Spatio-temporal resolution enhancement of video sequence based on super-resolution reconstruction

Miki Haseyama, Daisuke Izumi, Makoto Takizawa

Abstract

This paper proposes a new spatio-temporal resolution enhancement method of video sequences based on superresolution reconstruction. The proposed method derives a new observation model based on feature point correspondence between successive frames. The observation model is defined by including the motion estimation function in computing the warping matrix. Also, a new constraint is introduced to the optimization formula for estimating the parameters of the observation model, in order to achieve effective resolution-enhancement. By the newly obtained matrix and the new constraint introduction make accurate high-resolution and high frame rate video sequences. Simulation results are shown to confirm the high performance of the proposed method.
BibTeX
@inproceedings{haseyama2010spatio,
  author = {Miki Haseyama and Daisuke Izumi and Makoto Takizawa},
  title = {{Spatio-temporal resolution enhancement of video sequence based on super-resolution reconstruction}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2010},
  doi = {10.1109/icassp.2010.5495233},
}

Loading related content...

Figure