Skip to main content
SpringerLink
Log in

On the Sequential Accumulation of Evidence

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

In this paper, we introduce a method for sequentially accumulating evidence as it pertains to an active observer seeking to identify an object in a known environment. We develop a probabilistic framework, based on a generalized inverse theory, where assertions are represented by conditional probability density functions. This leads to a sequential recognition strategy in which evidence is accumulated over successive viewpoints using Bayesian chaining until a definitive assertion can be made. To illustrate the theory we show how the characteristics of belief distributions can be exploited in a model-based recognition problem, where the task is to identify an unknown model from a database of known objects on the basis of parameter estimates. We illustrate the robustness of the algorithm through recognition experiments in two very different contexts: (1) a highly structured recognition context where 3-D parametric models can be estimated directly from range data, (2) a complex environment, where the relationship between the data and the model is learned through an appearance-based strategy. Specifically, the flow fields computed through the object's motion are used as structural signatures for recognition.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Aloimonos, J. and Bandyopadhyay, A. 1987. Active vision. In Proceedings, 1st International Conference on Computer Vision, London, UK, June 1987. Computer Society of the IEEE. IEEE Computer Society Press: Los Alamitos, CA.

    Google Scholar 

  • Arbel, T. 1995. Recognizing volumetric objects in the presence of uncertainty. Master's thesis, McGill University, Montréal, Québec, Canada.

    Google Scholar 

  • Arbel, T. and Ferrie, F.P. 1996. Informative views and sequential recognition. In 4th European Conference on Computer Vision, Cambridge, UK, Apr. 14-18, 1996, Vol. 1064, B. Buxton and R. Cipolla (Eds.). Springer-Verlag: Berlin, pp. 469-481.

    Google Scholar 

  • Arbel, T. and Ferrie, F.P. 1999a. Entropy-based gaze planning. In Proceedings of the Second IEEE Workshop on Perception for Mobile Agents, Fort Collins, Colorado, June 1999. In association with the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 87-94.

  • Arbel, T. and Ferrie, F.P. 1999b. Viewpoint selection by navigation through entropy maps. In Proceedings of the Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece, Sept. 20-25, 1999, pp. 248-254.

  • Arbel, T., Whaite, P., and Ferrie, F.P. 1994. Recognizing volumetric objects in the presence of uncertainty. In Proceedings 12th International Conference on Pattern Recognition, Jerusalem, Israel, Oct. 9-13, 1994, IEEE Computer Society Press: Los Alamitos, CA, pp. 470-476.

    Google Scholar 

  • Arbel, T., Whaite, P., and Ferrie, F.P. 1996. Parametric shape recognition using a probabilistic inverse theory. Pattern Recognition Letters, 17(5):491-501.

    Google Scholar 

  • Arman, F. and Aggarwal, J.K. 1993. Model-based object recognition in dense-range images-a review. ACM Computing Surveys, 25(1):5-43.

    Google Scholar 

  • Aviv, G. 1989. Inherent ambiguities in recovering 3-d motion and structure from a noisy flow field. IEEE Transactions on Pattern Analysis and Machine Intelligence, II(5):477-489.

    Google Scholar 

  • Moghaddam, W.W.B. and Pentland, A. 1998. Beyond eigenfaces: Probabilistic matching for face recognition. Technical Report 443, M.I.T. Media Laboratory Perceptual Computing Section, 1998. Also Presented in the 3rd IEEE Intl. Conference on Automatic Face and Gesture Recogntion, Nara, Japan, April 1998.

  • Bajcsy, R. 1988. Active perception. The Proceedings of the IEEE, 76(8):996-1005.

    Google Scholar 

  • Bajcsy, R. and Solina, F. 1987. Three dimensional object recognition revisited. In Proceedings, 1st International Conference on Computer Vision, London, U.K., June 1987. Computer Society of the IEEE, IEEE Computer Society Press

  • Barr, A.H. 1981. Superquadrics and angle preserving transformations. IEEE Computer Graphics and Applications, 1(1):11-23.

    Google Scholar 

  • Benoit, S.M. and Ferrie, F.P. 1996. Monocular optical flow for realtime vision systems. In Proceedings of the 13th International Conference on Pattern Recognition, Vienna, Austria, Aug. 25-30, 1996, pp. 864-868.

  • Black, M.J. and Jepson, A.D. 1998a. A probablistic framework for matching temporal trajectories: Condensation-based recognition of gestures and expressions. In ECCV98, Freiburg, Germany, June 1998. Springer-Verlag: Berlin, Vol. I, pp. 909-924.

    Google Scholar 

  • Black, M.J. and Jepson, A.D. 1998b. Recognizing temporal trajectories using the condensation algorithm. In Intl. Conf. on Automatic Face and Gesture Recognition, Nara, Japan, 1998.

