Paper Info
Title
Subsampling Input Based Side Information Creation in Wyner-Ziv Video Coding
Abstract
Distributed video coding (DVC) has been intensively studied in recent years. This new coding paradigm substantially differs from conventional prediction-based video codecs such as MPEG and H.26x, which are characterized by a complex encoder and simple decoder. The conventional DVC codec, e.g., DISCOVER codec, uses advanced frame interpolation techniques to create SI based on adjacent decoded reference frames. The quality of SI is a well-recognized factor in the RD performance of WZ video coding. A high SI quality implies a high correlation between the created SI and the original WZ frame, which then decreases the rate required to achieve a given decoded quality. Clearly, the performance of an SI creation process based on adjacent previously decoded frames is limited by the quality of the past and the future reference frames as well as the distance and motion behavior between them. The correlation between high-motion frames is low and vice versa. That is, SI quality in the conventional codecs depends on the temporal correlation of key frames, which affects the bit rate and PSNR of the compression process. In this work, a novel DVC architecture for dealing with the cases of high-motion and large GOP-size sequences is proposed to better the rate-distortion (RD) performance. For high-motion video sequences, the proposed architecture generates SI by using sub sampled spatial information instead of interpolated temporal information. the proposed approach separates the video sequence into sub sampled key frames and corresponding WZ frames, which changes the creation of SI. That is, all successive frames on the encoder side are downsized to sub-frames, which are then compressed by an H.264/AVC intra encoder. Experimental results reveal that the sub sampling input based DVC codec can gain up to 1.47 dB in the RD measures and maintains the most important characteristic of the DVC codec, the encoder is lightweight, as compared with the conventional WZ codec, respectively.
Year
DOI
Venue
2013
10.1109/DCC.2013.98
DCC
Keywords
Field
DocType
subsampling input,conventional wz codec,dvc codec,wz video coding,conventional dvc codec,si quality,wyner-ziv video coding,conventional prediction-based video,high si quality,side information creation,discover codec,si creation process,key frame,correlation,data compression,image reconstruction,computer architecture,image resolution,image processing,codecs,interpolation,silicon,computer vision
Reference frame,Computer vision,Computer science,Interpolation,Image processing,Theoretical computer science,Coding (social sciences),Motion interpolation,Encoder,Artificial intelligence,Data compression,Codec
Conference
ISSN
Citations 
PageRank 
1068-0314
1
0.35
References 
Authors
0
3
Name
Order
Citations
PageRank
Yun-Chung Shen1346.30
Ji-Ciao Luo210.35
Ja-ling Wu31569168.11