论文信息 - Retrieving Similar Movements in Motion Capture Data

Retrieving Similar Movements in Motion Capture Data

Efficient and effective similarity retrieval in large human motion databases is valuable in many fields such as computer animation, security research, sports, and medicine. This demonstration paper presents a content-based retrieval system that is able to examine database motions and locate all their sub-motions similar to a query motion example. The proposed system does not require any textual annotations nor explicit knowledge of the data and can deal with spatio-temporal variances of individual human motions. The system is presented as an online web application indexing a real-life 68-minute human motion database.

Jan Sedmidubský | Jakub Valcik | J. Sedmidubský | Jakub Valcík

[1] Pavel Zezula,et al. A Key-Pose Similarity Algorithm for Motion Data Retrieval , 2013, ACIVS.

[2] Tido Röder,et al. Documentation Mocap Database HDM05 , 2007 .

[3] David Novak,et al. Metric Index: An efficient and scalable solution for precise and approximate similarity search , 2011, Inf. Syst..

[4] Xiaoyong Lei,et al. Motion Data Retrieval from Very Large Motion Databases , 2011, 2011 International Conference on Virtual Reality and Visualization.

[5] Carlos Agón,et al. Time-series data mining , 2012, CSUR.

[6] Tido Röder,et al. Efficient content-based retrieval of motion capture data , 2005, SIGGRAPH 2005.

[7] Hans-Peter Seidel,et al. Efficient and Robust Annotation of Motion Capture Data , 2009 .

[8] Woong Choi,et al. Similarity Retrieval of Motion Capture Data Based on Derivative Features , 2012, Journal of Advanced Computational Intelligence and Intelligent Informatics.

[9] Rynson W. H. Lau,et al. A real-time database architecture for motion capture data , 2011, ACM Multimedia.