CoChat
Sign Up
Cited by 23Video Surveillance and Tracking MethodsAdvanced Vision and ImagingTarget Tracking and Data Fusion in Sensor Networks

The DOI matches its Crossref record; its reference list is not available.

Statistical models of visual shape and motion

Blake, A., Bascle, B., Isard, M., MacCormick, J.·1998·Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences
DOI 10.1098/rsta.1998.0222
Open this paper in CoChat — free account

Abstract

The analysis of visual motion against dense background clutter is a challenging problem. Uncertainty in the positions of visually sensed features and ambiguity of feature correspondence call for a probabilistic treatment, capable of maintaining not simply a single estimate of position and shape but an entire distribution. Exact representation of the evolving distribution is possible when the distributions are Gaussian and this yields some powerful approaches. However, normal distributions are limited when clutter is present: because of their unimodality, they cannot be used to represent simultaneous alternative hypotheses.One powerful methodology for maintaining non–Gaussian distributions is based on random sampling techniques. The effectiveness of ‘factored sampling’ and ‘Markov chain Monte Carlo’ for interpretation of static images is widely accepted. More recently, factored sampling has been combined with learned dynamical models to propagate probability distributions for object position and shape. Progress in several areas is reported here. First a new observational model is described that takes object opacity into account. Secondly, complex shape models to represent combined rigid and non–rigid motion have been developed, together with a new algorithm to decompose rigid from non–rigid. Lastly, more powerful dynamical prior models have been constructed by appending suitable discrete labels to a continuous system state; this may also have applications to gesture recognitio…

Overview

Integrity signals

Registry

Crossref · 10.1098/rsta.1998.0222

Cites

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Instead of being the first stage in a feedforward pipeline, V1 is better described as the unique high-resolution buffer in the visual system for geometric calculations.

    “This led us to propose that, instead of being the first stage in a feedforward pipeline, 13 V1 is better described as the unique high-resolution buffer in the visual system for geometric calculations. 40,41”

    From Hierarchical Bayesian inference in the visual cortex (2003) · cites this paper as [13]

Citations

No citation lists for this paper

No citation lists for this paper yet — checked again daily.