  • Black, M.J. and Yacoob, Y. 1997. Recognizing facial expressions in image sequences using local parametrized models of image motion. Int. Journal of Computer Vision, 25(1):23-48. Also found in Xerox PARC, Techinical Report SPL-95-020.

    Google Scholar 

  • Bobick, A.F. and Davis, J.W. 1996. An appearance-based representation of action. Technical Report 369, MIT Media Lab, Feb., 1996, (submitted to ICPR 96).

  • Burgard, W., Fox, D., and Thrun, S. 1997. Active mobile robot localization. In Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, Nagoya, Japan, Aug. 23-29, 1997.

  • Callari, F.G. and Ferrie, F.P. 1996. Active recognition: Using uncertainty to reduce ambiguity. In Proceedings of the 13th International Conference on Pattern Recognition, Vienna, Austria, Aug. 25-30, 1996. International Association for Pattern Recognition, IEEE-Computer Society Press: Los Alamitos, CA, pp. 925-929.

    Google Scholar 

  • Chin, R.T. and Dyer, C.R. 1986. Model-based recognition in robot vision. Computing Surveys, 18(1):67-108.

    Article  Google Scholar 

  • Cover, T.M. and Thomas, J.A. 1991. Elements of Information Theory. Wiley & Sons: New York, NY.

    Google Scholar 

  • Darrell, T., Sclaroff, S., and Pentland, A. 1990. Segmentation by minimal description. In Proceedings, 3RD International Conference on Computer Vision, Osaka, Japan, Dec. 1990. IEEE Computer Society, IEEE Computer Society Press: Los Alamitos, CA, pp. 112-116.

    Google Scholar 

  • Dempster, A.P. and Shafer, G. 1976. A Mathematical Theory of Evidence. Princeton University Press: Princeton, NJ.

    Google Scholar 

  • Dickinson, S.J., Christensen, H.I., Tsotsos, J.K., and Olofsson, G. 1997. Active object recognition integrating attention and viewpoint control. Academic Press: Orlendo, FL, Computer Vision, Image Understanding, 67(3):239-260.

    Google Scholar 

  • Durrant-Whyte, H. 1988. Sensor models and multisensor integration. International Journal of Robotics Research, 7(6):97-113.

    Google Scholar 

  • Ferrie, F.P. and Lagarde, J. 1989. On computing stable surface descriptions from range images. In Proceedings 5th International Conference on Image Analysis, Positano, Italy, Sept. 20-22, 1989.

  • Ferrie, F.P., Lagarde, J., and Whaite, P. 1993. Darboux frames, snakes, and super-quadrics: Geometry from the bottom up. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(8):771-784.

    Google Scholar 

  • Herbin, S. 1996. Recognizing 3d objects by generating random actions. In Proceedings, Conference on Computer Vision and Pattern Recognition, San Francisco, June 1996. Computer Society of the IEEE, IEEE Computer Society Press: Los Alamitos, CA, pp. 35-40.

    Google Scholar 

  • Hummel, R.A. and Landy, M.S. 1988. A statistical viewpoint on the theory of evidence. PAMI, 10(2):235-247.

    Google Scholar 

  • Hutchinson, S. and Kak, A. 1989. Planning sensing strategies in a robot work cell with multi-sensor capabilities. IEEE Transactions on Robotics and Automation, 5(6):765-783.

    Google Scholar 

  • Isard, M. and Blake, A. 1996. Contour tracking by stohastic propagation of conditional density. In Computer Vision-ECCV 96, Cambridge, UK, Apr. 14-18, 1996, B. Buxton and R. Cipolla (Eds.), Springer-Verlag: Berlin, pp. 343-356.

    Google Scholar 

  • Jebara, T., Russell, K., and Pentland, A. 1988. Mixtures of eigenfeatures for real-time structure from texture. In Proceedings, 6TH International Conference on Computer Vision, Bombay, India, Jan. 1998. Computer Society of the IEEE, IEEE Computer Society Press: Los Alamitos, CA.

    Google Scholar 

  • Keren, D., Cooper, D., and Subrahmonia, J. 1992. Describing complicated objects by implicit polynomials. Technical Report 102, Brown University LEMS, Laboratory for Engineering Man/Macine Systems, Division of Engineering, Brown University, Providence RI 021912 USA, 1992.

    Google Scholar 

  • Kirby, M. and Sirovich, L. 1990. Application of the karhunen-loeve procedure for the characterization of human faces. IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Computer Society Press: Los Alamitos, CA, 12(1):103-108.

    Google Scholar 

  • Kittler, J. and Hancock, E.R. 1989. Combining evidence in probabilistic relaxation. PRAI, 3:29-51.

