芸術科学会論文誌 投稿用カバーシート

■ 論文種類（以下のうちから一つ選択）
  ・原著論文 フルペーパー    

■ 論文分野（1)～3)のうちから一つ選択）
  2) 科学系分野

■ カテゴリ（1個以上選択）
  a-3) CG技術(アニメーション)
  a-4) CG技術(可視化)

■ 該当特集（以下のうちから一つ選択）
  ・一般論文

■ 論文題名(和文、英文)
A Simple and Efficient Method to Extract Keyposes from Mocap Data

■ 著者名(和文、英文)
Sindharta Tanuwijaya (シンダルタ　タヌイジャヤ)
Yoshio Ohno (義夫　大野)

■ 著者所属(和文、英文)
Keio University (慶應義塾大学)

■ 著者e-mail
sin@on.ics.keio.ac.jp
ohno@on.ics.keio.ac.jp

■ 連絡担当者の氏名、住所、所属、電話、Fax、e-mail
氏名： Sindharta Tanuwijaya (シンダルタ　タヌイジャヤ)
所属： 慶應義塾大学大学院　理工学研究科　大野研究室
Fax:
e-mail： sin@on.ics.keio.ac.jp , sindharta_tanuwijaya@yahoo.co.jp


■ 論文概要(和文400字程度、英文100ワード程度)
Researchers have been constantly developing new methods for generating realistic human motion. A common and popular approach is to use motion capture data or mocap data. However, this approach produces a mountain of data and there is an increasing necessity for quick and efficient mocap data search methods.

For text documents, search results are usually returned in the form of a list of documents' titles. This allows users to quickly browse the search results and easily find the documents that they are looking for. Applying this method to mocap data requires the extraction of keyposes since displaying every frame will only present excessive and unnecessary information. 

The authors of this paper propose a simple and efficient method to automatically extract keyposes of mocap data. The proposed method requires only O(kn) operations. Thus, users can vary the search parameters and results will be presented interactively. Our results show that the proposed approach is applicable to mocap data of complex motions and motions composing of many motion segments.


■ キーワード(和文5個程度、英文5個程度)
mocap, data, keypose, search, retrieval, animation