The Possibility of Personal Identification Using Skeletal Information in Hip-hop Dance

Bibliographic Information

Other Title
  • ヒップホップダンスにおける骨格情報のみによる個人識別の検討

Search this article

Description

同じダンスであってもダンサーによって異なる印象を与えるように,ダンスは個性によって自身の感情やイメージを効果的に伝えることができる.ここで独自にダンスを習得する場合において,自身の個性に合ったダンス動画を探し練習することが考えられるが,自身の個性に合ったダンスを探すことは容易ではない.そこで本研究では,個性の抽出に向けまず骨格情報に着目し,ヒップホップダンスを対象に,Kinectによって取得できる骨格情報から自身のダンスを判定可能かについて検討を行った.ここでは,基本的なステップで構成されたダンスを用いてダンス経験者と未経験者を対象に実験を行い,経験者ほど骨格情報のみから自身を判別可能であることを明らかにした.次に,経験者を対象に実践的なダンスを用いて実験を行い,熟達者ほど自身のダンスを骨格情報のみから判別可能であることを明らかにした.また,経験者が自身の判別に用いた要素をもとにダンスの骨格情報から角度と移動量について特徴量を生成し,機械学習で特に角度を利用することで個人のダンスを高精度に判別可能であることを明らかにした.

The same dance can give different impressions depending on the way the dancers convey their own emotions and personality through their interpretation of the dance. Beginner dancers who are teaching themselves often search for dance videos online that match their own personality in order to practice and mimic them, but it is not easy to find a dance that suits their own personality and skill level. This study focused on personality in dancing, in particular the possibility of its extraction. We examined hip-hop dance to determine whether it is possible to identify one's own dance from skeleton information acquired by Kinect. Here, we did the experiment with experienced and inexperienced participants using the choreography consisting of basic steps. The results showed that experienced participants could distinguish their own dances by only skeleton information. Next, we did the experiment using the practical choreography for experienced participants, the results showed that rich experienced dancers could distinguish their own dances by only skeleton information. Furthermore, we generated angle features and amount of movement feature from the skeletal information of the dances, based on the factors that experienced dancers used to identify their own dances, and clarified that individual dance can be distinguished accurately by machine learning.

Journal

Details 詳細情報について

Report a problem

Back to top