Abstract
This paper describes the development and implementation of some layers of a line-segment-based module to recover ego motion while building a 3D map of the environment in which the absolute vertical is taken into account. We use a monocular sequence of images and 2D-line segments in this sequence. The proposed method reduces the disparity between two frames in such a way that 3D vision is simplified. In particular, the correspondence problem is simplified. Moreover, a estimation of the 3D rotation is provided.
Using the vertical as a basic cue for 3D-orientation tremendously simplifies and improves the structure from motion paradigm, but the usual equations have to be worked out in a different way.
An approach which combines ecological hypotheses and general rigid motion equations is presented, and the equations are derived and discussed in the case of small rigid motions. Algorithms, based on the minimization of theMahalanobis distance between two estimates, are given and their implementations discussed.
Similar content being viewed by others
References
Belluta P, Collini G, Verri A, Torre V (1989) 3D visual information from vanishing points. In: Proceedings of the Workshop on Interpretation of 3D Scenes, Austin. IEEE Computer Society Press, Los Alamitos, CA
Carlsson S (1991) Projectively invariant representation of planar shape. In: Fifth Scandinavian Workshop on Computational Vision. Royal College of Stockholm, Sweden
Deriche R, Faugeras OD (1990): Tracking line segments. In: Proceedings of the 1st ECCV, Antibes. Springer, Berlin Heidelberg New York, pp 259–269
Fang J, Huang T (1984) Some experiments on estimating the 3-D motion parameters of a rigid body from two consecutive image frames. IEEE Trans Pattern Anal Machine Intell 6:547–554
Faugeras O (1993) Three-dimensional computer vision: a geometric viewpont. MIT Press, Boston
Faugeras OD, Lustman F, Toscani G (1987) Motion and structure from point and line matches. In: Proceedings of the First International Conference on Computer Vision. London, pp 25–34
Faugeras OD, Deriche R, Ayache N, Lustman F, Giuliano E (1988) Depth and motion analysis: the machine being developed within esprit project 940. In: Proceedings of the IAPR Workshop on Computer Vision (Special Hardware and Industrial Applications). Institute of Industrial Science, University of Tokyo, pp 35–44
Francois E, Bouthemy P (1991) Multiframe-based identification of mobile components of a scene with a moving camera. In: Conference Computer Vision and Pattern Recognition, Hawai. IEEE Computer Society Press, Los Alamitos, CA, pp 166–172
Giai-Checa B, Viéville T (1992) 3D-vision for active visual loops using locally rectilinear edges. In: Henderson T (ed) Seventh IEEE Symposium on Intelligent Control, Glasgow. IEEE Computer Society Press, pp 341–347
Gibson J (1979) The Ecological Approach to Visual Perception. Lawrence Erlbaum Associates, London
Kanatani K (1990) Hypothesizing and testing geometric attributes of image data: In: Proceedings of the 3rd ICCV, Osaka, Japan. IEEE Computer Society Press, Los Alamitos, CA, pp 370–373
Lebègue X, Aggarwal J (1992) Detecting 3D parallel lines for perceptual organization. In: 2nd ECC, Genoa. Springer, Berlin Heidelberg New York, pp 720–724
Lenz R (1990) Group theoretical methods in image processing (Lectures Notes in Computer Science, vol 314). Springer, Berlin Heidelberg New York
Liu Y, Huang TS (1988) Estimation of rigid body motion using straight line correspondences. In: Computer Vision, Graphics and Image Processing 44:35–57
Longuet-Higgins HC (1981) A computer algorithm for reconstructing a scene from two projections. Nature 293:133–135
Mitiche A, Seida S, Aggarwal JK (1986) Interpretation of structure and motion using straight line correspondences. In: Proceedings of the 8th ICPR, Paris. IEEE Computer Society Press, Los Alamitos, CA, pp 1110–1112
Weiss RS, Collins RT (1990) Vanishing point calculation as a statistical inference on the unit sphere. In: Proceedings of the 3rd ICCV, Osaka, Japan. IEEE Computer Society Press, Los Alamitos, CA, pp 400–405
Shigang L, Tsuji F, Imai M (1990) Determining camera rotation from vanishing points of lines on horizontal planes. In: Proceedings of the 3rd ICCV, Osaka, Japan. IEEE Computer Society Press, Los Alamitos, CA, pp 499–502
Viéville T (1990) Estimation of 3D-motion and structure from tracking 2D-lines in a sequence of images. In: Proceedings of the 1st ECCV, Antibes. Springer, Berlin Heidelberg New York, pp 281–292
Viéville T (1991) Real time gaze control: architecture for sensing behaviours. In: Eklund O (ed) The 1991 Stockholm Workshop on Computational Vision, Rosenon, Sweden. Royal Institute of Technology, Stockholm, Sweden
Viéville T, Faugeras O (1989) Computation of inertial information on a robot. In: Miura H, Suguru A (eds) Fifth International Symposium on Robotics Research. MIT Press, Cambridge, pp 57–65
Viéville T, Faugeras O (1989) Cooperation of the inertial and visual systems. In: Henderson T (ed) Traditional and non-traditional robotic sensors. Springer, Berlin Heidelberg New York, pp 339–350
Viéville T, Faugeras O (1990) Feed forward recovery of motion and structure from a sequence of 2D-lines matches. In: Tsuji S, Kak A, Eklundh JO (eds) Third International Conference on Computer Vision, Osaka. IEEE Computer Society Press, Los Alamitos, California, pp 517–522
Author information
Authors and Affiliations
Corresponding author
Additional information
Based on “Computation of ego motion and structure from visual and inertial sensors using the vertical cue” by T. Viéville and P.E.D.S. Facao and E. Clergue, which appeared in the Fourth International Conference on Computer Vision, Berlin, 1993 May 11–14, pages 591–598, ©1993 IEEE
Rights and permissions
About this article
Cite this article
Viéville, T., Clergue, E. & Facao, P.E.D.S. Computation of ego motion using the vertical cue. Machine Vis. Apps. 8, 41–52 (1995). https://doi.org/10.1007/BF01213637
Issue Date:
DOI: https://doi.org/10.1007/BF01213637