Movatterモバイル変換

[0]ホーム
URL:

Skip to main content

Advertisement

Springer Nature Link
Log in

Lateral Interaction in Accumulative Computation: Motion-Based Grouping Method

  • Conference paper

Abstract

To be able to understand the motion of non-rigid objects, techniques in image processing and computer vision are essential for motion analysis. Lateral interaction in accumulative computation for extracting non-rigid blobs and shapes from an image sequence has recently been presented, as well as its application to segmentation from motion. In this paper we show an architecture consisting of five layers based on spatial and temporal coherence in visual motion analysis with application to visual surveillance. The LIAC method used in general task ”spatio-temporal coherent shape building” consists in (a) spatial coherence for brightness-based image segmentation, (b) temporal coherence for motion-based pixel charge computation, (c) spatial coherence for charge-based pixel charge computation, (d) spatial coherence for charge-based blob fusion, and, (e) spatial coherence for charge-based shape fusion. In our case, temporal coherence (in accumulative computation) is understood as a measure of frame to frame motion persistency on a pixel, whilst spatial coherence (in lateral interaction) is a measure of pixel to neighbouring pixels accumulative charge comparison.

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

Access this chapter

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Huang, T.S.: Image Sequence Analysis. Springer, Heidelberg (1983)

    Google Scholar 

  2. Aggarwal, J.K., Nandhakumar, N.: On the computation of motion from sequences of images - A review. Proceedings of the IEEE 76(8) (1988)

    Google Scholar 

  3. Wang, J., Huang, T.S., Ahuja, N.: Motion and Structure from Image Sequences. Springer, Heidelberg (1993)

    Google Scholar 

  4. Little, J.J., Boyd, J.E.: Recognizing people by their gait: The shape of motion. Videre: Journal of Computer Vision Research 1(2), 2–32 (1998)

    Google Scholar 

  5. Polana, R., Nelson, R.: Detecting activities. In: Proceedings of the IEEE Conference on Com-puter Vision and Pattern Recognition, pp. 2–7 (1993)

    Google Scholar 

  6. Polana, R., Nelson, R.: Recognition of nonrigid motion. In: Proceedings DARPA Image Understanding Workshop, pp. 1219–1224 (1994)

    Google Scholar 

  7. Bobick, A.F., Davis, J.W.: An appearance-based representation of action. In: Proceedings 13th International Conference on Pattern Recognition, pp. 307–312 (1996)

    Google Scholar 

  8. Yang, M.-H., Ahuja, N.: Extracting gestural motion trajectories. In: Proceedings 2nd International Conference on Automatic Face and Gesture Recognition, pp. 10–15 (1998)

    Google Scholar 

  9. Olson, T., Brill, F.: Moving object detection and event recognition algorithms for smart cameras. In: Proceedings DARPA Image Understanding Workshop, pp. 159–175 (1997)

    Google Scholar 

  10. Fernández, M.A., Fernández-Caballero, A., López, M.T., Mira, J.: Length-speed ratio (LSR) as a characteristic for moving elements real-time classification. Real-Time Imaging 9, 49–59 (2003)

    Article  Google Scholar 

  11. Fernández-Caballero, A., Fernández, M.A., Mira, J., Delgado, A.E.: Spatio-temporal shape building from image sequences using lateral interaction in accumulative computation. Pattern Recognition 36(5), 1131–1142 (2003)

    Article MATH  Google Scholar 

  12. Mira, J., Delgado, A.E., Fernández-Caballero, A., Fernández, M.A.: Knowledge modelling for the motion detection task: The algorithmic lateral inhibition method. Expert Systems with Applications 27(2), 169–185 (2004)

    Article  Google Scholar 

  13. Fernández-Caballero, A., Mira, J., Fernández, M.A., López, M.T.: Segmentation from motion of non-rigid objects by neuronal lateral interaction. Pattern Recognition Letters 22(14), 1517–1524 (2001)

    Article MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Universidad de Castilla-La Mancha, E.P.S.A., 02071, Albacete, Spain

    Antonio Fernández-Caballero, Miguel A. Fernández & Maria T. López

  2. Universidad Nacional de Educación a Distancia, E.T.S.I. Informática, 28040, Madrid, Spain

    Jose Mira & Ana E. Delgado

Authors
  1. Antonio Fernández-Caballero

    You can also search for this author inPubMed Google Scholar

  2. Jose Mira

    You can also search for this author inPubMed Google Scholar

  3. Ana E. Delgado

    You can also search for this author inPubMed Google Scholar

  4. Miguel A. Fernández

    You can also search for this author inPubMed Google Scholar

  5. Maria T. López

    You can also search for this author inPubMed Google Scholar

Editor information

Editors and Affiliations

  1. Istituto di Cibernetica “Eduardo Caianiello”, CNR, Pozzuoli (NA), Italy

    Massimo De Gregorio

  2. Istituto di Cibernetica “E. Caianiello” del CNR, Via Campi Flegrei, 34, 80078, Pozzuoli (NA), Italy

    Vito Di Maio

  3. Institute of Cybernetics “E. Caianiello”, CNR, Pozzuoli, (Naples), Italy

    Maria Frucci

  4. Istituto di Cibernetica “Eduardo Caianiello”, CNR, Pozzuoli, Italy

    Carlo Musio

Rights and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Fernández-Caballero, A., Mira, J., Delgado, A.E., Fernández, M.A., López, M.T. (2005). Lateral Interaction in Accumulative Computation: Motion-Based Grouping Method. In: De Gregorio, M., Di Maio, V., Frucci, M., Musio, C. (eds) Brain, Vision, and Artificial Intelligence. BVAI 2005. Lecture Notes in Computer Science, vol 3704. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11565123_38

Download citation

Publish with us

[8]ページ先頭
©2009-2025 Movatter.jp