Background subtraction is a popular algorithm for video object segmentation. It identifies foreground objects by comparing the input images with a pure background image. In camera-motion compensated sequences, small errors in the motion estimation can lead to large image differences along sharp edges. Consequently, the errors in the image registration finally lead to segmentation errors. This paper proposes a computationally efficient approach to detect image areas having a high risk of showing misregistration errors. Furthermore, we describe how existing change detection algorithms can be modified to avoid segmentation errors in these areas. Experiments show that our algorithm can improve the segmentation quality. The algorithm is memory efficient and suitable for real-time processing.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Misregistration errors in change detection algorithms and how to avoid them


    Contributors:
    Farin, D. (author) / de With, P.H.N. (author)


    Publication date :

    2005-01-01


    Size :

    256837 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Misregistration Errors in Change Detection algorithms and Howto Avoid Them

    Farin, D. / de With, P. H. N. | British Library Conference Proceedings | 2005


    Misregistration sensitivity in clustered-dot color halftones

    Oztan, B. / Sharma, G. / Loce, R.P. | British Library Online Contents | 2008


    Hidden Errors in Turbine Blade Moment Measurement and How to Avoid Them

    Boynton, R. / Society of Allied Weight Engineers | British Library Conference Proceedings | 1997



    Designing User-Interfaces for the Cockpit: Five Common Design Errors and How to Avoid Them

    Sherry, L. / Polson, P. / Feary, M. et al. | British Library Conference Proceedings | 2002