Active egomotion estimation: A qualitative approach

  • Yiannis Aloimonos
  • Zoran Duriç
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 588)


Passive navigation refers to the ability of an organism or a robot that moves in its environment to determine its own motion precisely on the basis of some perceptual input, for the purposes of kinetic stabilization. The problem has been treated, for the most part, as a general recovery from dynamic imagery problem, and it has been formulated as the general 3-D motion estimation (or structure from motion) module. Consequently, if a robust solution to the passive navigation problem—as it has been formulated in the recovery paradigm—is achieved, we will immediately be able to solve many other important problems, as simple applications of the general principle. However, despite numerous theoretical results, no technique has found applications in systems that can perform well in the real world. In this paper, we outline some of the reasons behind this and we develop a robust solution to the passive navigation problem which is
  • purposive, in the sense that it does not claim any generality. It just solves the kinetic stabilization problem and cannot be used as it is for other problems related to 3-D motion.

  • qualitative, in the sense that the solution comes as the answer to a series of simple yes/no questions and not as the result of complicated numerical processing.

  • active, in the sense that the activity of the observer (in this case “saccades”) is essential for the solution of the problem.

The input to the perceptual process of kinetic stabilization that we have developed is the normal flow, i.e. the projection of the optic flow along the direction of the image gradient.

Contributions of this work are the fact that translation can be estimated reliably from a normal flow field that also contains rotation.


Motion Estimation Half Plane Normal Flow Visual Motion Inertial Sensor 
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. Adiv, G.: Determining three-dimensional motion and structure from optical flow generated by several moving objects. IEEE Trans. PAMI 7 (1985a) 384–401.Google Scholar
  2. Adiv, G.: Inherent ambiguities in recovering 3D motion and structure from a noisy flow field. Proc. IEEE Conference on Computer Vision and Pattern Recognition (1985b) 70–77.Google Scholar
  3. Aloimonos, J.: Purposive and qualitative active vision. Proc. DARPA Image Understanding Workshop (1990a) 816–828.Google Scholar
  4. Aloimonos, J.: Perspective approximations. Image and Vision Computing 8 (1990b) 177–192.Google Scholar
  5. Aloimonos, J., Brown, CM.: The relationship between optical flow and surface orientation. Proc. International Conference on Pattern Recognition, Montreal, Canada (1984).Google Scholar
  6. Aloimonos, J., Weiss, I., Bandopadhay, A.: Active vision. Int'l. J. Comp. Vision 2 (1988) 333–356.Google Scholar
  7. Ballard, D.H.: Parameter networks. Artificial Intelligence 22 (1984) 235–267.Google Scholar
  8. Bruss, A., Horn, B.K.P.: Passive navigation. Computer Vision, Graphics Image Processing 21 (1983) 3–20.Google Scholar
  9. Duriç, Z., Aloimonos, J.: Passive navigation: An active and purposive solution. Technical Report CAR-TR-560, Computer Vision Laboratory, Center for Automation Research, University of Maryland, College Park (1991).Google Scholar
  10. Horn, B.K.P.: Relative Orientation. MIT AI Memo 994 (1988).Google Scholar
  11. Horn, B.K.P., Weldon, E.J.: Computationally efficient methods of recovering translational motion. Proc. International Conference on Computer Vision (1987) 2–11.Google Scholar
  12. Longuet-Higgins, H.C.: A computer algorithm for reconstructing a scene from two projections. Nature 293 (1981) 133–135.Google Scholar
  13. Longuet-Higgins, H.C., Prazdny, K.: The interpretation of a moving retinal image. Proc. Royal Soc. London B 208 (1980) 385–397.Google Scholar
  14. Marr, D.: Vision (W.H. Freeman, San Francisco (1982).Google Scholar
  15. Negahdaripour, S.: Ph.D. Thesis, MIT Artificial Intelligence Laboratory (1986).Google Scholar
  16. Nelson, R.C., Aloimonos, J.: Finding motion parameters from spherical flow fields (Or the advantages of having eyes in the back of your head). Biological Cybernetics 58 (1988) 261–273.PubMedGoogle Scholar
  17. Nelson, R., Aloimonos, J.: Using flow field divergence for obstacle avoidance in visual navigation. IEEE Trans. PAMI 11 (1989) 1102–1106.Google Scholar
  18. Spetsakis, M.E., Aloimonos, J.: Optimal computing of structure from motion using point correspondences in two frames. Proc. International Conference on Computer Vision (1988).Google Scholar
  19. Spetsakis, M.E., Aloimonos, J.: Unification theory of structure from motion. Technical Report CAR-TR-482, Computer Vision Laboratory, Center for Automation Research, University of Maryland, College Park (1989).Google Scholar
  20. Spetsakis, M.E., Aloimonos, J.: Structure from motion using line correspondences. Int'l. J. Computer Vision 4 (1990) 171–183.Google Scholar
  21. Tsai, R.Y., Huang, T.S.: Uniqueness and estimation of three dimensional motion parameters of rigid objects with curved surfaces. IEEE Trans. PAMI 6 (1984) 13–27.Google Scholar
  22. Ullman, S.: The Interpretation of Visual Motion (MIT Press, Cambridge, MA (1979).Google Scholar
  23. Weng, J., Huang, T.S., Ahuja, N.: A two step approach to optimal motion and structure estimation. Proc. IEEE Computer Society Workshop on Computer Vision (1987).Google Scholar
  24. Young, G.S., Chellappa, R.: 3-D motion estimation using a sequence of noisy stereo images. Proc. IEEE Conference on Computer Vision and Pattern Recognition (1988).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Yiannis Aloimonos
    • 1
  • Zoran Duriç
    • 1
  1. 1.Computer Vision Laboratory, Center for Automation Research, Department of Computer Science and Institute for Advanced Computer StudiesUniversity of MarylandCollege Park

Personalised recommendations