There have been important recent advances in object recognition through the matching of invariant local image features. However, the existing approaches are based on matching to individual training images. This paper presents a method for combining multiple images of a 3D object into a single model representation. This provides for recognition of 3D objects from any viewpoint, the generalization of models to non-rigid changes, and improved robustness through the combination of features acquired under a range of imaging conditions. The decision of whether to cluster a training image into an existing view representation or to treat it as a new view is based on the geometric accuracy of the match to previous model views. A new probabilistic model is developed to reduce the false positive matches that would otherwise arise due to loosened geometric constraints on matching 3D and non-rigid models. A system has been developed based on these approaches that is able to robustly recognize 3D objects in cluttered natural images in sub-second times.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Local feature view clustering for 3D object recognition


    Contributors:
    Lowe, D.G. (author)


    Publication date :

    2001-01-01


    Size :

    1019834 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Local Feature View Clustering for 3D Object Recognition

    Lowe, D. G. / IEEE | British Library Conference Proceedings | 2001




    3D object recognition from range images using local feature histograms

    Hetzel, G. / Leibe, B. / Levi, P. et al. | IEEE | 2001


    3D Object Recognition from Range Images Using Local Feature Histograms

    Hetzel, G. / Leibe, B. / Levi, P. et al. | British Library Conference Proceedings | 2001