Advertisement

Video Registration: A Perspective

  • Mubarak Shah
  • Rakesh Kumar
Part of the The International Series in Video Computing book series (VICO, volume 5)

Abstract

The increased availability of low-cost, low-power, highly accurate video imagery has resulted in a rapid growth of the applications for this data. Video imagery is collected by handheld units, permanently mounted or track mounted units, and airborne sensors such as Unmanned Aerial Vehicles (UAVs). Video imagery has many advantages over still frame imagery for scene understanding; for example, it provides context and timing relationships, which are suitable for dynamic situation monitoring and action verification. Manipulation of video requires automatic processing and analysis (computer vision and image processing), vast amounts of storage and efficient search methods (databases), high bandwidth communication (networking), and real-time implementations (VLSI/hardware). Users of video imagery include disaster relief agencies, environmental monitoring and planning applications, tactical military groups, civilian agencies such as homeland security agencies, city planners, transportation (traffic management), the entertainment industry, law enforcement groups, landscape ecologists, WWW users and trainers and educators.

Keywords

Computer Vision Optical Flow Motion Model Bundle Adjustment Video Segmentation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Doug Ayers and Mubarak Shah, “Monitoring Human Behavior from Video Taken in an Office Environment”, Image and Vision Computing, Volume 19, Issue 12, pp. 833–846, 2001.CrossRefGoogle Scholar
  2. [2]
    Cen Rao, Alper Yilmaz and Mubarak Shah, “View Invariant Representation and Recognition of Actions,” Int. Journal of Computer Vision, pp 203–226, Volume 50, no 2, November 2002.zbMATHCrossRefGoogle Scholar
  3. [3]
    Serge Ayer and Harpreet S. Sawhney, “Layered Representation of Motion Video Using Robust Maximum-Likelihood Estimation of Mixture Models and MDL Encoding.” ICCV, pp. 777–784, 1995.Google Scholar
  4. [4]
    Claudette Cédras and Mubarak Shah, “Motion Based Recognition: A Survey”, Image and Vision Computing, Volume 13, No.2, pages 129–155, March 1995.CrossRefGoogle Scholar
  5. [5]
    Ju, S., Black, M. J., and Jepson, A. D., “Skin and Bones: Multi-layer, locally affine, optical flow and regularization with transparency”, IEEE Conf. on Computer Vision and Pattern Recognition, CVPR’96, San Francisco, CA, June 1996, pp. 307–314.Google Scholar
  6. [6]
    L. Brown, “A Survey of Image Registration Techniques”, ACM Computing Surveys, 24(4), pp. 325–376, 1992.CrossRefGoogle Scholar
  7. [7]
    P.J. Burt and E.H. Adelson, “A Multiresolution Spline with Applications to Image Mosaics”, ACM Trans. on Graphics, 2(4):217–236, 1983.CrossRefGoogle Scholar
  8. [8]
    Mubarak Shah and Ramesh Jain, “Motion-Based Recognition”, Kluwer Academic Publishers, 1997.zbMATHGoogle Scholar
  9. [9]
    B. Lucas and T. Kanade. “An iterative image registration technique with an application to stereo vision”, Proceedings of the 7th International Joint Conference on Artificial Intelligence, pp. 674–679, 1981.Google Scholar
  10. [10]
    R. Kumar, H. Sawhney, J. Asmuth, A. Pope, and S. Hsu, “Registration of video to geo-referenced imagery”, Fourteenth International Conference on Pattern Recognition, vol. 2. pp. 1393–1400, 1998.Google Scholar
  11. [11]
    J.Bergen, P. Anandan, K. Hanna, and R. Hingorani, “Hierarchical model-based motion estimation”, Proc. European Conference on Computer Vision, pp. 237–252, 1992.Google Scholar
