Abstract
This paper addresses the problem of obstacle detection for mobile robots. The visual information provided by a single on-board camera is used as input. We assume that the robot is moving on a planar pavement, and any point lying outside this plane is treated as an obstacle. We address the problem of obstacle detection by exploiting the geometric arrangement between the robot, the camera, and the scene. During an initialization stage, we estimate an inverse perspective transformation that maps the image plane onto the horizontal plane. During normal operation, the normal flow is computed and inversely projected onto the horizontal plane. This simplifies the resultant flow pattern, and fast tests can be used to detect obstacles. A salient feature of our method is that only the normal flow information, or first order time-and-space image derivatives, is used, and thus we cope with the aperture problem. Another important issue is that, contrasting with other methods, the vehicle motion and intrinsic and extrinsic parameters of the camera need not be known or calibrated. Both translational and rotational motion can be dealt with. We present motion estimation results on synthetic and real-image data. A real-time version implemented on a mobile robot, is described.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aloimonos Y (1990) Purposive and qualitative active vision. Proceedings of the 10th IEEE International Conference on Pattern Recognition, Atlantic City, NJ USA, IEEE Computer Society Press, pp 346–360
Aloimonos Y, Duvic Z (1994) Estimating the heading direction using normal flow. Int J Comput Vision 13:33–56
Carlsson S, Eklundh J (1990) Obstacle detection using model based prediction and motion parallax. Proceedings of the 1st European Conference on Comput Vision, Antibes, France, Springer, Berlin Heidelberg New York, pp 297–306
Cipolla R, Blake A (1992) Surface orientation and time to contact from image divergence and deformation. Proceedings of the 2nd European Conference on Computer Vision, Santa Margherita, Italy, Springer, Berlin Heidelberg New York, pp 187–202
Cipolla R, Okamoto Y, Kuno Y (1993) Robust structure from motion using motion parallax. Proceedings of the 4th International Conference on Computer Vision, Berlin, IEEE Computer Society Press, pp 374–382
Enkelmann W (1990) Obstacle detection by evaluation of optical flow field from image sequences. Proceedings of the 1st European Conference on Computer Vision, Antibes, France, Springer, Berlin Heidelberg New York pp 134–138
Fermüller C (1993) Global 3D motion estimation. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition CVPR, New York, IEEE Computer Society Press, pp 415–421
Fermüller C (1993) Navigational preliminaries. In: Aloimonos Y (ed) Active perception. Lawrence Erlbaum, New Jersey
Gelb A (1974) Applied optimal estimation. MIT Press, Cambridge
Girosi F, Verri A, Torre V (1989) Constraints for the computation of optical flow. Proceedings of the IEEE Worskhop on Visual Motion, Irvine, CA, IEEE Computer Society Press, pp 116–124
Horn B (1986) Robot vision. MIT Press, Cambridge
Horn BKP, Shunck B (1981) Determining optical flow. Artificial Intell 17:185–203
Horn BKP, Weldon EJ (1988) Direct methods for recovering motion. Int J Comput Vision 2:51–76
Irani M, Rousso B, Peleg P (1994) Recovery of ego-motion using image stabilization. Proceedings of the IEEE International Conference on Compuer Vision and Pattern Recognition CVPR, Seattle, IEEE Computer Society Press, pp 454–460
Koenderink J, van Doom J (1991) Affine structure from motion. J Opt Soc Ame 8:377–385
Little JJ, Verri A (1989) Analysis of differential and matching methods for optical flow. Proceedings of the IEEE Worskhop on Visual Motion, Irvine, CA, IEEE Computer Society Press, pp 173–180
Mallot H, Bulthoff H, Little J, Bohrer S (1991) Inverse perspective mapping simplifies opticla flow computation and obstacle detection. Biol Cybernetics 64:177–185
Nagel H (1983) Displacement vectors derived from second-order intensity variations in image sequence. Computer Vision Graphics and Image Processing 21:85–117
Nagel HH (1987) On the estimation of optical flow: relations between different approaches and some new results. Artif Intell 33:299–323
Nagel H, Enkelmann W (1986) An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Trans PAMI 8:565–593
Negahdaripour S, Lee S (1992) Motion recovery from images sequences using only first order optical flow information. Int J Comput Vision 9:163–184
Sandini G, Tistarelli M (1990) Robust obstacle detection using optical flow. Proceedings of the IEEE International Workshop on Robust Comput Vision, Seattle, IEEE Computer Society Press, pp 396–411
Santos-Victor J, Sandini G, Curotto F, Garibaldi S (1993) Divergent stereo for robot navigation: learning from bees. In IEEE International Conference on Computer Vision and Pattern Recognition, IEEE Computer Society Press, pp 434–439
Santos-Victor J, Sandini G, Curotto F, Garibaldi S (1995) Divergent stereo in autonomous navigation: from bees to robots. Int J Comput Vision 14:159–177
Sinclair D, Blake A, Murray D (1994) Robust estimation of egomotion from normal flow. Int J Comput Vision 13:57–70
Subbarao M, Waxman A (1986) Closed form solutions to image flow equations for planar surfaces in motion. Comput Vision Graph Image Processing 36:208–228
Sundareswaran W (1991) Egomotion from global flow field data. Proceedings of the IEEE Workshop on Visual Motion, Princeton, NJ, IEEE Computer Society Press, pp 140–145
Wang J, Adelson E (1993) Layered representation for motion analysis. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, IEEE Computer Society Press, pp 361–366
Zielke T, Storjohann K, Mallot H, Seelen W (1990) Adapting computer vision systems to visual environment: topographic mapping. Proceedings of the 1st European Conference on Computer Vision, Antibes, France, Springer, Berlin Heidelberg New York, pp 613–615
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Santos-Victor, J., Sandini, G. Uncalibrated obstacle detection using normal flow. Machine Vis. Apps. 9, 130–137 (1996). https://doi.org/10.1007/BF01216818
Issue Date:
DOI: https://doi.org/10.1007/BF01216818