Journal of Electrical Engineering and information Science

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

Multilayer Stereo Image Matching Based upon Phase-Magnitude an Mean Field Approximation

  • Hong Jeong (Department of Electronics Engineering, Pohang University of Science and Technology) ;
  • Kim, Jung-Gu (Department of Electronics Engineering, Pohang University of Science and Technology) ;
  • Chae, Myoung-Sik (SK Telecom)
  • Published : 1997.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper introduces a new energy function, as maximum a posteriori(MAP) estimate of binocular disparity, that can deal with both random dot stereo-gram(RDS) and natural scenes. The energy function uses phase-magnitude as features to detect only the shift for a pair of corrupted conjugate images. Also we adopted Fleet singularity that effectively detects unstable areas of image plant and thus eliminates in advance error-prone stereo mathcing. The multi-scale concept is applied to the multi laser architecture that can search the solutions systematically from coarse to fine details and thereby avoids drastically the local minima. Using mean field approximation, we obtained a compact representation that is suitable for fast computation. In this manner, the energy function satisfies major natural constraints and requirements for implementing parallel relaxation. As an experiment, the proposed algorithm is applied to RDS and natural stereo images. As a result we will see that it reveals good performance in terms of recognition errors, parallel implementation, and noise characteristics.

Keywords

References

  1. Interational Journal of Computer Vison v.1 no.2 Efficient registration of stero images by matchnig grap descriptions of edge segments N.Ayache;B.Faverjon
  2. Ist Conf. Computer Vision Fast and reliable trinocular stereovision N.Ayache;F.Lustman
  3. Proc. 7th Intern. Joint Conf. Arif. Intell Depth from edges and intensity based stereo H.H.Barker;T.O.Binford
  4. J. Royal Statis. Soc., Ser v.B36 Spatial Interaction and the satisfical analysis of lattice systems J.E.Besag
  5. The Pyramid as a Structure for Efficent Computation P.J.Burt
  6. Phyamidal systems for computer vision V.Cantoni;S.Levialdi(ed).
  7. Introduction to Modern Satisical Machnics D.Chandler
  8. J. Opt. Soc. Journal of Computer Vision v.A4 Relations between the statistics of natural images and the response properties of cortial cells D.J.Field
  9. Intrnatiional journal of computer Vision v.5 Compuation of component image velocity from local phase information D.J.fleet;A.D.Jepson
  10. Comput. Vison, Graphis, Image Procestion v.53 Phase-based disparity measurement D.J.Fleet;A.D.Jepson;M.Jenkin
  11. Measurement of Image Velocity D.J.Fleet
  12. IEEE Trans. Pattern Anal Machine Intell v.PAMI-15 no.12 Stability of phase information D.J.Fleet
  13. IEEE Trans. Pattern Anal Machine Intell v.PAMI-13 The design and use of steer-able filters W.T.Freeman;E.H.Adelson
  14. J.IEE v.93 Theory of communication D.Gabor
  15. IEEE Trans. Pattern Anal Machine Intell v.PAMI-6 Stochastic relaxation, Gibbs distributions, and Bayesian restoration of images S.Geman;D.Geman
  16. Proc. 1st IEEE conf. Computer Vison Pattern Recognitton Scene matching by hierachical correlation F.Glazer;G.Reynoids;P.Anandan
  17. Phil. Trans. Royal Soc. v.B292 A Computer implementation of a theory of human stereo vision W.E.L.Grimson
  18. From Image to Surfaces: A Computational Study of the Human Early Visual System W.E.L.Grimson
  19. IEEE Trans. Pattern Anal Machine Intell v.PAMI-7 no.1 Computational experiments with a feature based stereo algorithm W.E.L.Grimson
  20. Artificial Intelligence v.17 Determing optical flow B.K.P.Hom;B.G.Schunck
  21. Proc. IEEE CVPR The fast Compuation of Disparity from Phase Difference A.Jepson;M.Jenkin
  22. Proc. DARPA Image Underatanding Workshop A computational framework for the visual correspondence problem M.Kass
  23. IEEE. J. Robotics and Automation v.RA-3 no.4 Positioning 3D objects using stereo images Y.C.Kim;J.K.Aggarwl
  24. Science v.220 Optimization by Simulated Anneling S.Kirkpatrick C.Gelatt;M.Vecchi
  25. First European Conference Computer Vision Vertical and horizontal disparities from phase L.Langly;T.J.Atherton;R.G.Wison;M.H.E.Larcombe
  26. Proc. Roy. Soc. v.B204 A computational theory of human stereo vision D.Marr;T.Poggio
  27. Artificial Intelligence v.17 Psychophysical and computational studies towords a theory of human steropsis J.E.W.Mayhew;J.P.frisby
  28. Compt. Vison. Graphics, Image Processing v.31 Segment based stereo matching G.Medioni;r.Nevatia
  29. Proc. 5th Int. Joint Conf. Arificial Intelligence Towards automatic visual obstacle avoidance H.P.Moravec
  30. ACCV'95 Second Asian Conference on Computer Vision Stereo matching for occlusion bounfaries using mormalization light intensity O.Nakayama;Y.Shirai
  31. Proc. IEEE v.69 no.5 The importance of phase in signals A.V.Oppenheim;J.s.Lim
  32. Perception v.14 PMF A stereo correspondence algorithm using a disparity gradient limit S.B.Pliiard;J.E.Mayhew;J.P.Frisby
  33. Biological Cybernetics v.59 Stereo disoarity computation using Gaborfiliters T.D.Sanger
  34. IEEE Trans. Info. Theory v.38 Shiftable multiscale transforms T.D.Sanger
  35. Proc. Workshop an Computer Vision: Representation and Control An image flow paradigm A.M.Waxman
  36. Proc. 3rd ICCV A theory of image flow paradigm J.Weng
  37. International Journal of computer Vison v.11 no.3 Image matching using the windowed Fourier phase J.Weng
  38. Preattentive Gaze Control for Robot Vision Thesis: LIU-TEK_LIC-1992:14 C.J.Westelius