Advertisement

Association of motion verbs with vehicle movements extracted from dense optical flow fields

  • H. Kollnig
  • H. -H. Nagel
  • M. Otte
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 801)

Abstract

This contribution addresses the problem of detection and tracking of moving vehicles in image sequences from traffic scenes recorded by a stationary camera. By replacing the low level vision system component for the estimation of displacement vectors by an optical flow estimation module we are able to detect all moving vehicles in our test image sequence. By replacing the edge detector and by doubling the sampling rate we improve the model-based object tracking system significantly compared to an earlier system. The trajectories of vehicles are characterized by motion verbs and verb phrases. Results from various experiments with real world traffic scenes are presented.

Keywords

Image Sequence Optical Flow Edge Element Conceptual Description Motion Verb 
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. [André et al. 88]
    E. André, G. Herzog, T. Rist, On the Simultaneous Interpretation of Real World Image Sequences and their Natural Language Descriptions: The System Soccer, in Y. Kodratoff (ed.), Proc. 8th Europ. Conf. on Artificial Intelligence, München, Aug. 1–5, 1988, pp. 449–454.Google Scholar
  2. [Birnbaum et al. 93]
    L. Birnbaum, M. Brand, P. Cooper, Looking for Trouble: Using Causal Semantics to Direct Focus of Attention, in Proc. Int. Conf. on Computer Vision (ICCV '93), Berlin, Germany, May 11–14, 1993, pp. 49–56.Google Scholar
  3. [Campani & Verri 92]
    M. Campani, A. Verri, Motion Analysis from First-Order Properties of Optical Flow, Computer Vision, Graphics, and Image Processing 56 (1992) 90–107.Google Scholar
  4. [Deriche & Faugeras 90]
    R. Deriche, O. Faugeras, Tracking line segments, Image and Vision Computing 8:4 (1990) 261–270.Google Scholar
  5. [Du et al. 93]
    L. Du, G. D. Sullivan, K. D. Baker, Quantitative Analysis of the Viewpoint Consistency Constraint in Model-Based Vision, in Proc. Int. Conf. on Computer Vision (ICCV '93), Berlin, Germany, May 11–14, 1993, pp. 632–639.Google Scholar
  6. [Gong & Buxton 93]
    S. Gong, H. Buxton, From Contextual Knowledge to Computational Constraints, in Proc. Brit. Machine Vision Conf., Guildford, UK, Sept. 21–23, 1993, pp. 229–238.Google Scholar
  7. [Heinze et al. 91]
    N. Heinze, W. Krüger, H.-H. Nagel, Berechnung von Bewegungsverben zur Beschreibung von aus Bildfolgen gewonnenen Fahrzeugtrajektorien in Straßenverkehrsszenen (in German), Informatik — Forschung und Entwicklung 6 (1991) 51–61.Google Scholar
  8. [Herzog 92]
    G. Herzog, Utilizing Interval-Based Event Representations for Incremental High-Level Scene Analysis, in Proc. Fourth European Workshop on Semantics of Time, Space and Movement and Spatio-Temporal Reasoning, Château de Bonas, France, Sept. 4–8, 1992, pp. 425–435.Google Scholar
  9. [Koller 92]
    D. Koller, Detektion, Verfolgung und Klassifikation bewegter Objekte in monokularen Bildfolgen am Beispiel von StraΒenverkehrsszenen (in German), Dissertation, Fakultät für Informatik der Universität Karlsruhe (TH), Karlsruhe, Juni 1992, available as vol. DISKI 13, Dissertationen zur Künstlichen Intelligenz, infix-Verlag, Sankt Augustin, Deutschland, 1992.Google Scholar
  10. [Koller et al. 91]
    D. Koller, N. Heinze, H.-H. Nagel, Algorithmic Characterization of Vehicle Trajectories from Image Sequences by Motion Verbs, in IEEE Conf. Computer Vision and Pattern Recognition (CVPR '91), Lahaina, Maui, Hawaii/HI, June 3–6, 1991, pp. 90–95.Google Scholar
  11. [Koller et al. 93]
    D. Koller, K. Daniilidis, H.-H. Nagel, Model-Based Object Tracking in Monocular Image Sequences of Road Traffic Scenes, Intern. Journal of Comp. Vision 10:3 (1993) 257–281.Google Scholar
  12. [Kollnig & Nagel 93]
    H. Kollnig, H.-H. Nagel, Ermittlung von begrifflichen Beschreibungen von Geschehen in Straßenverkehrsszenen mit Hilfe unscharfer Mengen (in German), Informatik — Forschung und Entwicklung 8 (1993) 186–196.Google Scholar
  13. [Kories & Zimmermann 86]
    R. Kories, G. Zimmermann, A Versatile Method for the Estimation of Displacement Vector Fields from Image Sequences, in Proc. of IEEE Workshop on Motion: Representation and Analysis, Kiawah Island Resort,Charleston/SC,May 7–9, 1986,pp. 101–106.Google Scholar
  14. [Liu & Huang 93]
    Y. Liu, T.S. Huang, Vehicle-Type Motion Estimation from Multi-frame Images, IEEE Trans. on Pattern Analysis and Machine Intelligence PAMI-15:8 (1993) 802–808.Google Scholar