  12. [12]
    R. Szeliski, “Image mosaicing for tele-reality applications”, IEEE Workshop on Applications of Computer Vision, pp. 44–53, 1994.Google Scholar
  13. [13]
    Mubarak Shah, “The Changing Shape of Computer Vision in the Twenty First Century”, Int. Journal of Computer Vision, pp 103–110, Volume 50, no 2, November 2002.CrossRefGoogle Scholar
  14. [14]
    S. Mann and R. W. Picard, “Video orbits of the projective group a simple approach to featureless estimation of parameters”, IEEE Transactions on Image Processing, 6(9), pp. 1281–1295, 1997.CrossRefGoogle Scholar
  15. [15]
    R. Cannata, M. Shah, S. Blask, and J. Van Workum, “Autonomous Video Registration Using Sensor Model Parameter Adjustments”, Applied Imagery Pattern Recognition Workshop, pp. 215–222, 2000.Google Scholar
  16. [16]
    Omar Javed and Mubarak Shah “Tracking and Object Classification for Automated Surveillance”, European Conference on Computer Vision, Copenhagen, Denmark, pp. 343–357, May 28–31, 2002.Google Scholar
  17. [17]
    Sohaib Khan, “Visual Tracking of People and Object-Based Video Segmentation”, Ph.D. thesis, Computer Science, University of Central Florida, 2002.Google Scholar
  18. [18]
    J. Shi, and C. Tomasi, “Good Features to Track”, CVPR, pp. 593–600, 1994.Google Scholar
  19. [19]
    Krishnan Rangarajan and Mubarak Shah, “Establishing Motion Correspondence”, CVGIP: Image Understanding, pp. 56–73, July 1991.Google Scholar
  20. [20]
    W. Freeman and E. Adelson, “The design and use of steerable filters”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(9): 891–906, 1991.CrossRefGoogle Scholar
  21. [21]
    John Y. A. Wang and Edward H. Adelson. “Representing Moving Images with Layers” IEEE Transactions on Image Processing, Special Issue: Image Sequence Compression, 3(5) pp. 625–638, September 1994.Google Scholar
  22. [22]
    Torr, P. H. S., “Geometric Motion Segmentation and Model Selection”, Philosophical Transactions of the Royal Society A, editors: Lasenby, J. and Zisserman, A. and Cipolla, R. and Longuet-Higgins, H., pp. 1321–1340, 1998.Google Scholar
  23. [23]
    B.K.P. Horn and B.G. Schunck, “Determining optical flow”, Artificial Intelligence, volume 17, pp: 185–203, 1981.CrossRefGoogle Scholar
  24. [24]
    B.K.P. Horn, “Relative Orientation”, IEEE International Journal of Computer Vision, volume 4, pp: 59–78, 1990.CrossRefGoogle Scholar
  25. [25]
    Longuet-Higgins, H.C, “A computer algorithm for reconstructing a scene from two projections”, Nature, vol.293, pp: 133–135, 1981CrossRefGoogle Scholar
  26. [26]
    Hartley, R. I., “In Defence of the 8-point Algorithm”, IEEE International Conference on Computer Vision, pp: 1064–1075, Cambridge, MA., 1995Google Scholar
  27. [27]
    Faugeras, O.D., “Three-Dimensional Computer Vision: A Geometric Viewpoint”, The MIT Press, 1993.Google Scholar
  28. [28]
    Faugeras, O.D. and Robert, L., “What can two images tell us about a third one”, European Conference on Computer Vision, Springer-Verlag, pp: 485–492, 1994Google Scholar
  29. [29]
    Faugeras, O.D. and Mourrain, B., “On the Geometry and Algebra of the Point and Line Correspondences between N Images”, IEEE International Conference on Computer Vision, pp: 951-962, Cambridge, MA., 1995.Google Scholar
  30. [30]
    Hai Tao, Harpreet S. Sawhney, and Rakesh Kumar, “Dynamic layer representation with applications to tracking,” In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, Hilton Head, South Carolina, 2000.Google Scholar
  31. [31]
