Skip to main content
SpringerLink
Log in

3D Constraints on Monocular Image Sequences: Theory and Algorithms

  • Chapter
Image Technology

  • 232 Accesses

Abstract

Deriving three-dimensional information about a scene from its images is a challenging problem in computer vision. Multiple views of a scene/object from a moving camera can be used for this task. This paper presents a critical appraisal of the theory and algorithms for problems involving 3D geometric constraints between a scene and its multiple views. The essential constraints between the 3D shape, the view transformations and the 2D image projections are presented for various widely applicable models of projection. The recent trend in representing 3D shape in a fixed object-centered coordinate system figures prominently in this paper. It is shown how this approach nicely separates the contribution of 3D shape and motion as manifested in the image motion. This is contrasted with the traditional approach of computing 3D motion as a precursor to the computation of 3D structure. Methods that incorporate these constraints using discrete features (like points) and spatio-temporal intensity gradients are presented.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 219.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. G. Adiv. Determining 3D motion and structure from optical flows generated by several moving objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 7(4):384–401, 1985.

    Article  Google Scholar 

  2. G. Adiv. Inherent ambiguities in recovering 3D information from a noisy flow field. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(5):477–489, 1989.

    Article  Google Scholar 

  3. P. Anandan, Measuring Visual Motion from Image Sequences PhD thesis, University of Massachusetts at Amherst, MA, 1987. COINS TR 87-21.

    Google Scholar 

  4. P. Anandan. A computational framework and an algorithm for the measurement of visual motion. International Journal of Computer Vision, 2(3):283–310, 1989.

    Article  Google Scholar 

  5. A. Azarbayejani, B. Horowitz, and A. Pentland. Recursive estimation of structure and motion using relative orientation constraints. In Proc. Computer Vision and Pattern Recognition Conference, pp. 294-299, 1993.

    Google Scholar 

  6. M. Boldt, R. Weiss, and E. Riseman. Token-based extraction of straight lines. IEEE Transactions on Systems Man and Cybernetics, 19(6):1581–1594, 1989.

    Article  Google Scholar 

  7. J.L. Crowley, P. Stelmaszyk, and C. Discours. Measuring image flow by tracking edgelines. In Proc. 2nd Intl. Conf on Computer Vision, pp. 658-664, 1988.

    Google Scholar 

  8. K. Daniilidis and H.H. Nagel. Analytical results on error sensitivity of motion estimation from two views. In Proc. 1st European Conference on Computer Vision, pp. 199-208, 1990.

    Google Scholar 

  9. K. Daniilidis and H.H. Nagel. The coupling of rotation and translation in motion estimation of planar surfaces. In Proc. Computer Vision and Pattern Recognition Conference, pp. 188-193, 1993.

    Google Scholar 

  10. R. Deriche and O. Faugeras. Tracking line segments. In Proc. 1st European Conference on Computer Vision, pp. 259-268, 1990.

    Google Scholar 

  11. R. Dutta and M.A. Snyder. Robustness of correspondence-based structure from motion. In Proc. 3rd Intl. Conf. on Computer Vision, pp. 106-110, 1990.

    Google Scholar 

  12. J.R. Bergen et al. Hierarchial model-based motion estimation. In Proc. 2nd European Conference on Computer Vision, pp. 237-252, 1992.

    Google Scholar 

  13. K.J. Hanna. Direct multi-resolution estimation of ego-motion and structure from motion. In Proc. IEEE Wkshp. on Visual Motion, pp. 156-162, 1991.

    Google Scholar 

  14. R. Hartley and R. Gupta. Computing matched epipolar projections. In Proc. Computer Vision and Pattern Recongnition Conference, pp. 549-555, 1993.

    Google Scholar 

  15. J.C. Hay. Optical motions and space perception: An extension of Gibson’s analysis. Psychological Review, 73:550–565, 1966.

    Article  Google Scholar 

  16. D.J. Heeger and A.D. Jepson. Subspace methods for recovering rigid motion I: Algorithm and implementation. Technical Report RBCV-TR-90-35, University of Toronto, 1990.

    Google Scholar 

  17. J. Heel. Temporally integrated surface reconstruction. In Proc. 3rd Intl. Conf on Computer Vision, pp. 292-295, 1990.

