Abstract
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.
Similar content being viewed by others
References
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 85–94
Bajcsy R (1988) Active perception. Proc IEEE 76:996–1005
Ballard DH (1991) Animate vision. Artificial intelligence 48:57–86
Bodington R, Sullivan GD, Baker KD (1989) Consistent labelling of image features using an assumption-based truth maintenance system. Image Vision Comput 7:43–49
Burt PJ (1988) Smart sensing within a pyramid vision machine. Proc IEEE 76:1006–1115
Denasi S, Quaglia G, Rinaudi D (1992) The use of perceptual organization in the prediction of geometric structures. Pattern Recogn Letters 13:529–539
Deriche R (1987) Using Canny's criteria to derive a recursively implemented optimal edge detector. Int J Comput Vision 18–23
Dickmanns E, Mysliwetz B (1992) Recursive 3D road and relative ego-state Recognition. IEEE PAMI 14:199–213
Duda RO, Hart PE (1972) Use of the Hough transform to detect lines and curves in pictures. Commun ACM 15:11–15
Duda RO, Nitzan D, Barrett P (1979) Use of range and reflectance data to find planar surface regions. IEEE PAMI 1:259–271
Faugeras OD, Toscani G (1986) The calibration problem for stereo. IEEE Conference on Computer Vision and Pattern Recognition, Miami, Fla. pp 15–20
Gallice J, Alizon J, Trassoudaine L (1992) The Annual Report of The PROMETHEUS Project: the works of Clermont-Ferrand University, Clermont-Ferrand, France
Gil B, Mitiche A, Aggarwal JK (1983) Experiments in combining intensity and range edge maps. Comput Vision, Graph Image Process 21:395–411
Jain A, Newman T, Goulish M (1992) Range-intensity histogram for segmenting LADAR Images. Pattern Recogn Letters 13:41–56
Kanade T, Thorpe C (1986) Autonomous land vehicle project at CMU. ACM Computer Conference, Cincinnati
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 437–452
Magee MJ, Boyter BA, Chien CH, Aggarwal JK (1985) Experiments in intensity guided range sensing recognition of three-dimensional objects. IEEE PAMI 7:629–637
Masaki I (1992) Vision-based vehicle guidance, Springer, Berlin, Heidelberg, New York
Morgenthaler DG, Hennessy SJ, DeMenthon D (1990) Range-video fusion and comparison of inverse perspective algorithms in static images. IEEE Trans Sys Man Cybernetics 20:1301–1312
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 277–281
Thorpe C (ed) (1990) Vision and navigation: the Carnegie Mellon NavLab. Kluwer, Norwell, Mass.
Thorpe C, Hebert MH, Kanade T, Shafer SA (1988) Vision and navigation for the Carnegie Mellon Navlab. IEEE PAMI 10
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 2:570–577
Turk MA, Morgenthaler DG, Gremban KD, Marra M (1988) VITS — a vision system for autonomous land vehicle navigation. IEEE PAMI 10:342–350
Worrall AD, Baker KD, Sullivan GD (1988) Model based perspective inversion. Image Vision Comput 7:17–23
Xie M, Thonnat M (1992) An algorithm for finding closed curves. Pattern Recogn Letters 13:73–81
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 865–873
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Xie, M., Trassoudaine, L., Alizon, J. et al. Road obstacle detection and tracking by an active and intelligent sensing strategy. Machine Vis. Apps. 7, 165–177 (1994). https://doi.org/10.1007/BF01211661
Issue Date:
DOI: https://doi.org/10.1007/BF01211661