
Signal Processing
Camera
Internal
Sensor
Motion

Keywords

  • Autobiographical Memory
  • Collective Behavior
  • Crowd Emotions Detection
  • Dynamic Bayesian Networks
  • Dynamic event modeling

Cite this

Baig, M. W., Barakova, E. I., Marcenaro, L., Rauterberg, G. M. W., & Regazzoni, C. S. (2014). Crowd emotion detection using dynamic probabilistic models. In A. P. del Pobil, E. Chinellato, E. Martinez-Martin, J. Hallam, E. Cervera, & A. Morales (Eds.), From Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castellón, Spain, July 22-25, 2014. Proceedings (pp. 328-337). (Lecture Notes in Artificial Intelligence; Vol. 8575). Berlin: Springer. https://doi.org/10.1007/978-3-319-08864-8_32
Baig, M.W. ; Barakova, E. I. ; Marcenaro, L. ; Rauterberg, G.M.W. ; Regazzoni, C. S. / Crowd emotion detection using dynamic probabilistic models. From Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castellón, Spain, July 22-25, 2014. Proceedings. editor / A.P. del Pobil ; E. Chinellato ; E. Martinez-Martin ; J. Hallam ; E. Cervera ; A. Morales. Berlin : Springer, 2014. pp. 328-337 (Lecture Notes in Artificial Intelligence).
@inproceedings{6f3ba1f46ebb4efdadf98d8174413f4d,
title = "Crowd emotion detection using dynamic probabilistic models",
abstract = "Detecting emotions of a crowd to control the situation is an area of emerging interest. The purpose of this paper is to present a novel idea to detect the emotions of the crowd. Emotions are defined as evolving quantities arising from the reaction to contextual situations in a set of dynamic pattern of events. These events depend on internal and external interaction states in an already mapped space. The emotions of multiple people constituting a crowd in any surveillance environment are estimated by their social and collective behaviors using sensor signals e.g., a camera, which captures and tracks their motion. The feature space is constructed based on local features to model the contextual situations and the different interactions corresponding to different emergent behaviors are modeled using bio-inspired dynamic model. The changes in emotions correspond to behavioral changes which are produced to regulate behaviors under different encountered situations. Proposed algorithm involves the probabilistic signal processing modelling techniques for analysis of different types of collective behaviors based on interactions among people and classification models to estimate emotions as positive or negative. The evaluations are performed on simulated data show the proposed algorithm effectively recognizes the emotions of the crowd under specific situations. {\circledC} 2014 Springer International Publishing Switzerland.",
keywords = "Autobiographical Memory, Collective Behavior, Crowd Emotions Detection, Dynamic Bayesian Networks, Dynamic event modeling",
author = "M.W. Baig and Barakova, {E. I.} and L. Marcenaro and G.M.W. Rauterberg and Regazzoni, {C. S.}",
year = "2014",
doi = "10.1007/978-3-319-08864-8_32",
language = "English",
isbn = "978-3-319-08863-1",
series = "Lecture Notes in Artificial Intelligence",
publisher = "Springer",
pages = "328--337",
editor = "{del Pobil}, A.P. and E. Chinellato and E. Martinez-Martin and J. Hallam and E. Cervera and A. Morales",
booktitle = "From Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castell{\'o}n, Spain, July 22-25, 2014. Proceedings",
address = "Germany",

}

Baig, MW, Barakova, EI, Marcenaro, L, Rauterberg, GMW & Regazzoni, CS 2014, Crowd emotion detection using dynamic probabilistic models. in AP del Pobil, E Chinellato, E Martinez-Martin, J Hallam, E Cervera & A Morales (eds), From Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castellón, Spain, July 22-25, 2014. Proceedings. Lecture Notes in Artificial Intelligence, vol. 8575, Springer, Berlin, pp. 328-337, conference; From Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castellón, Spain, July 22-25, 2014. Proceedings, 1/01/14. https://doi.org/10.1007/978-3-319-08864-8_32

Crowd emotion detection using dynamic probabilistic models. / Baig, M.W.; Barakova, E. I.; Marcenaro, L.; Rauterberg, G.M.W.; Regazzoni, C. S.

From Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castellón, Spain, July 22-25, 2014. Proceedings. ed. / A.P. del Pobil; E. Chinellato; E. Martinez-Martin; J. Hallam; E. Cervera; A. Morales. Berlin : Springer, 2014. p. 328-337 (Lecture Notes in Artificial Intelligence; Vol. 8575).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Crowd emotion detection using dynamic probabilistic models

AU - Baig, M.W.

AU - Barakova, E. I.

AU - Marcenaro, L.

AU - Rauterberg, G.M.W.

AU - Regazzoni, C. S.

PY - 2014

Y1 - 2014

N2 - Detecting emotions of a crowd to control the situation is an area of emerging interest. The purpose of this paper is to present a novel idea to detect the emotions of the crowd. Emotions are defined as evolving quantities arising from the reaction to contextual situations in a set of dynamic pattern of events. These events depend on internal and external interaction states in an already mapped space. The emotions of multiple people constituting a crowd in any surveillance environment are estimated by their social and collective behaviors using sensor signals e.g., a camera, which captures and tracks their motion. The feature space is constructed based on local features to model the contextual situations and the different interactions corresponding to different emergent behaviors are modeled using bio-inspired dynamic model. The changes in emotions correspond to behavioral changes which are produced to regulate behaviors under different encountered situations. Proposed algorithm involves the probabilistic signal processing modelling techniques for analysis of different types of collective behaviors based on interactions among people and classification models to estimate emotions as positive or negative. The evaluations are performed on simulated data show the proposed algorithm effectively recognizes the emotions of the crowd under specific situations. © 2014 Springer International Publishing Switzerland.

AB - Detecting emotions of a crowd to control the situation is an area of emerging interest. The purpose of this paper is to present a novel idea to detect the emotions of the crowd. Emotions are defined as evolving quantities arising from the reaction to contextual situations in a set of dynamic pattern of events. These events depend on internal and external interaction states in an already mapped space. The emotions of multiple people constituting a crowd in any surveillance environment are estimated by their social and collective behaviors using sensor signals e.g., a camera, which captures and tracks their motion. The feature space is constructed based on local features to model the contextual situations and the different interactions corresponding to different emergent behaviors are modeled using bio-inspired dynamic model. The changes in emotions correspond to behavioral changes which are produced to regulate behaviors under different encountered situations. Proposed algorithm involves the probabilistic signal processing modelling techniques for analysis of different types of collective behaviors based on interactions among people and classification models to estimate emotions as positive or negative. The evaluations are performed on simulated data show the proposed algorithm effectively recognizes the emotions of the crowd under specific situations. © 2014 Springer International Publishing Switzerland.

KW - Autobiographical Memory

KW - Collective Behavior

KW - Crowd Emotions Detection

KW - Dynamic Bayesian Networks

KW - Dynamic event modeling

UR - http://www.scopus.com/inward/record.url?scp=84958552118&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-08864-8_32

DO - 10.1007/978-3-319-08864-8_32

M3 - Conference contribution

SN - 978-3-319-08863-1

T3 - Lecture Notes in Artificial Intelligence

SP - 328

EP - 337

BT - From Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castellón, Spain, July 22-25, 2014. Proceedings

A2 - del Pobil, A.P.

A2 - Chinellato, E.

A2 - Martinez-Martin, E.

A2 - Hallam, J.

A2 - Cervera, E.

A2 - Morales, A.

PB - Springer

CY - Berlin

ER -

Baig MW, Barakova EI, Marcenaro L, Rauterberg GMW, Regazzoni CS. Crowd emotion detection using dynamic probabilistic models. In del Pobil AP, Chinellato E, Martinez-Martin E, Hallam J, Cervera E, Morales A, editors, From Animals to Animats 13 : 13th International Conference on Simulation of Adaptive Behavior, SAB 2014, Castellón, Spain, July 22-25, 2014. Proceedings. Berlin: Springer. 2014. p. 328-337. (Lecture Notes in Artificial Intelligence). https://doi.org/10.1007/978-3-319-08864-8_32