References 39 · Cited by 23

Research works printed but not linked: 45

  1. Barnett S. 1990 Matrices: methods and applications. Oxford University Press. · DOI
  2. 10.1109/ICCV.1998.710738 · DOI
  3. Baumberg A. & Hogg D. 1994 Learning flexible models from image sequences. In Proc. 3rd European Conf. Computer Vision (ed. J.-O. Eklundh) pp. 299-308. Springer. · DOI
  4. Baumberg A. & Hogg D. 1995a An adaptive eigenshape model. In Proc. of British Machine Vision Conf. pp. 87-96. BMVA. · DOI
  5. Baumberg A., 1995, Generating spatiotemporal models from examples, Proc. British Machine Vision Conf., 2, 413
  6. 10.1109/ICCV.1995.466898 · DOI
  7. Blake A. & Isard M. 1994 3D position attitude and shape input using video tracking of hands and lips. In Proc. Siggraph pp. 185-192. ACM. · DOI
  8. Blake A. & Isard M. 1998 Active contours. Springer. · DOI
  9. 10.1016/0004-3702(95)00032-1 · DOI
  10. 10.1109/ICCV.1995.466914 · DOI
  11. 10.1109/ICCV.1995.466880 · DOI
  12. Cootes T., 1993, Building and using flexible models incorporating grey-level information. In Proc. 4th, Int. Conf. on Computer Vision, 242
  13. Dempster A., 1977, Maximum likelihood from incomplete data via the EM algorithm, J. R. Statist. Soc. B, 39, 1, 10.1111/j.2517-6161.1977.tb01600.x · DOI · Paper page
  14. Duda R. & Hart P. 1973 Pattern classification and scene analysis. Wiley.
  15. Fernyhough J. Cohn A. & Hogg D. 1996 Generation of semantic regions from image sequences. In Proc. 4th European Conf. on Computer Vision pp. 475-484. Springer. · DOI
  16. Freeman W. & Tenenbaum J. 1997 Learning bilinear models for two-factor problems in vision. In Proc. Conf. Computer Vision and Pattern Recognition pp. 554-560. IEEE. · DOI
  17. Gelb A. (ed.) 1974 Applied optimal estimation. Cambridge MA: MIT Press.
  18. 10.1109/TPAMI.1984.4767596 · DOI · Paper page
  19. Gordon N., 1993, Novel approach to nonlinear/non-Gaussian Bayesian state estimation, IEE Proc. F, 140, 107
  20. Grenander U. 1976 Lectures in pattern theory I II and III. Springer. · DOI
  21. Grenander U., 1994, Representations of knowledge in complex systems (with discussion), J. R. Statist. Soc. B, 56, 549, 10.1111/j.2517-6161.1994.tb02000.x · DOI
  22. Grenander U. Chow Y. & Keenan D. 1991 HANDS. A pattern theoretical study of biological shapes. New York: Springer. · DOI
  23. Huang X. Arika Y. & Jack M. 1990 Hidden Markov models for speech recognition. Edinburgh University Press.
  24. Isard M. & Blake A. 1996 Visual tracking by stochastic propagation of conditional density. In Proc. 4th European Conf. Computer Vision pp. 343-356. Springer. · DOI
  25. Isard M. & Blake A. 1998a Condensation-conditional density propagation for visual tracking. Int. J. Computer Vision. (In the press.)
  26. 10.1109/ICCV.1998.710707 · DOI
  27. Kendall M. & Stuart A. 1979 The advanced theory of statistics vol. 2. Inference and relationship. London: Charles Griffing.
  28. Kitagawa G., 1996, Monte Carlo filter and smoother for non-Gaussian nonlinear state space models, J. Computat. Graph. Statist., 5, 1, 10.1080/10618600.1996.10474692 · DOI
  29. Knill D. Kersten D. & Yuille A. 1996 A Bayesian formulation of visual perception. In Perception as Bayesian inference (ed. D. Knill & W. Richard) pp. 1-22. Cambridge University Press. · DOI · Paper page
  30. 10.1364/JOSAA.8.000377 · DOI
  31. Koller D. Weber J. & Malik J. 1994 Robust multiple car tracking with occlusion reasoning. In Proc. 3rd European Conf. Computer Vision pp. 189-196. Springer. · DOI
  32. 10.1109/ICCV.1995.466919 · DOI
  33. 10.1109/ICCV.1998.710748 · DOI
  34. 10.1016/0262-8856(93)90006-3 · DOI
  35. Mumford D. 1996 Pattern theory: a unifying perspective. In Perception as Bayesian inference (ed. D. Knill & W. Richard) pp. 25-62. Cambridge University Press. · DOI
  36. 10.1109/34.291452 · DOI
  37. North B. & Blake A. 1997 Using expectation-maximisation to learn dynamical models from visual data. In Proc. British Machine Vision Conf. pp. 669-678. BMVA.
  38. Rao C. 1973 Linear statistical inference and its applications. New York: Wiley. · DOI
  39. Reynard D. Wildenberg A. Blake A. & Marchant J. 1996 Learning dynamics of complex motions from image sequences. In Proc. 4th European Conf. Computer Vision pp. 357-368. Springer. · DOI
  40. 10.1098/rsta.1990.0127 · DOI
  41. 10.1016/0262-8856(96)01103-1 · DOI
  42. 10.1109/34.329011 · DOI
  43. 10.1007/BF00129684 · DOI
  44. 10.1109/34.99234 · DOI
  45. Vetter T. & Poggio T. 1996 Image synthesis from a single example image. In Proc. 4th European Conf. Computer Vision pp. 652-659. Springer. · DOI

Metadata

Authors
Blake, A., Bascle, B., Isard, M., & MacCormick, J.
Affiliations
University of Oxford (GB)
ORCID
Blake, A.
Venue
Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences
Publisher
The Royal Society
Published
1998-05-15
Volume
356
Issue
1740
Pages
1283-1302
ISSN
  • 1364-503X (ISSN-L)
  • 1471-2962
DOI
10.1098/rsta.1998.0222
OpenAlex
W4237328298
Cited by
23
References
39
Citations by year
2020: 1 · 2018: 1 · 2016: 1 · 2015: 1 · 2013: 2
FWCI
2.61
Type
journal article
Language
en
Open access
closed
Locations
Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
  • Physical Sciences › Computer Science › Artificial Intelligence › Target Tracking and Data Fusion in Sensor Networks
Keywords
visual motion processing, background clutter, probabilistic shape models, non-Gaussian distributions, Markov chain Monte Carlo, motion decomposition, gesture recognition

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review