5th International Mobile Multimedia Communications Conference

Research Article

Super-resolution reconstruction of video sequences based on back-projection and motion estimation

Download610 downloads
  • @INPROCEEDINGS{10.4108/ICST.MOBIMEDIA2009.7469,
        author={Giaime Ginesu and Tiziana Dess\'{\i} and Luigi Atzori and Daniele D. Giusto},
        title={Super-resolution reconstruction of video sequences based on back-projection and motion estimation},
        proceedings={5th International Mobile Multimedia Communications Conference},
        publisher={ICST},
        proceedings_a={MOBIMEDIA},
        year={2010},
        month={5},
        keywords={},
        doi={10.4108/ICST.MOBIMEDIA2009.7469}
    }
    
  • Giaime Ginesu
    Tiziana Dessì
    Luigi Atzori
    Daniele D. Giusto
    Year: 2010
    Super-resolution reconstruction of video sequences based on back-projection and motion estimation
    MOBIMEDIA
    ICST
    DOI: 10.4108/ICST.MOBIMEDIA2009.7469
Giaime Ginesu1,*, Tiziana Dessì1,*, Luigi Atzori1,*, Daniele D. Giusto1,*
  • 1: Department of Electronic Engineering, University of Cagliari, Italy.
*Contact email: g.ginesu@diee.unica.it, tiziana.dessi@gmail.com, l.atzori@diee.unica.it, ddgiusto@unica.it

Abstract

Bandwidth limitation and service costs are important factors when dealing with mobile multimedia contents’ fruition. Super-resolution reconstruction might be a relevant solution, since it allows for restoring the original spatial resolution from low-resolution compressed data. In this way, both content and service providers, not to tell the final users, are relieved from the burden of providing and supporting large multimedia data transfer. In the proposed work, the highresolution video sequence is reconstructed through iterative processing of inter-frame information and interpolative techniques. Resolution enhancement is based on iterative update of the high-resolution image estimate through motion and scene change detection. The devised technique is derived from the work of Irani and Peleg [8]. The main contribution of the proposed approach consists in the generalization of the transformation model through the exploitation of local change. Results are encouraging and prove that the devised scheme outperforms alternative techniques.