TY - CONF
KW - Digital storage
KW - dance
KW - Pattern recognition
KW - Extraction
KW - Data mining
KW - Kinematics
KW - Kinematics
KW - choreographic sequences
KW - Key-frame extraction
KW - keyframe extraction
KW - Summarization
AU - Athanasios Voulodimos
AU - Nikolaos Doulamis
AU - Anastasios Doulamis
AU - Ioannis Rallis
AU - IEEE
AB - Capturing, documenting and storing Intangible Cultural Heritage content has been recently enabled at unprecedented volume and quality levels through a variety of sensors and devices. When it comes to the performing arts, and mainly dance and kinesiology, the massive amounts of RGB-D and 3D skeleton data produced by video and motion capture devices the huge number of different types of existing dances and variations thereof, dictate the need for organizing, indexing, archiving, retrieving and analyzing dance-related cultural content in a tractable fashion and with lower computational and storage resource requirements. In this context, we present a novel framework based on kinematics modeling for the extraction of salient 3D human motion data from real-world choreographic sequences. Two approaches are proposed: A clustering-based method for the selection of the basic primitives of a choreography, and a kinematics-based method that generates meaningful summaries at hierarchical levels of granularity. The dance summarization framework has been successfully validated and evaluated with two real-world datasets and with the participation of dance professionals and domain experts.
AN - WOS:000455146803004
BT - 2018 24th International Conference on Pattern Recognition (ICPR)
C3 - Proc. Int. Conf. Pattern Recognit.
DA - 2018///
DB - Scopus
DO - 10.1109/ICPR.2018.8545078
LA - English
N2 - Capturing, documenting and storing Intangible Cultural Heritage content has been recently enabled at unprecedented volume and quality levels through a variety of sensors and devices. When it comes to the performing arts, and mainly dance and kinesiology, the massive amounts of RGB-D and 3D skeleton data produced by video and motion capture devices the huge number of different types of existing dances and variations thereof, dictate the need for organizing, indexing, archiving, retrieving and analyzing dance-related cultural content in a tractable fashion and with lower computational and storage resource requirements. In this context, we present a novel framework based on kinematics modeling for the extraction of salient 3D human motion data from real-world choreographic sequences. Two approaches are proposed: A clustering-based method for the selection of the basic primitives of a choreography, and a kinematics-based method that generates meaningful summaries at hierarchical levels of granularity. The dance summarization framework has been successfully validated and evaluated with two real-world datasets and with the participation of dance professionals and domain experts.
PB - Institute of Electrical and Electronics Engineers Inc.
PY - 2018
SN - 10514651 (ISSN); 9781538637883 (ISBN)
SP - 3013
EP - 3018
EP - 
T2 - 2018 24th International Conference on Pattern Recognition (ICPR)
TI - Kinematics-based Extraction of Salient 3D Human Motion Data for Summarization of Choreographic Sequences
UR - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85059737928&doi=10.1109%2fICPR.2018.8545078&partnerID=40&md5=74245ca672cf41fce02ee6c0c1220c8d
VL - 2018-August
ER -