A Research on Multi-attribute Sequence Query Processing Techniques for Motion Databases

Due to the development of computer technology and the mature development of motion capture technology, the applications of motion databases become more and more important. How to analysis the huge data stored in the database and efficiently retrieved the matched data is an important research issue. 3D animation design is one of the important applications of motion databases. Based on our teaching experience, the bottleneck of the students’ learning of animation is the motion animation of the 3D characters. Therefore, the motion database can be used to assist the design of the motions for 3D characters. However, it is still a difficult problem because of the high complexity of the matching mechanism and the difficult of user interface design. In this paper, the motion data can be represented as multi-attribute multi-dimensional sequences while the corresponding index structures and query processing mechanism are proposed for efficiently processing the motion queries. Moreover, Microsoft Kinect is used in this paper as the user interface. The captured data can be used as the user query and the further comparison will be performed to find the matched motion data.

[1]  Edgar Chia-Han Lin,et al.  Research on Multi-Attribute Sequence Query Processing Techniques over Data Streams , 2014 .

[2]  Zhigang Deng,et al.  Compression of Human Motion Capture Data Using Motion Pattern Indexing , 2009, Comput. Graph. Forum.

[3]  Wei Wang,et al.  A system for analyzing and indexing human-motion databases , 2005, SIGMOD '05.

[4]  David J. Fleet,et al.  This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Gaussian Process Dynamical Model , 2007 .

[5]  Taku Komura,et al.  Finding repetitive patterns in 3D human motion captured data , 2008, ICUIMC '08.

[6]  Chih-Yi Chiu,et al.  Content-based retrieval for human motion data , 2004, J. Vis. Commun. Image Represent..

[7]  B. Prabhakaran,et al.  Indexing 3-D Human Motion Repositories for Content-Based Retrieval , 2009, IEEE Transactions on Information Technology in Biomedicine.

[8]  Jessica K. Hodgins,et al.  Performance animation from low-dimensional control signals , 2005, SIGGRAPH 2005.

[9]  Daniel A. Keim,et al.  A pivot-based index structure for combination of feature vectors , 2005, SAC '05.

[10]  Zhiwen Yu,et al.  3D motion sequence retrieval based on data distribution , 2008, 2008 IEEE International Conference on Multimedia and Expo.

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

[12]  Feng Liu,et al.  3D motion retrieval with motion index tree , 2003, Comput. Vis. Image Underst..

[13]  Dimitrios Gunopulos,et al.  Indexing multi-dimensional time-series with support for multiple distance measures , 2003, KDD '03.

[14]  Arbee L. P. Chen,et al.  Indexing and matching multiple-attribute strings for efficient multimedia query processing , 2006, IEEE Transactions on Multimedia.

[15]  Edgar Chia-Han Lin.  A Research on Multi-dimensional Multi-attribute String Matching Mechanism for 3D Motion Databases , 2016 .

[16]  Arbee L. P. Chen,et al.  Approximate Video Search Based on Spatio-Temporal Information of Video Objects , 2006, 22nd International Conference on Data Engineering Workshops (ICDEW'06).

[17]  Beng Chin Ooi,et al.  Indexing the Distance: An Efficient Method to KNN Processing , 2001, VLDB.

[18]  Edgar Chia-Han Lin,et al.  Research on Sequence Query Processing Techniques over Data Streams , 2013 .

[19]  Kyriakos Mouratidis,et al.  Aggregate nearest neighbor queries in spatial databases , 2005, TODS.

[20]  Edgar Chia-Han Lin.  A Research on 3D Motion Database Management and Query System Based on Kinect , 2015 .

[21]  Nicola J. Ferrier,et al.  Automated analysis of repetitive joint motion , 2003, IEEE Transactions on Information Technology in Biomedicine.