  15. [Lowe 92]
    D. G. Lowe, Robust Model-Based Motion Tracking Through the Integration of Search and Estimation, International Journal of Computer Vision 8:2 (1992) 113–122.Google Scholar
  16. [Mohnhaupt & Neumann 90]
    M. Mohnhaupt, B. Neumann, On the Use of Motion Concepts for Top-Down Control in Traffic Scenes, in O. Faugeras (ed.), Proc. Second European Conference on Computer Vision (ECCV '90), Antibes, France, Apr. 23–26, 1990, Lecture Notes in Computer Science 427, Springer-Verlag, Berlin, Heidelberg, New York/NY and others, 1990, pp. 598–600.Google Scholar
  17. [Nagel 88]
    H.-H. Nagel, From Image Sequences towards Conceptual Descriptions, Image and Vision Computing 6:2 (1988) 59–74.Google Scholar
  18. [Nagel 91]
    H.-H. Nagel, La représentation de situations et leur reconnaissance à partir de séquences d'images — The Representation of Situations and their Recognition from Image Sequences, in 8e Congrès Reconnaissance des Formes et Intelligence Artificielle, Lyon—Villeurbanne, 25–29 Novembre 1991, AFCET, 1991, pp. 1221–1229.Google Scholar
  19. [Nagel & Kollnig 94]
    H.-H. Nagel, H. Kollnig, Description of the Motion of Road Vehicle Agglomerations in Image Sequences by Natural Language Verbs (1994). In preparation.Google Scholar
  20. [Neumann & Novak 86]
    B. Neumann, H.-J. Novak, Naos: Ein System zur natürlichsprachlichen Beschreibung zeitveränderlicher Szenen, Informatik-Forschung und Entwicklung 1 (1986) 83–92.Google Scholar
  21. [Otte & Nagel 92a]
    M. Otte, H.-H. Nagel, Extraction of Line Drawings from Gray Value Images by Non-Local Analysis of Edge Element Structures, in G. Sandini (ed.), Proc. Second European Conference on Computer Vision (ECCV '92), S. Margherita Ligure, Italy, May 18–23, 1992, Lecture Notes in Computer Science 588, Springer-Verlag, Berlin and others, 1992, pp. 687–695.Google Scholar
  22. [Otte & Nagel 92b]
    M. Otte, H.-H. Nagel, Verbesserte Extraktion von Strukturen aus Kantenelementbildern durch Auswertung von Kantenelementketten (in German), Interner Bericht, Institut für Algorithmen und Kognitive Systeme, Fakultät für Informatik der Universität Karlsruhe (TH), Karlsruhe, Deutschland, Oktober 1992.Google Scholar
  23. [Otte & Nagel 94]
    M. Otte, H.-H. Nagel, Optical Flow Estimation: Advances and Comparisons, in: Proc. Third Europ. Conf. on Computer Vision ECCV '94, Stockholm, Sweden, May 2–6, 1994.Google Scholar
  24. [Retz-Schmidt 91]
    G. Retz-Schmidt, Recognizing Intentions, Interactions and Causes of Plan Failures, User Modeling and User-Adapted Interaction 1:2 (1991) 173–202.Google Scholar
  25. [Sung 88]
    C.-K. Sung, Extraktion von typischen und komplexen Vorgängen aus einer Bildfolge einer Verkehrsszene (in German), in H. Bunke, O. Kübler, P. Stucki (Hrsg.), Mustererkennung 1988, Zürich, Informatik-Fachberichte 180, Springer-Verlag, Berlin u.a., 1988, pp. 90–96.Google Scholar
  26. [Tan et al. 92]
    T. N. Tan, G. D. Sullivan, K. D. Baker, Linear Algorithms for Object Pose Estimation, in Proc. British Machine Vision Conference, Leeds, UK, Sept. 22–24, 1992, pp. 600–609.Google Scholar
  27. [Tan et al. 93]
    T. N. Tan, G. D. Sullivan, K. D. Baker, Recognising Objects on the Ground Plane, in Proc. British Machine Vision Conference, Guildford, UK, Sept. 21–23, 1993, pp. 85–94.Google Scholar
  28. [Toal & Buxton 92]
    A. F. Toal, H. Buxton, Spatio-temporal Reasoning within a Traffic Surveillance System, in G. Sandini (ed.), Proc. Second European Conference on Computer Vision (ECCV '92), S. Margherita Ligure, Italy, May 18–23, 1992, Lecture Notes in Computer Science 588, Springer-Verlag, Berlin, Heidelberg, New York/NY and others, 1992, pp. 884–892.Google Scholar
  29. [Worrall et al. 93]
    A. D. Worrall, G. D. Sullivan, K. D. Baker, Advances in Model-Based Traffic Vision, in Proc. Brit. Machine Vision Conf., Guildford, UK, Sept. 21–23, 1993, pp. 559–568.Google Scholar
  30. [Zhang et al. 93]
    S. Zhang, G. D. Sullivan, K. D. Baker, The Automatic Construction of a View-Independent Relational Model for 3-D Object Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-15:6 (1993) 531–544.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • H. Kollnig
    • 1
  • H. -H. Nagel
    • 1
    • 2
  • M. Otte
    • 1
  1. 1.Institut für Algorithmen und Kognitive SystemeFakultät für Informatik der Universität Karlsruhe (TH)KarlsruheGermany
  2. 2.Fraunhofer-Institut für Informations- und Datenverarbeitung (IITB)KarlsruheGermany

Personalised recommendations