Advertisement

Intelligent Visual Descriptor Extraction from Video Sequences

  • Paraskevi Tzouveli
  • Georgios Andreou
  • Gabriel Tsechpenakis
  • Yiannis Avrithis
  • Stefanos Kollias
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3094)

Abstract

Extraction of visual descriptors is a crucial problem for state-of-the-art visual information analysis. In this paper, we present a knowledge-based approach for detection of visual objects in video sequences, extraction of visual descriptors and matching with pre-defined objects. The proposed approach models objects through their visual descriptors defined in MPEG7. It first extracts moving regions using an efficient active contours technique. It then computes visual descriptions of the moving regions including color, motion and shape features that are invariant to affine transformations. The extracted features are matched to a-priori knowledge about the objects’ descriptions, using appropriately defined matching functions. Results are presented which illustrate the theoretical developments.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Akrivas, G., Wallace, M., Andreou, G., Stamou, G., Kollias, S.: Context-Sensitive Semantic Query Expansion. In: IEEE International Conference Artificial Intelligence Systems AIS 2002 (to appear)Google Scholar
  2. 2.
    Avrithis, Y., Xirouhakis, Y., Kollias, S.: Affine-invariant curve normalization for object shape representation, classification, and retrieval. Machine Vision and Applications 13, 80–94 (2001)CrossRefGoogle Scholar
  3. 3.
    Bezdek, J.C.: Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum Press, New York (1981)zbMATHGoogle Scholar
  4. 4.
    Black, M.J., Anandan, P.: The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields. In: CVIU, vol. 63(1), pp. 75–104 (1996)Google Scholar
  5. 5.
    Haykin, S.: Neural Networks, ch. 5, pp. 124–126. Macmillan College Publishing Company, Basingstoke (1994)zbMATHGoogle Scholar
  6. 6.
    Huber, P.: Robust Statistics. Wiley. (ed.) NY (1981)Google Scholar
  7. 7.
    Ip, H.S., Dinggang, S.: An Affine-Invariant Active Contour Model (AI-Snake) for Model-Based Segmentation. Image and Vision Computing 16(2), 135–146 (1998)CrossRefGoogle Scholar
  8. 8.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active Contour Models. Int. Journal of Comp. Vis. 1(4), 321–331 (1988)CrossRefGoogle Scholar
  9. 9.
    Madisetti, V.K., Williams, D.B. (eds.): The Digital Signal Processing Handbook, ch. 74, pp. 20–26. CRC Press, Boca Raton (1998)Google Scholar
  10. 10.
    ISO/IEC JTC1/SC29/WG11, Text of ISO/IEC 15938-3/FCD, Information Technology – Multimedia Content Description Interface – Part 3 Visual (October 2001)Google Scholar
  11. 11.
    Tsechpenakis, G., Xirouhakis, Y., Delopoulos, A.: A Multiresolution Approach for Main Mobile Object Localization in Video Sequences. In: International Workshop on Very Low Bitrate Video Coding (VLBV 2001), Athens, Greece (October 2001)Google Scholar
  12. 12.
    Tsechpenakis, G., Tsapatsoulis, N., Kollias, S.: Probabilistic Boundary-Based Contour Tracking with Snakes in Natural Cluttered Video Sequences. Int. Journal of Image and Graphics, IJIG (2003) (accepted)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Paraskevi Tzouveli
    • 1
  • Georgios Andreou
    • 1
  • Gabriel Tsechpenakis
    • 1
  • Yiannis Avrithis
    • 1
  • Stefanos Kollias
    • 1
  1. 1.Image, Video and Multimedia Systems Lab., School of Electrical and Computer EngineeringNational Technical University of Athens 

Personalised recommendations