Abstract

A temporal image sequence increases the dimension of the data by simply stacking images above each other. This further raises the computational complexity of the processes. The typical content of a pixel or a voxel is its grey or color value. With some processing, features and fitted model parameters are added. In a pyramid these values are repeatedly summarized in the stack of images or image descriptions with a constant factor of reduction. From this derives their efficiency of allowing \(\log(\mbox{diameter})\) complexity for global information transmission. Content propagates bottom-up by reduction functions like inheritance or filters. Content propagates top-down by expansion functions like interpolation or projection. Moving objects occlude different parts of the image background. Computing one pyramid per frame needs lots of bottom-up computation and very complex and time consuming updating. In the new concept we propose one pyramid per object and one pyramid for the background. The connection between both is established by coordinates that are coded in the pyramidal cells much like in a Laplacian pyramid or a wavelet. We envision that this code will be stored in each cell and will be invariant to the basic movements of the object. All the information about position and orientation of the object is concentrated in the apex. New positions are calculated for the apex and can be accurately reconstructed for every cell in a top-down process. At the new pixel locations the expected content can be verified by comparing it with the actual image frame.

Keywords

Image Segmentation Machine Intelligence Interest Point Reduction Function Base Graph 
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.

References

  1. 1.
    Feldman, J.A., Ballard, D.H.: Connectionist models and their properties. Cognitive Science (6), 205–254 (1982)CrossRefGoogle Scholar
  2. 2.
    Tsotsos, J.K.: On the relative complexity of passive vs active visual search. Intl. J. Computer Vision 7(2), 127–141 (1992)CrossRefGoogle Scholar
  3. 3.
    Tsotsos, J.K.: How does human vision beat the computational complexity of visual perception? In: Pylyshyn, Z. (ed.) Computational Processes in Human Vision: An Interdisciplinary Perspective, pp. 286–338. Ablex Press, Notwood (1988)Google Scholar
  4. 4.
    Zeki, S.: A Vision of the Brain. Blackwell, Oxford (1993)Google Scholar
  5. 5.
    Pizlo, Z., Salach-Golyska, M., Rosenfeld, A.: Curve detection in a noisy image. Vision Research 37(9), 1217–1241 (1997)CrossRefGoogle Scholar
  6. 6.
    Pizlo, Z.: Perception viewed as an inverse problem. Vision Research 41(24), 3145–3161 (2001)CrossRefGoogle Scholar
  7. 7.
    Privitera, C.M., Stark, L.W.: Algorithms for defining visual regions-of-interest: Comparison with eye fixations. IEEE Tr. Pattern Analysis and Machine Intelligence 22(9), 970–982 (2000)CrossRefGoogle Scholar
  8. 8.
    Jolion, J.M., Rosenfeld, A.: A Pyramid Framework for Early Vision. Kluwer Academic Publishers, Dordrecht (1994)Google Scholar
  9. 9.
    Tanimoto, S.L.: Paradigms for pyramid machine algorithms. In: Cantoni, V., Levialdi, S. (eds.) Pyramidal Systems for Image Processing and Computer Vision. NATO ASI Series, vol. F25, pp. 173–194. Springer, Heidelberg (1986)Google Scholar
  10. 10.
    Tanimoto, S.L., Klinger, A. (eds.): Structured Computer Vision: Machine Perception through Hierarchical Computation Structures. Academic Press, New York (1980)Google Scholar
  11. 11.
    Rosenfeld, A. (ed.): Multiresolution Image Processing and Analysis. Springer, Berlin (1984)MATHGoogle Scholar
  12. 12.
    Tanimoto, S.L.: From pixels to predicates in pyramid machines. In: Simon, J.C. (ed.) Proceedings of the COST-13 workshop ’From the Pixels to the Features’. AFCET, Bonas, France (August 1988)Google Scholar
  13. 13.
