In this paper we present a new Bayesian framework for partially occluded object recognition with one-to-one correspondence. We introduce two different statistical models for occlusion: One model assumes that each feature in the model can be occluded independent of whether any other features are occluded, whereas the second model uses spatially correlated occlusion to represent the extent of occlusion. Using these models, the object recognition problem reduces to finding the object hypothesis with largest generalized likelihood We develop fast algorithms for finding the optimal one-to-one correspondence between scene features and object model features to compute the generalized likelihood. We evaluate our algorithms using examples extracted from synthetic aperture radar imagery, and illustrate the performance advantages of our approach over alternative algorithms proposed by others.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Feature based object recognition using statistical occlusion models with one-to-one correspondence


    Contributors:


    Publication date :

    2001-01-01


    Size :

    696286 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Feature Based Object Recognition using Statistical Occlusion Models with One-to-one Correspondence

    Ying, Z. / Castanon, D. / IEEE | British Library Conference Proceedings | 2001


    Statistical Approaches to Feature-Based Object Recognition

    Wells, W. M. | British Library Online Contents | 1997


    Partially Occluded Object Recognition Using Statistical Models

    Ying, Z. / Castanon, D. | British Library Online Contents | 2002


    Statistical Feature Based Target Recognition

    Mitchell, R. / Westerkamp, J. / IEEE | British Library Conference Proceedings | 1998


    A symmetric patch-based correspondence model for occlusion handling

    Yi Deng, / Qiong Yang, / Xueyin Lin, et al. | IEEE | 2005