Detailed Visual Recognition of Road Scenes for Guiding Autonomous Vehicles

  • Ernst D. Dickmanns


Considerate re-use of elements of the Sobel-gradient operator also for corner detection in a new scheme allows unified extraction of edge-, corner- and linearly shaded blob features that can be done in real time taking recent microprocessor technology (GPUs) into account. In turn, this allows much more detailed visual recognition of complex road scenes in connection with corresponding knowledge bases on motion processes for dynamic vision. These subjects are discussed in a survey fashion as background material. The article concentrates on the new corner detection scheme looking directly for curvature components of the intensity function in several pairs of orthogonal directions. Typical results are shown for traffic scenes on highways. The new scheme is especially suited for recognizing blinking spot lights and brake (stop) lights.


Graphic Processing Unit Traffic Sign Central Pixel Corner Detection Recursive Estimation 
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.


  1. 1.
    Dickmanns ED, Zapp A (1987) Autonomous high speed road vehicle guidance by computer vision. 10th IFAC World Congr. Munich, Prepr, vol 4, pp 232-237Google Scholar
  2. 2.
    Masaki I (1992++) yearly International symposium on intelligent vehicles – Proceedings, in later years appearing under IEEE – ITSC sponsorshipGoogle Scholar
  3. 3.
    Thomanek F, Dickmanns D (1992) Obstacle d, tracking and state estimation for autonomous road vehicle guidance. IEEE/RSJ international conference on intelligent robots and systems, IROS, vol. II, Raleigh, pp 1399-1406Google Scholar
  4. 4.
    Fuerstenberg KC, Dietmayer KCJ, Willhoeft V (2002) Pedestrian recognition in urban traffic using a vehicle based multilayer laser-scanner. IEEE intelligent vehicle symposium, VersailleGoogle Scholar
  5. 5.
    Wang CC, Thorpe C, Suppe A (2003) Ladar-based detection and tracking of moving objects from a ground vehicle at high speeds. IEEE-symposium on intelligent vehicles (IV)Google Scholar
  6. 6.
    Fuerstenberg KC, Dietmayer KCJ (2004) Object tracking and classification for multiple active safety and comfort applications using a multilayer laserscanner. IEEE-symposium on intelligent vehicles, Parma, pp 807-812Google Scholar
  7. 7.
    von Holt V (2004) Integrale Multisensorielle Fahrumgebungserfassung nach dem 4D-Ansatz. Dissertation, UniBwM, LRTGoogle Scholar
  8. 8.
    DARPA (2006) Urban challenge, route network definition file (RNDF) and mission data file (MDF) formats, May 12Google Scholar
  9. 9.
    Dickmanns ED (1995) Road vehicle eyes for high precision navigation. In: Linkwitz et al (eds) High precision navigation. Dümmler, Bonn, pp 329-336Google Scholar
  10. 10.
    Dickmanns ED (2007) Dynamic vision for perception and control of motion. Springer, LondonGoogle Scholar
  11. 11.
    Dickmanns ED (1987) 4-D dynamic scene analysis with integral spatio-temporal models. In: Bolles R, Roth B (eds) Robotics research, 4th international symposium, MIT Press, Cambridge, MAGoogle Scholar
  12. 12.
    Gregor R, Lützeler M, Pellkofer M, Siedersberger K-H, Dickmanns ED (2000) EMS-vision: A perceptual system for autonomous vehicles. IEEE intelligent vehicle symposium, Dearborn, pp 52–57Google Scholar
  13. 13.
    Gregor R, Dickmanns ED (2000) EMS-vision: Mission performance on road networks. IEEE intelligent vehicle symposium, Dearborn, pp 140-145Google Scholar
  14. 14.
    Goebl M, Faerber G (2007) A real-time-capable hard- and software architecture for joint image and knowledge processing in cognitive automobiles. Proceedings of the IEEE intelligent vehicle symposium, IEEE-Press, p 734-740Google Scholar
  15. 15.
    Hofmann U (2004) Zur visuellen Umfeldwahrnehmung autonomer Fahrzeuge. Dissertation, UniBw Munich, LRTGoogle Scholar
  16. 16.
    Kuehnle A (1991) Symmetry-based recognition of vehicle rears. In: Pattern recognition letters, vol 12. North-Holland, pp 249–258Google Scholar
  17. 17.
    Zielke T, Brauckmann M, von Seelen W (1993) Intensity and edge-based symmetry detection with an application to car following. CGVIP: Image Understanding 58:177–190Google Scholar
  18. 18.
    Schmid M (1993) 3-D-Erkennung von Fahrzeugen in Echtzeit aus monokularen Bildfolgen. Dissertation UniBw Munich, LRT Also: Fortschrittsberichte VDI Verlag, Reihe 10, Nr. 293Google Scholar
  19. 19.
    Thomanek F (1996) Visuelle Erkennung und Zustandsschätzung von mehreren Straßenfahrzeugen zur autonomen Fahrzeugführung. Dissertation, UniBw Munich, LRT. Also: Fortschrittsberichte VDI Verlag, Reihe 12, Nr. 272Google Scholar
  20. 20.
    Estable S, Schick J, Stein F, Janssen R, Ott R, Ritter W, Zheng YJ (1994) A real-time traffic sign recognition system. In: Proceedings of the international symposium on intelligent vehicles’94, Paris, pp 213–218Google Scholar
  21. 21.
    Schiehlen J (1995) Kameraplattformen fuer aktiv sehende Fahrzeuge. Dissertation, UniBw Munich, LRT. Also: Fortschrittsberichte VDI Verlag, Reihe 8, Nr. 514Google Scholar
  22. 22.
    Lützeler M (2002) Fahrbahnerkennung zum Manövrieren auf Wegenetzen mit aktivem Sehen. Dissertation, UniBw Munich, LRTGoogle Scholar
  23. 23.
    Pellkofer M (2003) Verhaltensentscheidung für autonome Fahrzeuge mit Blickrichtungs-steuerung. Dissertation, UniBw Munich, LRTGoogle Scholar
  24. 24.
    Fuchs T (2008) Das Gehirn – ein Beziehungsorgan. KohlhammerGoogle Scholar
  25. 25.
    Dickmanns ED (2006) Corner detection with minimal effort on multiple scales. Proceedings of Vision Application (VISAPP), SetubalGoogle Scholar
  26. 26.
    Dickmanns ED (2008) Generalized Nonplanarity Features. UniBwM/LRT/TAS/TR 2008–08Google Scholar
  27. 27.
    Harris C, Stephens M (1988) A combined corner and edge detector. In: Alvey vision conference, pp 147-151Google Scholar
  28. 28.
    Tomasi C, Kanade T (1991) Detection and tracking of point features. CMU, Tech. Rep. CMU-CS-91–132, Pittsburgh, PAGoogle Scholar
  29. 29.
    Schweitzer M, Wuensche H-J (2009) Efficient keypoint matching for robot vision using GPUs. In: Proceedings of the 5th IEEE workshop on embedded computer vision (ECVW), ICCV-KyotoGoogle Scholar
  30. 30.
    Bay H, Tuytelaars T, Gool LV (2006) Surf: Speeded up robust features. In: Proceedings of ECCVGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.UniBw Munich/LRT/TASNeubibergGermany

Personalised recommendations