    Bister, M., Cornelis, J., Rosenfeld, A.: A critical view of pyramid segmentation algorithms. Pattern Recognition Letters 11(9), 605–617 (1990)MATHCrossRefGoogle Scholar
  14. 14.
    Jolion, J.M., Montanvert, A.: The adaptive pyramid, a framework for 2D image analysis. Computer Vision, Graphics, and Image Processing: Image Understanding 55(3), 339–348 (1992)MATHGoogle Scholar
  15. 15.
    Burt, P.J., Adelson, E.H.: The Laplacian pyramid as a compact image code. IEEE Transactions on Communications COM-31(4), 532–540 (1983)CrossRefGoogle Scholar
  16. 16.
    Anderson, C.H., Burt, P.J., van der Wal, G.S.: Change detection and tracking using pyramid transform techniques. In: Intelligent Robots and Computer Vision, September 16-20. SPIE, vol. 579, pp. 72–78 (1985)Google Scholar
  17. 17.
    Kropatsch, W.G., Haxhimusa, Y., Ion, A.: Multiresolution Image Segmentations in Graph Pyramids. In: Kandel, A., Bunke, H., Last, M. (eds.) Applied Graph Theory in Computer Vision and Pattern Recognition, vol. 52, pp. 3–41. Springer, New York (2007)CrossRefGoogle Scholar
  18. 18.
    Pal, N.R., Pal, S.K.: A review on image segmentation techniques. Pattern Recognition 26(3), 1277–1294 (1993)CrossRefGoogle Scholar
  19. 19.
    Nacken, P.F.: Image segmentation by connectivity preserving relinking in hierarchical graph structures. Pattern Recognition 28(6), 907–920 (1995)CrossRefGoogle Scholar
  20. 20.
    Keselman, Y., Dickinson, S.: Generic Model Abstraction from Examples. IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI) 27(7), 1141–1156 (2005)CrossRefGoogle Scholar
  21. 21.
    Hu, W., Tan, T., Wang, L., Maybank, S.: A survey on visual surveillance of object motion and behaviors. IEEE Transactions on Systems, Man and Cybernetics 34, 334–352 (2004)Google Scholar
  22. 22.
    Yilmaz, A., Javed, O., Shah, M.: Object tracking: A survey. ACM Comput. Surv. 38(4), Article 13 (2006) Google Scholar
  23. 23.
    Moeslund, T.B., Hilton, A., Krüger, V.: A survey of advances in vision-based human motion capture and analysis. Computer Vision and Image Understanding 104, 90–126 (2006)CrossRefGoogle Scholar
  24. 24.
    Moeslund, T.B., Hilton, A., Krüger, V.: A survey of computer vision-based human motion capture. Computer Vision and Image Understanding 81, 231–268 (2001)MATHCrossRefGoogle Scholar
  25. 25.
    Veenman, C.J., Reinders, M.J.T., Backer, E.: Resolving motion correspondence for densely moving points. IEEE Tr. Pattern Analysis and Machine Intelligence 23(1), 54–72 (2001)CrossRefGoogle Scholar
  26. 26.
    Serby, D., Koller-Meier, S., Gool, L.V.: Probabilistic object tracking using multiple features. In: International Conference of Pattern Recognition, pp. 184–187. IEEE Computer Society, Los Alamitos (2004)Google Scholar
  27. 27.
    Shafique, K., Shah, M.: A non-iterative greedy algorithm for multi-frame point correspondence. In: ICCV, Nice, France, vol. 1, pp. 110–115. IEEE Computer Society, Los Alamitos (2003)Google Scholar
  28. 28.
    Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE Tr. Pattern Analysis and Machine Intelligence 25(5), 564–575 (2003)CrossRefGoogle Scholar
  29. 29.
    Csaba Beleznai, B.F., Bischof, H.: Human detection in groups using a fast mean shift procedure. In: International Conference on Image Processing, pp. 349–352. IEEE Computer Society, Los Alamitos (2004)Google Scholar
  30. 30.
    Yilmaz, A., Xin, L., Shah, M.: Contour-based object tracking with occlusion handling in video acquired using mobile cameras. IEEE Tr. Pattern Analysis and Machine Intelligence 26(11), 1531–1536 (2004)CrossRefGoogle Scholar
  31. 31.
    Yunqiang, C., Yong, R., Huang, T.S.: JPDAF based HMM for real-time contour tracking. In: CVPR, Kauai, HI, USA, vol. 1, pp. 543–550. IEEE Computer Society, Los Alamitos (2001)Google Scholar
  32. 32.