    Google Scholar 

  18. B.K.P. Horn. Recovering baseline and orientation from essential matrix. Internal Report, 1990.

    Google Scholar 

  19. B.K.P. Horn. Relative orientation. International Journal of Computer Vision, 4(1):59–78, 1990.

    Article  Google Scholar 

  20. B.K.P. Horn. Relative orientation revisited. Journal of the Optical Society of America A, 8(10):1630–1638, 1991.

    Article  Google Scholar 

  21. B.K.P. Horn and B.G. Schunck. Determining optical flow. Artificial Intelligence, 17(1-3):185–203, 1981.

    Article  Google Scholar 

  22. B.K.P. Horn and E.J. Weldon. Direct methods for recovering motion. International Journal of Computer Vision, 2(1):51–76, 1988.

    Article  Google Scholar 

  23. T.S. Huang and O.D. Faugeras. Some properties of the E matrix in two-view motion estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(12):1310–1312, 1989.

    Article  Google Scholar 

  24. J.J. Kowenderink and Andrea J. van Doorn. Affine structure from motion. Journal of the Optical Society of America A, 81:377–385, 1991.

    Article  Google Scholar 

  25. Chia-Hoang Lee. Structure and motion from two perspective views via planar patch. In Proc. 2nd Intl. Confi on Computer Vision, pp. 158-164, 1988.

    Google Scholar 

  26. Chia-Hoang Lee and T. Huang. Finding point correspondences and determining motion of a rigid object from two weak perspective views. Computer Vision Graphics and Image Processing, 52:309–327, 1990.

    Article  Google Scholar 

  27. H.C. Longuet-Higgins. A computer algorithm for reconstructing a scene from two projections. Nature, 293:133–135, 1981.

    Article  Google Scholar 

  28. H.C. Longuet-Higgins and K. Prazdny. The interpretation of a moving retinal image. In Proc. Royal Society of London B, pp. 385-397, 1980.

    Google Scholar 

  29. R. Manmatha. Thesis Proposal, Univ. of Massachusetts, 1992.

    Google Scholar 

  30. R. Manmatha and J. Oliensis. Extracting affine defformations from image patches — i. finding scale and rotation. In Proc. Computer Vision and Pattern Recognition Conference, pp. 754-755, 1933.

    Google Scholar 

  31. S. Maybank, Theory of Reconstruction from Image Motion. Springer-Verlag, 1993.

    Google Scholar 

  32. R. Mohr, F. Veillon, and L. Quan. Relative 3D reconstruction using multiple uncalibrated images. In Proc. Computer Vision and Pattern Recongnition Conference, pp. 543-548, 1993.

    Google Scholar 

  33. J.L. Mundy and A. Zisserman, Geometric Invariance in Computer Vision. The MIT Press, MA, 1992.

    Google Scholar 

  34. S. Negahdaripour and B.K.P. Horn. Direct passive navigation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 9(1):168–176, 1987.

    Article  MATH  Google Scholar 

  35. J. Oliensis and J.I. Thomas. Incorporating motion error in multi-frame structure from motion. In Proc. IEEE Wkshp. on Visual Motion, pp. 8-13. 1991.

    Google Scholar 

  36. C.J. Poelman and T. Kanade. A paraperspective factorization method for shape and motion recovery. Technical Report CMU-CS-92-208, Carnegie Mellon University, 1992.

    Google Scholar 

  37. K. Rangarajan and M. Shah. Establishing motion correspondence. In Proc. Computer Vision and Pattern Recognition Conference, pp. 103-108, 1991.

    Google Scholar 

  38. J.H. Rieger and D.T. Lawton. Processing differential image motion. Journal of the Optical Society of America A, 2(2):354–360, 1985.

    Article  Google Scholar 

  39. H.S. Sawhney and A.R. Hanson. Comparative results of some motion algorithms on real image sequences. In Proc. DARPA Image Understanding Workshop, 1990.

    Google Scholar 

  40. H.S. Sawhney and A.R. Hanson. Identification and 3D description of “shallow” environmental structure in a sequence of images. In Proc. Computer Vision and Pattern Recognition Conference, pp. 179-186, 1991.

    Google Scholar 

  41. H.S. Sawhney and A.R. Hanson. Trackability as a cue for potential obstacle identification and 3D description. International Journal of Computer Vision, 1993.

    Google Scholar 

  42. H.S. Sawhney J. Oliensis, and A.R. Hanson. Image description and 3D reconstruction from image trajectories of rotational motion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(9), 1993.

