We present a method for boosting the resolution of ‘target’ frames of video using available supra-Nyquist information in surrounding frames during slow scene motion. Pixels in the frames surrounding a target frame were aligned to the target frame at subpixel resolution, by estimating translations of small upsampled image patches surrounding each pixel. This analysis was performed locally in order to account for the kinds of complex scene motion typical of human face imagery, motion which cannot often be effectively modeled using whole-image 2D affine transforms. Composite super-resolved images were built up from translated pixels, and missing pixels in the super-resolved pixel plane were imputed via adaptive-bandwidth bandpass interpolation and median filtering. Ambiguities in motion estimation due to the ‘aperture problem’ were systematically explored through visualization.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Super-Resolution of Video Sequences Using Local Motion Estimates


    Contributors:


    Publication date :

    2007-10-01


    Size :

    2631546 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Simultaneous Super-Resolution for Video Sequences

    Victor, M. / Zibetti, W. / Mayer, J. | British Library Conference Proceedings | 2005


    Simultaneous super-resolution for video sequences

    Zibetti, Marcelo / Mayer, Joceli | IEEE | 2005


    Practical Super-Resolution from Dynamic Video Sequences

    Jiang, Z. / Wong, T.-T. / Bao, H. et al. | British Library Conference Proceedings | 2003


    Practical super-resolution from dynamic video sequences

    Zhongding Jiang, / Tien-Tsin Wong, / Hujun Bao, | IEEE | 2003