TY - CPAPER
KW - AI for Serious Games
KW - Background subtraction
KW - Classification performance
KW - Convolution
KW - Convolutional neural networks
KW - convolutional neural network
KW - Data set
KW - Deep neural networks
KW - Gesture recognition
KW - Intangible cultural heritage
KW - Intangible cultural heritages
KW - Learning schemes
KW - Moving averages
KW - Neural networks
KW - Posture identification
KW - Serious games
KW - Virtual reality
AU - Nikolaos Bakalos
AU - Ioannis Rallis
AU - Nikolaos Doulamis
AU - Anastasios Doulamis
AU - Eftychios Protopapadakis
AU - Athanasios Voulodimos
AB - In this paper we present a deep learning scheme for classification of dance postures using Kinect II RGB data and Convolutional Neural Networks (CNN). This is achieved through the analysis of a data-set that includes three traditional Greek dances, where each dance was performed by 3 different dancers. The obtained data were processed and analyzed using a deep convolutional neural network, in order to identify the primitive postures that comprise the choreography. To enhance the classification performance, a background subtraction framework was utilized, while the CNN architecture was adapted to simulate a moving average behavior. The overall system can be used as an AI module for assessing the performance of users in a serious game for learning traditional dance choreographies
C2 - Int. Conf. Virtual Worlds Games Serious Appl., VS-Games - Proc.
DO - 10.1109/VS-Games.2019.8864522
LA - English
N1 - Journal Abbreviation: Int. Conf. Virtual Worlds Games Serious Appl., VS-Games - Proc.
N2 - In this paper we present a deep learning scheme for classification of dance postures using Kinect II RGB data and Convolutional Neural Networks (CNN). This is achieved through the analysis of a data-set that includes three traditional Greek dances, where each dance was performed by 3 different dancers. The obtained data were processed and analyzed using a deep convolutional neural network, in order to identify the primitive postures that comprise the choreography. To enhance the classification performance, a background subtraction framework was utilized, while the CNN architecture was adapted to simulate a moving average behavior. The overall system can be used as an AI module for assessing the performance of users in a serious game for learning traditional dance choreographies
PB - Institute of Electrical and Electronics Engineers Inc.
PY - 2019
SN - 9781538671238 (ISBN)
SP - 95
EP - 101
TI - Choreographic Pose Identification using Convolutional Neural Networks
UR - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85074251800&doi=10.1109%2fVS-Games.2019.8864522&partnerID=40&md5=8c2cdbe30c5a08fee23b3e43e5a70711
ER -