    M. Irani, B. Rousso and S. Peleg, “Computing occluding and transparent motions,” International Journal of Computer Vision, February 1994.Google Scholar
  32. [32]
    Harpreet S. Sawhney, Serge Ayer and Monika Gorkani, “Modelbased 2D and 3D dominant motion estimation for mosaicing and video representation,” In Proceedings of the International Conference of Computer Vision, pp. 583–590, Cambridge, MA., 1995.Google Scholar
  33. [33]
    Horn, B.K.P. & E.J. Weldon, Jr., “Direct methods for recovering motion,” International Journal of Computer Vision, Vol. 2, No.1, pp. 51–76, June 1988.CrossRefGoogle Scholar
  34. [34]
    R. Kumar, P. Anandan, M. Irani, J. Bergen, and K. Hanna, “Representation of scenes from collections of images,” In Proceedings of the IEEE Workshop on Visual Representations, Cambridge, MA, 1995.Google Scholar
  35. [35]
    G. Adiv, “Determining three-dimensional motion and structure from optical flow generated by several moving objects,” In IEEE Transactions on Pattern Analysis and Machine Intelligence, July 1985.Google Scholar
  36. [36]
    R. Kumar, P. Anandan, and K. Hanna, “Direct recovery of shape from multiple views: a parallax based approach,” In Proceedings of the International Conference on Pattern Recognition, Jerusalem, Israel, 1994.Google Scholar
  37. [37]
    H. Sawhney, “3D geometry from planar parallax”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1994.Google Scholar
  38. [38]
    R. Wildes, D. Hirvonen, S. Hsu, T. Klinedinst, R. Kumar, B. Lehman, B. Matei, W. Zhao, “Video georegistration: algorithm and quantitative evaluation,” In Proceedings of IEEE International Conference on Computer Vision, Vancouver, July 2001.Google Scholar
  39. [39]
    S. Hsu, S. Samarasekera, R. Kumar, and H.S. Sawhney, “Pose estimation, model refinement, and enhanced visualization using video,” In IEEE Proceedings of Computer Vision and Pattern Recognition, Hilton Head, South Carolina, pp. 488–495, 2000.Google Scholar
  40. [40]
    Hanna, K.J., and Okamoto, N.E., “Combining stereo and motion analysis for direct estimation of scene structure,” In Proceedings of the IEEE International Conference on Computer Vision, pp. 357–365, Berlin 1993.Google Scholar
  41. [41]
    R. Mandelbaum, G. Salgian and H.S. Sawhney, “Correlation-based Estimation of Ego-Motion and Structure from Motion and Stereo”, in Proceedings of the IEEE International Conference on Computer Vision, Corfu, Greece, Sep. 1999.Google Scholar
  42. [42]
    Harpreet S. Sawhney, Yanlin Guo, Keith Hanna, Rakesh Kumar, Sean Adkins, and Samuel Zhou. “Hybrid stereo camera: An ibr approach for synthesis of very high resolution stereoscopic image sequences”, In SIGGRAPH 2001, Computer Graphics Proceedings, Annual Conference Series. ACM Press/ACM SIGGRAPH, 2001.Google Scholar
  43. [43]
    R. Kumar, H. Sawhney, S. Samarasekera, S. Hsu, H. Tao, Y. Guo, K. Hanna, A. Pope, R. Wildes, D. Hirvonen,M. Hansen, P. Burt, “Aerial Video Surveillance and Exploitation”, Proceedings of the IEEE, Special Issue on Third Generation Surveillance Systems, 89(10): 1518–1539, October 2001.Google Scholar
  44. [44]
    Sohaib Khan, Mubarak Shah, “Object Based Segmentation of Video Using Color, Motion and Spatial Information”, IEEE Computer Vision and Pattern Recognition Conference, CVPR 2001, Kauai, Hawaii, Dec 11–13, 2001Google Scholar

Copyright information

© Springer Science+Business Media New York 2003

Authors and Affiliations

  • Mubarak Shah
    • 1
  • Rakesh Kumar
    • 2
  1. 1.Computer Vision Laborotory Computer ScienceUniversity of Central FloridaOrlandoUSA
  2. 2.Sarnoff CorporationPrincetonUSA

Personalised recommendations