Efficient Algorithms for Motion Based Video Retrieval

  • Jong Myeon Jeong
  • Young Shik Moon
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2195)


In this paper, efficient algorithms for content-based video retrieval using motion information are proposed. We describe algorithms for a temporal scale invariant and spatial translation absolute retrieval using trail model and a temporal scale absolute and spatial translation invariant retrieval using trajectory model. In the retrieval using trail model, the Distance transformation is performed on each trail image in database. Then, from a given query trail the pixel values along the query trail are added in each distance image to compute the average distance between the trails of query image and database image. For the spatial translation invariant retrieval using trajectory model, a new coding scheme referred to as Motion Retrieval Code is proposed, which is suitable for representing object motions in video. Since the Motion Retrieval Code is designed to reflect the human visual system, it is very efficient to compute the similarity between two motion vectors, using a few bit operations.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    S. Dagtas, W. Al-Khatib, A. Ghafoor and R. L. Kashyap, “Models for Motion-Based Video Indexing and Retrieval,” IEEE Trans. on IP., vol. 9, no. 1, pp. 88–101, Jan. 2000.Google Scholar
  2. [2]
    Z. Aghbari K. Kaneko, and A. Makinouchi, “A Motion-Location Based Indexing Method for Retrieval MPEG Videos,” Proc. of the 9th Int. Workshop on Database and Expert Sys. Appli., pp. 102–107, 1998.Google Scholar
  3. [3]
    K. W. Lee, W. S. You and J. Kim, Hierarchical Object Motion Trajectory Descriptors, ISO/IECJTC1/SC29/ WG11/MPEG99/M4681, Vancouver, Jul. 1999.Google Scholar
  4. [4]
    S. F. Chang, W. Chen, H. J. Meng, H. Sundaram, and D. Zhong, “A Fully Automated Content-Based Video Search Engine Supporting Spatiotemporal Queries,” IEEE Trans. on CSVT., vol. 8, no. 5, pp. 602–615, Sep. 1998.Google Scholar
  5. [5]
    S. Panchanathan, F. Golshani, and Y. C. Park, “VideoRoadMap: A System for Interactie Classification and Indexing of Still and Motion Pictures,” Proc. of IEEE Instrumentation and Measurement Tech. Conf., pp. 18–21, 1998.Google Scholar
  6. [6]
    N. Dimitrova, and F. Golshani, “Motion Recovery for Video Content Classification,” ACM Trans. on Info. Sys., vol. 13, no. 4, pp. 408–439, Oct. 1995.CrossRefGoogle Scholar
  7. [7]
    K. W. Lee, W. S. You and J. Kim, “Video Retrieval based on the Object’s Motion Trajectory,” Proc. of SPIE, vol. 4067, pp. 114–124, 2000.CrossRefGoogle Scholar
  8. [8]
    W. Chen, S. F. Chang, “Motion Trajectory Matching of Video Objects,” Proc. of SPIE, vol. 3972, pp. 544–553, 2000.CrossRefGoogle Scholar
  9. [9]
    G. Borgefors, “Distance Transformations in Digital Images,” CVGIP, vol.34, no. 3, pp. 334–371, 1986.Google Scholar
  10. [10]
    D. H. Ballard, C. M. Brown, Computer Vision, Prentice-Hall, 1982.Google Scholar
  11. [11]
    I. K. Sethi and R. Jain, “Finding Trajectories of Feature Points in an Monocular Image Sequence,” IEEE Trans. on PAMI., vol. 9, no. 1, pp. 56–73, Jan. 1987.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Jong Myeon Jeong
    • 1
  • Young Shik Moon
    • 2
  1. 1.Broadcasting Media Technology DepartmentETRIDaejonKorea
  2. 2.Dept. of computer science & engr.Hanyang UniversityAnsanKorea

Personalised recommendations