    Google Scholar 

  • Lejeune, A. and Ferrie, F.P. 1993. Partitioning range images using curvature and scale. In Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,NewYork City,New York, June 15-17, 1993, pp. 800-801.

  • Li, N., Dettmer, S., and Shah, M. 1997. Visually recognizing speech using eigen sequences. In MBR97, Ch. 15.

  • Mohr, S.P.R. and Schmid, C. 1997. Bayesian decision versus voting for image retrieval. In CAIP:97.

  • Nayar, S.K., Murase, H., and Nene, S.A. 1996. Parametric Appearance Representation in Early Visual Learning. Oxford University Press: Oxford, UK, Ch. 6.

    Google Scholar 

  • Onishi, M.I.M., Nishikawa, N., and Fukunaga, K. 1998. Object recognition using sequential images, and application to active vision. In 2nd International workshop on Statistical Techniques in Pattern Recognition, Sydney, Australia, 1998. Osaka Prefecture University: Japan.

    Google Scholar 

  • Pentland, A., Picard, R.W., and Sclaroff, S. 1996. Photobook: Content-based manipulation of image databases. International Journal of Computer Vision, 18(3):233-254.

    Google Scholar 

  • Pentland, A. and Sclaroff, S. 1991. Closed form solutions for physically based shape modelling and recognition. In IEEE Transactions on Pattern Analysis and Machine Intelligence: Special Issue on Physical Modeling in Computer Vision, 13(7):715-729.

    Google Scholar 

  • Raja, N.S. and Jain, A.K. 1992. Recognizing geons from superquadrics fitted to range data. Image and Vision Computing, 10(3):179-190.

    Google Scholar 

  • Rao, B.S. and Durrant-Whyte, H. 1993. A decentralized bayesian algorithm for identification of tracked targets. IEEE Transactions on Systems, Man, and Cybernetics, 23(6):1685-1698.

    Google Scholar 

  • Schiele, B. and Crowley, J.L. 1996. Probabilistic object recognition using multidimensional receptive field histogram. In Proceedings of the 13th International Conference on Pattern Recognition, Vienna, Austria, Aug. 25-30, 1996. International Association for Pattern Recognition, IEEE-CS.

  • Sirovich, L. and Kirby, M. 1987. Low-dimensional procedure for the characterization of human faces. Journal of the Optical Society of America, 4(3):519-524.

    Google Scholar 

  • Subrahmonia, J., Cooper, D.B., and Keren, D. 1992. Practical reliable bayesian recognition of 2D and 3D objects using implicit polynomials and algebraic invariants. LEMS 107, Brown University LEMS, Laboratory fo Engineering Man/Machine systems, Division of Engineering, Brown University, Providence, RI 02912, USA,1992.

    Google Scholar 

  • Tarantola, A. 1987. Inverse Problem Theory: Methods for Data Fitting and Model Parameter Estimation. Elsevier Science Publishing Company, New York, NY.

    Google Scholar 

  • Turk, M. and Pentland, A.P. 1991. Eigenfaces for recognition. CogNeuro, 3(1):71-96.

    Google Scholar 

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

    Google Scholar 

  • Watanabe, N.T.M. and Onoguchi, 1996.A moving object recognition method by optical flow analysis. In Proceedings of the 13th International Conference on Pattern Recognition, Vienna, Austria, Aug. 1996, Vol. 10th, pp. 528-533. International Association for Pattern Recognition, Surrey, UK.

    Google Scholar 

  • Whaite, P. and Ferrie, F.P. 1991. From uncertainty to visual exploration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(10):1038-1049.

    Google Scholar 

  • Whaite, P. and Ferrie, F.P. 1997a. Autonomous exploration: Driven by uncertainty. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(3):193-205.

    Google Scholar 

  • Whaite, P. and Ferrie, F.P. 1997b. On the sequential determination of model misfit. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(8):899-905.

    Google Scholar 

  • Wilkes, D. and Tsotsos, J.K. 1992. Active object recognition. In Proceedings, Conference on Computer Vision and Pattern Recognition, Champaign, Il, June 15-18, 1992. Computer Society of the IEEE, IEEE Computer Society Press: Los Alamitos, CA, pp. 136-141.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Centre for Intelligent Machines, McGill University, 3480 University St., Montréal, Québec, Canada, H3A 2A7

    Tal Arbel & Frank P. Ferrie

Authors
  1. Tal Arbel
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Frank P. Ferrie
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Arbel, T., Ferrie, F.P. On the Sequential Accumulation of Evidence. International Journal of Computer Vision 43, 205–230 (2001). https://doi.org/10.1023/A:1011187530616

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1011187530616

Search

Navigation