Cargando…

Emotion Recognition from Skeletal Movements

Automatic emotion recognition has become an important trend in many artificial intelligence (AI) based applications and has been widely explored in recent years. Most research in the area of automated emotion recognition is based on facial expressions or speech signals. Although the influence of the...

Descripción completa

Detalles Bibliográficos
Autores principales: Sapiński, Tomasz, Kamińska, Dorota, Pelikant, Adam, Anbarjafari, Gholamreza
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7515139/
https://www.ncbi.nlm.nih.gov/pubmed/33267360
http://dx.doi.org/10.3390/e21070646
_version_ 1783586750240653312
author Sapiński, Tomasz
Kamińska, Dorota
Pelikant, Adam
Anbarjafari, Gholamreza
author_facet Sapiński, Tomasz
Kamińska, Dorota
Pelikant, Adam
Anbarjafari, Gholamreza
author_sort Sapiński, Tomasz
collection PubMed
description Automatic emotion recognition has become an important trend in many artificial intelligence (AI) based applications and has been widely explored in recent years. Most research in the area of automated emotion recognition is based on facial expressions or speech signals. Although the influence of the emotional state on body movements is undeniable, this source of expression is still underestimated in automatic analysis. In this paper, we propose a novel method to recognise seven basic emotional states—namely, happy, sad, surprise, fear, anger, disgust and neutral—utilising body movement. We analyse motion capture data under seven basic emotional states recorded by professional actor/actresses using Microsoft Kinect v2 sensor. We propose a new representation of affective movements, based on sequences of body joints. The proposed algorithm creates a sequential model of affective movement based on low level features inferred from the spacial location and the orientation of joints within the tracked skeleton. In the experimental results, different deep neural networks were employed and compared to recognise the emotional state of the acquired motion sequences. The experimental results conducted in this work show the feasibility of automatic emotion recognition from sequences of body gestures, which can serve as an additional source of information in multimodal emotion recognition.
format Online
Article
Text
id pubmed-7515139
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-75151392020-11-09 Emotion Recognition from Skeletal Movements Sapiński, Tomasz Kamińska, Dorota Pelikant, Adam Anbarjafari, Gholamreza Entropy (Basel) Article Automatic emotion recognition has become an important trend in many artificial intelligence (AI) based applications and has been widely explored in recent years. Most research in the area of automated emotion recognition is based on facial expressions or speech signals. Although the influence of the emotional state on body movements is undeniable, this source of expression is still underestimated in automatic analysis. In this paper, we propose a novel method to recognise seven basic emotional states—namely, happy, sad, surprise, fear, anger, disgust and neutral—utilising body movement. We analyse motion capture data under seven basic emotional states recorded by professional actor/actresses using Microsoft Kinect v2 sensor. We propose a new representation of affective movements, based on sequences of body joints. The proposed algorithm creates a sequential model of affective movement based on low level features inferred from the spacial location and the orientation of joints within the tracked skeleton. In the experimental results, different deep neural networks were employed and compared to recognise the emotional state of the acquired motion sequences. The experimental results conducted in this work show the feasibility of automatic emotion recognition from sequences of body gestures, which can serve as an additional source of information in multimodal emotion recognition. MDPI 2019-06-29 /pmc/articles/PMC7515139/ /pubmed/33267360 http://dx.doi.org/10.3390/e21070646 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Sapiński, Tomasz
Kamińska, Dorota
Pelikant, Adam
Anbarjafari, Gholamreza
Emotion Recognition from Skeletal Movements
title Emotion Recognition from Skeletal Movements
title_full Emotion Recognition from Skeletal Movements
title_fullStr Emotion Recognition from Skeletal Movements
title_full_unstemmed Emotion Recognition from Skeletal Movements
title_short Emotion Recognition from Skeletal Movements
title_sort emotion recognition from skeletal movements
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7515139/
https://www.ncbi.nlm.nih.gov/pubmed/33267360
http://dx.doi.org/10.3390/e21070646
work_keys_str_mv AT sapinskitomasz emotionrecognitionfromskeletalmovements
AT kaminskadorota emotionrecognitionfromskeletalmovements
AT pelikantadam emotionrecognitionfromskeletalmovements
AT anbarjafarigholamreza emotionrecognitionfromskeletalmovements