운동학적 접근 방법을 사용한 복잡한 인간 동작 질의 시스템

A Kinematic Approach to Answering Similarity Queries on Complex Human Motion Data

  • 한혁 (서울대학교 컴퓨터공학부) ;
  • 김신규 (서울대학교 컴퓨터공학부) ;
  • 정형수 (서울대학교 컴퓨터공학부) ;
  • 염헌영 (서울대학교 컴퓨터공학부)
  • 발행 : 2009.08.30

초록

대규모 인간 동작 데이터베이스에서 고차원의 데이터를 처리하는 것이 큰 비용을 요구하기에, 최근 데이터베이스 및 그래픽스 학계는 인간 동작 데이터 질의 및 접근에 큰 관심을 가지게 되었다. 특히, 인간 동작 데이터를 위한 효과적인 유사도(거리) 측정 방법이나 질의 처리는 여전히 많은 연구진들이 도전하고 있는 문제이다. 이에, 본 연구진은 SMoFinder 라고 명명한 동작 질의 처리 시스템을 제안한다. SMoFinder는 새롭게 고안된 운동학적 거리 측정 그리고 적응적 프레임 세그멘테이션에 기반하는 효율적인 인덱싱을 사용하여 동작 질의를 처리한다. 이를 위해, SMoFinder에서는 인간 동작을 다연결 물리 운동으로 간주하고 새로운 가중치 Minkowski 함수를 정의했다. 또한, 효율적인 인덱싱을 위해 모든 프레임을 저장하지 않고 유사한 프레임들 중에서 대표 프레임을 뽑아서 저장하는 적응적 세그멘테이션을 고안했다. 그리고, 효율적인 검색을 위해 이들 대표 프레임들만 가지고 k-근접 이웃 질의를 수행하는 새로운 방법을 제안한다. 마지막으로, SMoFinder가 데이터베이스 용량이 크게 줄지만(1/25배), 검색 능력은 다른 시스템과 동일하거나 우월하다는 것을 실험을 통해 보여주고자 한다.

Recently there has arisen concern in both the database community and the graphics society about data retrieval from large motion databases because the high dimensionality of motion data implies high costs. In this circumstance, finding an effective distance measure and an efficient query processing method for such data is a challenging problem. This paper presents an elaborate motion query processing system, SMoFinder (Similar Motion Finder), which incorporates a novel kinematic distance measure and an efficient indexing strategy via adaptive frame segmentation. To this end, we regard human motions as multi-linkage kinematics and propose the weighted Minkowski distance metric. For efficient indexing, we devise a new adaptive segmentation method that chooses representative frames among similar frames and stores chosen frames instead of all frames. For efficient search, we propose a new search method that processes k-nearest neighbors queries over only representative frames. Our experimental results show that the size of motion databases is reduced greatly (${\times}1/25$) but the search capability of SMoFinder is equal to or superior to that of other systems.

키워드

참고문헌

  1. Hyungsoo Jung, Hyuck Han, Shingyu Kim, Heon Y. Yoem. SMoFinder: A System for Querying Complex Human Motions Using a Kinematic Approach. In Proceedings of the 2008 Third International Conference on Convergence and Hybrid Information Technology, pages 640-643, Busan, Korea, 2008.
  2. CMU graphics lab motion capture database. http://mocap.cs.cmu.edu/.
  3. CMU graphics lab motion capture database. http://mocap.cs.cmu.edu/.
  4. R. Agrawal, C. Faloutsos, and A. N. Swami. Efficient similarity search in sequence databases. In Proceedings of the 4th International Conference on Foundations of Data Organization and Algorithms, pages 69–84, London, UK, 1993. Springer-Verlag.
  5. L. Chen, M. T. Ozsu, and V. Oria. Robust and fast similarity search for moving object trajectories. In Proceedings of the 2005 ACM SIGMOD international conference on Management of data, pages 491-502, New York, NY, USA, 2005. ACM.
  6. Y. Chen, S. Jiang, B. C. Ooi, and A. K. H. Tung. Querying complex spatio-temporal sequences in human motion databases. In ICDE, pages 90–99, 2008.
  7. P. Ciaccia, M. Patella, and P. Zezula. M-tree: An efficient access method for similarity search in metric spaces. In The VLDB Journal, pages 426–435, 1997.
  8. C. Faloutsos, M. Ranganathan, and Y. Manolopoulos. Fast subsequence matching in time-series databases. In Proceedings of the 1994 ACM SIGMOD international conference on Management of data, pages 419–429, New York, NY, USA, 1994. ACM.
  9. A. Guttman. R-trees: a dynamic index structure for spatial searching. In Proceedings of the 1984 ACM SIGMOD international conference on Management of data, pages 47–57, New York, NY, USA, 1984. ACM.
  10. E. Keogh, K. Chakrabarti, M. Pazzani, and S. Mehrotra. Locally adaptive dimensionality reduction for indexing large time series databases. In Proceedings of the 2001 ACM SIGMOD international conference on Management of data, pages 151–162, New York, NY, USA, 2001. ACM.
  11. E. Keogh, K. Chakrabarti, M. Pazzani, and S. Mehrotra. Locally adaptive dimensionality reduction for indexing large time series databases. In Proceedings of the 2001 ACM SIGMOD international conference on Management of data, pages 151–162, New York, NY, USA, 2001. ACM.
  12. L. Kovar and M. Gleicher. Automated extraction and parameterization of motions in large data sets. ACM Trans. Graph., 23(3):559–568, 2004. https://doi.org/10.1145/1015706.1015760
  13. M. Müller, T. Röder, and M. Clausen. Efficient content-based retrieval of motion capture data. ACM Trans. Graph., 24(3):677–685, 2005. https://doi.org/10.1145/1073204.1073247
  14. K. pong Chan and A. W.-C. Fu. Efficient time series matching by wavelets. In ICDE, pages 126–133, 1999.
  15. S. Salvador and P. Chan. Fastdtw: Toward accurate dynamic time warping in linear time and space. In KDD Workshop on Mining Temporal and Sequential Data, 2004.
  16. H. T. Shen, B. C. Ooi, and X. Zhou. Towards effective indexing for very large video sequence database. In Proceedings of the 2005 ACM SIGMOD international conference on Management of data, pages 730–741, New York, NY, USA, 2005. ACM.
  17. M. Vlachos, M. Hadjieleftheriou, D. Gunopulos, and E. Keogh. Indexing multi-dimensional time-series with support for multiple distance measures. In Proceedings of the 9th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 216–225, New York, NY, USA, 2003. ACM.
  18. P. N. Yianilos. Data structures and algorithms for nearest neighbor search in general metric spaces. In Proceedings of the 4th annual ACM/SIAM Symposium on Discrete algorithms, pages 311–321, Philadelphia, PA, USA, 1993. Society for Industrial and Applied Mathematics.