    Felzenszwalb, P.F.: Pictorial structures for object recognition. International Journal for Computer Vision 61, 55–79 (2005)CrossRefGoogle Scholar
  33. 33.
    Navaratnam, R., Thayananthan, A., Torr, P.H.S., Cipolla, R.: Hierarchical part-based human body pose estimation. In: British Machine Vision Conference (2005)Google Scholar
  34. 34.
    Bray, M., Koller-Meier, E., Schraudolph, N.N., Gool, L.J.V.: Fast stochastic optimization for articulated structure tracking. Image Vision Comput. 25(3), 352–364 (2007)CrossRefGoogle Scholar
  35. 35.
    Bobick, A.F., Wilson, A.D.: A state-based approach to the representation and recognition of gesture. IEEE Tr. Pattern Analysis and Machine Intelligence 19, 1325–1337 (1997)CrossRefGoogle Scholar
  36. 36.
    Wilson, A.D., Bobick, A.F., Cassell, J.: Temporal classification of natural gesture and application to video coding. In: Conference on Computer Vision and Pattern Recognition, pp. 948–954 (1997)Google Scholar
  37. 37.
    Starner, T., Weaver, J., Pentland, A.: Real-time american sign language recognition using desk and wearable computer based video. IEEE Tr. Pattern Analysis and Machine Intelligence 20(12), 1371–1375 (1998)CrossRefGoogle Scholar
  38. 38.
    Oliver, N., Rosario, B., Pentland, A.: A bayesian computer vision system for modeling human interactions. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 831–843 (2000)CrossRefGoogle Scholar
  39. 39.
    Wren, C.R., Pentland, A.P.: Dynamic modeling of human motion. In: International Conference on Automatic Face and Gesture Recognition, pp. 14–16. IEEE Computer Society, Los Alamitos (1998)Google Scholar
  40. 40.
    Pavlovic, V., Rehg, J.M., Cham, T.J., Murphy, K.P.: A dynamic bayesian network approach to figure tracking using learned dynamic models. In: International Conference on Computer Vision, vol. 1, pp. 94–101. IEEE Computer Society, Los Alamitos (1999)CrossRefGoogle Scholar
  41. 41.
    Kropatsch, W.G.: Building irregular pyramids by dual graph contraction. Vision, Image and Signal Processing 142(6), 366–374 (1995)CrossRefGoogle Scholar
  42. 42.
    Kropatsch, W.G., Haxhimusa, Y., Pizlo, Z., Langs, G.: Vision Pyramids that do not Grow too High. Pattern Recognition Letters 26(3), 319–337 (2005)CrossRefGoogle Scholar
  43. 43.
    Lowe, D.G.: Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  44. 44.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 731–737. IEEE, Los Alamitos (1997)Google Scholar
  45. 45.
    Haxhimusa, Y., Kropatsch, W.G., Pizlo, Z., Ion, A.: Approximative Graph Pyramid Solution of the E-TSP. Image and Vision Computing 27(7), 887–896 (2009)CrossRefGoogle Scholar
  46. 46.
    Artner, N.M., López Mármol, S.B., Beleznai, C., Kropatsch, W.G.: Kernel-based Tracking Using Spatial Structure. In: Kuipers, A., Bettina Heise, L.M. (eds.) Challenges in the Biosciences: Image Analysis and Pattern Recognition Aspects. Proceedings of 32nd OEAGM Workshop, Linz, Austria, OCG-Schriftenreihe books@ocg.at, Österreichische Computer Gesellschaft, pp. 103–114, Band 232 (2008)Google Scholar
  47. 47.
    Artner, N.M., Ion, A., Kropatsch, W.G.: Rigid Part Decomposition in a Graph Pyramid. In: Eduardo Bayro-Corrochano, J.O.E. (ed.) The 14th International Congress on Pattern Recognition, CIARP 2009. LNCS. Springer, Heidelberg (2009)Google Scholar
  48. 48.
    Zhang, R., Tsai, P.S., Cryer, J., Shah, M.: Shape from Shading; A Survey. IEEE Trans. on Pattern Analysis and Machine Intelligence 21(8), 609–706 (1999)Google Scholar
  49. 49.
    Illetschko, T.: Minimal combinatorial maps for analyzing 3d data. In: Technical Report PRIP-TR-110, Institute f. Automation 183/2, Dept. for Pattern Recognition and Image Processing, TU Wien, Austria (November 2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Walter G. Kropatsch
    • 1
  1. 1.PRIPVienna University of TechnologyAustria

Personalised recommendations