Machine Vision and Applications

, Volume 7, Issue 3, pp 165–177 | Cite as

Road obstacle detection and tracking by an active and intelligent sensing strategy

  • M. Xie
  • L. Trassoudaine
  • J. Alizon
  • J. Gallice


In this paper, we address the problem of road obstacle deletion. We propose a method based on an active and intelligent sensing strategy. A sensor composed of a range finder coupled with a (charge-coupled-device) CCD camera is used. This sensor is mounted in front of a vehicle. The basic idea is first to determine 2D visual targets in intensity images of the camera. Then the range finder will be used not only to confirm or reject the existence of the detected visual targets, but also to acquire 3D information of the confirmed visual targets. The central problem of this strategy is how to detect 2D visual targets from intensity images of a road scene. In our method, we consider line segments as significant features. We use the concept ofline segment of interest and the concept ofdominant line segment. With the help of the identified dominant line segments in an image, we can effectively ascertain 2D visual targets. Finally, we use the range finder to confirm or reject a 2D visual target. A confirmed visual target is temporally tracked with the help of the range finder.

Key words

Active and intelligent sensing Visual target Road obstacle Fusion Tracking 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Alizon J, Gallice J, Trassoudaine L, Treuillet S (1990) Multisensory data fusion for obstacle detection and tracking on motorways, Proc 3rd PROMETHEUS Workshop, Torino, Italy, pp 85–94Google Scholar
  2. Bajcsy R (1988) Active perception. Proc IEEE 76:996–1005Google Scholar
  3. Ballard DH (1991) Animate vision. Artificial intelligence 48:57–86Google Scholar
  4. Bodington R, Sullivan GD, Baker KD (1989) Consistent labelling of image features using an assumption-based truth maintenance system. Image Vision Comput 7:43–49Google Scholar
  5. Burt PJ (1988) Smart sensing within a pyramid vision machine. Proc IEEE 76:1006–1115Google Scholar
  6. Denasi S, Quaglia G, Rinaudi D (1992) The use of perceptual organization in the prediction of geometric structures. Pattern Recogn Letters 13:529–539Google Scholar
  7. Deriche R (1987) Using Canny's criteria to derive a recursively implemented optimal edge detector. Int J Comput Vision 18–23Google Scholar
  8. Dickmanns E, Mysliwetz B (1992) Recursive 3D road and relative ego-state Recognition. IEEE PAMI 14:199–213Google Scholar
  9. Duda RO, Hart PE (1972) Use of the Hough transform to detect lines and curves in pictures. Commun ACM 15:11–15Google Scholar
  10. Duda RO, Nitzan D, Barrett P (1979) Use of range and reflectance data to find planar surface regions. IEEE PAMI 1:259–271Google Scholar
  11. Faugeras OD, Toscani G (1986) The calibration problem for stereo. IEEE Conference on Computer Vision and Pattern Recognition, Miami, Fla. pp 15–20Google Scholar
  12. Gallice J, Alizon J, Trassoudaine L (1992) The Annual Report of The PROMETHEUS Project: the works of Clermont-Ferrand University, Clermont-Ferrand, FranceGoogle Scholar
  13. Gil B, Mitiche A, Aggarwal JK (1983) Experiments in combining intensity and range edge maps. Comput Vision, Graph Image Process 21:395–411Google Scholar
  14. Jain A, Newman T, Goulish M (1992) Range-intensity histogram for segmenting LADAR Images. Pattern Recogn Letters 13:41–56Google Scholar
  15. Kanade T, Thorpe C (1986) Autonomous land vehicle project at CMU. ACM Computer Conference, CincinnatiGoogle Scholar
  16. Koller D, Daniilidis K, Thorhallson T, Nagel HH (1992) Model-based object tracking in traffic scenes. Proc 2nd European Conference on Computer Vision, Santa Margherita, Ligure, Italy, pp 437–452Google Scholar
  17. Magee MJ, Boyter BA, Chien CH, Aggarwal JK (1985) Experiments in intensity guided range sensing recognition of three-dimensional objects. IEEE PAMI 7:629–637Google Scholar
  18. Masaki I (1992) Vision-based vehicle guidance, Springer, Berlin, Heidelberg, New YorkGoogle Scholar
  19. Morgenthaler DG, Hennessy SJ, DeMenthon D (1990) Range-video fusion and comparison of inverse perspective algorithms in static images. IEEE Trans Sys Man Cybernetics 20:1301–1312Google Scholar
  20. Tan TN, Sullivan GD, Baker KD (1992) Structure from motion using the ground plane constraint. Proc 2nd European Conference on Computer Vision, Santa Margherita, Ligure, Italy, pp 277–281Google Scholar
  21. Thorpe C (ed) (1990) Vision and navigation: the Carnegie Mellon NavLab. Kluwer, Norwell, Mass.Google Scholar
  22. Thorpe C, Hebert MH, Kanade T, Shafer SA (1988) Vision and navigation for the Carnegie Mellon Navlab. IEEE PAMI 10Google Scholar
  23. Trassoudaine L, Treuillet S, Gallice J, Alizon J (1991) Tracking front moving objects in outdoor scenes by using a multisensory vision/telemetry system. Proc 7th Scandinavian Conference on Image Analysis, Aalborg, Denmark 2:570–577Google Scholar
  24. Turk MA, Morgenthaler DG, Gremban KD, Marra M (1988) VITS — a vision system for autonomous land vehicle navigation. IEEE PAMI 10:342–350Google Scholar
  25. Worrall AD, Baker KD, Sullivan GD (1988) Model based perspective inversion. Image Vision Comput 7:17–23Google Scholar
  26. Xie M, Thonnat M (1992) An algorithm for finding closed curves. Pattern Recogn Letters 13:73–81Google Scholar
  27. Zielke T, Brauckmann M, Seelen WV (1992) Intensity and edge-based symmetry detection applied to car-following. 2nd European Conference on Computer Vision, Santa Margherita, Ligure, Italy, pp 865–873Google Scholar

Copyright information

© Springer-Verlag 1994

Authors and Affiliations

  • M. Xie
    • 1
  • L. Trassoudaine
    • 2
  • J. Alizon
    • 2
  • J. Gallice
    • 2
  1. 1.Center for Graphics and Imaging Technology, School of Applied ScienceNanyang Technological UniversitySingapore
  2. 2.Laboratoire d'ElectroniqueUniversité de Clermont-FerrandAubiereFrance

Personalised recommendations