    Google Scholar 

  43. Harpreet S. Sawhney. Spatial and Temporal Grouping in the Interpretation of Image Motion. PhD thesis, University of Massachusetts at Amherst, MA, 1992. COINS TR 92-05.

    Google Scholar 

  44. S.K. Sethi and R. Jain. Finding trajectories of feature points in a monocular image sequence. IEEE Transactions on Pattern Analysis and Machine Intelligence, 9(1):56–73, 1987.

    Article  Google Scholar 

  45. Amnon Shashua. Correspondence and affine shape from two orthographic views: Motion and recognition. Technical Report AI Meno No. 1327, Massachusetts Institute of Technology, 1991.

    Google Scholar 

  46. M. Spetsakis and Y. Aloimonos. A multi-frame approach to visual motion perception. International Journal of Computer Vision, 6(3):245–255, 1991.

    Article  Google Scholar 

  47. M.E. Spetsakis and J. Aloimonos. Optimal computing of structure from motion using point correspondences in two frames. In Proc. 2nd Intl. Conf. on Computer Vision, pp. 449-453, 1988.

    Google Scholar 

  48. R. Szeliski and S.B. Kang. Recovering 3D shape and motion from image streams using non-linear least squares. In Proc. Computer Vision and Pattern Recognition Conference, pp. 752-753, 1993.

    Google Scholar 

  49. R. Szeliski and S.B. Kang. Recovering 3D shape and motion from image streams using non-linear least squares. Technical Report CRL93/3, DEC Cambridge Research Lab., 1993.

    Google Scholar 

  50. J.I. Thomas, A. Hanson, and J. Oliensis. Understanding noise: The critical role of motion error in scene reconstruction. In Proc. 4th Intl. Conf On Computer Vision, pp. 325-329, 1993.

    Google Scholar 

  51. C. Tomasi. Shape and Motion from Image Streams: A Factorization Method. PhD thesis, Carnegie Mellon University, 1991. CMU-CS-91-172.

    Google Scholar 

  52. C. Tomasi and T. Kanade. Shape and motion from image streams under orthography: A factorization method. International Journal of Computer Vision, 9(2):137–154, 1992.

    Article  Google Scholar 

  53. R.Y. Tsai and T.S. Huang. Uniqueness and estimation of 3D motion parameters and surface structures of rigid objects. In Whitman Richards and Shimon Ullman, editors, Image Understanding 1984, pp. 135–171. Ablex Corporation, NJ, 1984.

    Google Scholar 

  54. S. Ullman. The Interpretation of Visual Motion. The MIT Press, Cambridge, MA, 1979.

    Google Scholar 

  55. A. Verri and T. Poggio. Motion field and optical flow: Qualitative properties. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(5):490–498, 1989.

    Article  Google Scholar 

  56. D. Weinshall. Model based invariants for 3D vision. International Journal of Computer Vision, 10(1):27–42, 1993.

    Article  MathSciNet  Google Scholar 

  57. D. Weinshall and C. Tomasi. Linear and incremental acquisition of invariant shape models from image sequences. In Proc. 4th Intl. Conf. On Computer Vision, pp. 675-682, 1993.

    Google Scholar 

  58. P. Werkhoven and J.J. Koenderink. Extraction of motion parallax structure in the visual system I. Biological Cybernetics, 59, 1990.

    Google Scholar 

  59. L.R. Williams and A.R. Hanson. Translating optical flow into token matches and depth from looming. In ICCV, pp. 441-448, 1988.

    Google Scholar 

  60. Z. Zhang and O. Faugeras. 3D Dynamic Scene Analysis: A Stereo Approach. Springer, Berlin, Heidelberg, 1992.

    MATH  Google Scholar 

Download references

Authors
  1. H. S. Sawhney
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. P. Anandan
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, 61801, USA

    Jorge L. C. Sanz

  2. IBM Argentina, Ingeniero Enrique Butty 275, 1300, Buenos Aires, Argentina

    Jorge L. C. Sanz

Rights and permissions

Reprints and permissions

Copyright information

© 1996 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Sawhney, H.S., Anandan, P. (1996). 3D Constraints on Monocular Image Sequences: Theory and Algorithms. In: Sanz, J.L.C. (eds) Image Technology. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-58288-2_2

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-58288-2_2

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-63528-1

  • Online ISBN: 978-3-642-58288-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation