Presentation | 2012-03-08 Distributed Video Coding by applying Super Resolution with Learning-Based Kernel Regression Ryotaro NAKAMURA, Shinobu KUDOH, Takayuki NAKACHI, Nozomu HAMADA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Distributed video coding(DVC) is a novel and interesting video coding scheme which utilizes inter-frame prediction at decoder. However, the coding efficiency of DVC is inferior as compared to the existing coding systems such as H.264/AVC etc. The coding efficiency of DVC is significantly affected by the prediction accuracy at generating side information and the data amount of the key-frames. This study tries to improve the coding efficiency of DVC by applying super resolution technique. The bit rate for key-frame coding is reduced by employing down-sampling at the encoder. In addition, the side information is generated by applying motion-compensation to the key frames with low resolution, then image interpolation employing kernel regression algorithm is applied. This process may reduce the amount of error correction. Experiments applied to several standard video images show the coding efficiency improvement by the proposed method at medium- and low-bit-rates. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Distributed Video Coding / Super Resolution / Kernel Regression / Video Coding / k-means Clustering |
Paper # | CAS2011-111,SIP2011-131,CS2011-103 |
Date of Issue |
Conference Information | |
Committee | CAS |
---|---|
Conference Date | 2012/3/1(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Circuits and Systems (CAS) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Distributed Video Coding by applying Super Resolution with Learning-Based Kernel Regression |
Sub Title (in English) | |
Keyword(1) | Distributed Video Coding |
Keyword(2) | Super Resolution |
Keyword(3) | Kernel Regression |
Keyword(4) | Video Coding |
Keyword(5) | k-means Clustering |
1st Author's Name | Ryotaro NAKAMURA |
1st Author's Affiliation | Department of System Design Engineering, Faculty of Science and Technology, Keio University() |
2nd Author's Name | Shinobu KUDOH |
2nd Author's Affiliation | / NTT Network Innovation Laboratories, Nippon Telegraph and Telephone Corporation |
3rd Author's Name | Takayuki NAKACHI |
3rd Author's Affiliation | Department of System Design Engineering, Faculty of Science and Technology, Keio University |
4th Author's Name | Nozomu HAMADA |
4th Author's Affiliation | |
Date | 2012-03-08 |
Paper # | CAS2011-111,SIP2011-131,CS2011-103 |
Volume (vol) | vol.111 |
Number (no) | 465 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |