Skip to main content
SpringerLink
Log in

Motion retrieval based on Switching Kalman Filters Model

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

A novel content-based motion descriptor is proposed. Firstly, the multi-view image information is captured to represent motion, and then the Switching Kalman Filters Model (S-KFM), which is a kind of the Dynamic Bayesian Network (DBN), is built based on the images fusion and the optical stream technology. Secondly, through the S-KFM inferring and sequence signal coding, a graph-based motion descriptor can be obtained. Lastly, motion matching results based on the graph model descriptor show our method is effective.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Bashir FI, Khokhar AA, Schonfeld D (2007) Real-time motion trajectory-based indexing and retrieval of video sequences. IEEE Trans Multimed 9:58–65

    Article  Google Scholar 

  2. Chakrabarti K, Keogh E, Mehrotra S, Pazzani M (2002) Locally adaptive dimensionality reduction for indexing large time series databases. ACM Trans Database Syst 27(2):188–228

    Article  Google Scholar 

  3. Chao M-W, Lin C-H, Assa J, Lee T-Y (2012) Human motion retrieval from hand-drawn sketch. IEEE Trans Vis Comput Graph 18(5):729–740

    Article  Google Scholar 

  4. Feng L, Yueting Z, Fei W, Yunhe P (2003) 3D motion retrieval with motion index tree. Comp Vision Image Underst 92(2):265–284

    Google Scholar 

  5. Gao Y, Tang J, Hong R, Yan S, Dai Q, Zhang N, Chua T-S (2012) Camera constraint-free view-based 3-D object retrieval. IEEE Trans Image Process 21(4):2269–2281

    Article  MathSciNet  Google Scholar 

  6. Gao Y, Wang M, Zha Z-J, Tian Q, Dai Q, Zhang N (2011) Less is more: efficient 3-D object retrieval with query view selection. IEEE Trans Multimed 13(5):1007–1018

    Article  Google Scholar 

  7. Graphics Lab. “Motion capture database”. Carnegie Mellon University, http://mocap.cs.cmu.edu/

  8. Keogh E, Palpanas T, Zordan V, Gunopulos D, Cardle M (2004) “Indexing large human-motion databases.” Proc VLDB: 780–791

  9. Kovar L, Gleicher M, Pighin F (2002) “Motion graphs.” Proc ACM SIGGRAPH: 473–482

  10. Lin Y (2006) “Efficient human motion retrieval in large databases.” Proc ACM GRAPHITE: 31–37

  11. Müller M, Röder T (2006) “Motion templates for automatic classification and retrieval of motion capture data.” Proc ACM SCA

  12. Nixon MS, Aguado AS (2008) “Feature extraction and image processing”, Second edition, published by Elsevier, pp 135–140

  13. Pavlovíc V, Rehg JM, Murphy KP, Cham T-J (1999) “A dynamic Bayesian network approach to figure tracking using learned dynamic models”. Intl. Conf. Computer Vision: 94–101

  14. Qian H, Debin Z, Siwei M, Wen G, Huifang S (2010) Deinterlacing using hierarchical motion analysis. IEEE Trans Circ Syst Video Technol 20(5):673–686

    Article  Google Scholar 

  15. Qinkun X, Haiyun W, Fei L, Yue G (2011) 3D object retrieval based on a graph model descriptor. Neurocomputing 74(17):2340–2348

    Google Scholar 

  16. Russell S, Norvig P (2004) “Artificial intelligence: a modern approach”, Second edition, published by Pearson Education Asia Limited, pp 430–436

  17. Shah VP, Younan NH, King RL (2008) An efficient pan-sharpening method via a combined adaptive PCA approach and contourlets. IEEE Trans Geosci Remote Sens 46(5):1323–1335

    Article  Google Scholar 

  18. Tam GKL, Lau RWH (2007) Deformable model retrieval based on topological and geometric signatures. IEEE Trans Vis Comput Graph 13(3):470–482

    Article  MathSciNet  Google Scholar 

  19. Tang Jeff KT, Leung H (2012) Retrieval of logically relevant 3D human motions by adaptive feature selection with graded relevance feedback. Pattern Recognit Lett 33(4):420–430

    Article  Google Scholar 

  20. Tian J, Qi W, Liu X (2011) Retrieving deep web data through multi-attributes interfaces with structured queries. Int J Softw Eng Knowl Eng 21(4):523–542

    Article  Google Scholar 

  21. Xiao QK, Dai QH, Wang HY (2008) 3D object retrieval approach based on directed acyclic graph lightfield feature. Electron Lett 44(14):847–849

    Article  Google Scholar 

  22. Xiaobai L, Liang L, Shuicheng Y, Hai J (2011) Adaptive object tracking by learning hybrid template on-line. IEEE Trans Circ Syst Video Technol 21(11):1588–1599

    Article  Google Scholar 

  23. Xiaohua D, Liang L, Hongyang C (2013) Discovering video shot categories by unsupervised stochastic graph partition. IEEE Trans Multimed (TMM) 15(1):167–180

    Article  Google Scholar 

  24. Yang Y, Nie F, Xu D, Luo J, Zhuang Y, Pan Y (2012) A multimedia retrieval framework based on semi-supervised ranking and relevance feedback. IEEE Trans Pattern Anal Mach Intell 34(4):723–742

    Article  Google Scholar 

  25. Zhang Z, Tao D (2012) Slow feature analysis for human action recognition. IEEE Trans Pattern Anal Mach Intell 34(3):436–450

    Article  MathSciNet  Google Scholar 

Download references

Acknowledgment

This work is partly supported by the National Basic Research Project of China (No. 2010CB731800) and the China National Foundation (No. 60972095, 61271362).

Author information

Authors and Affiliations

  1. Department of Electronics Information Engineering, Xi’an Technological University, Xi’an, 710032, China

    Qinkun Xiao & Yichuang Luo

  2. STMicroelectronics R&D of Asia-Pacific, Singapore, 554574, Singapore

    Haiyun Wang

Authors
  1. Qinkun Xiao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yichuang Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Haiyun Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qinkun Xiao.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Xiao, Q., Luo, Y. & Wang, H. Motion retrieval based on Switching Kalman Filters Model. Multimed Tools Appl 72, 951–966 (2014). https://doi.org/10.1007/s11042-013-1416-x

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-013-1416-x

Keywords

Search

Navigation