Abstract

This paper presents a parallel and scalable solution for adaptive deblocking filtering in H.264/AVC. While traditionally in deblocking filtering, the edges in a macroblock are processed in a sequential order, this paper demonstrates how algorithm modifications can be used to enable processing multiple consecutive edges at the same time. The proposed method increases the throughput in proportion to the number of edges that are being processed simultaneously without affecting the PSNR and bit-rate. Details of the method to process 2 consecutive edges in parallel as well as extensions to process 4 and 8 consecutive edges, are provided. A dedicated hardware architecture to process 2 edges is presented along with synthesis results. The architecture achieves a 2x increase in throughput at the expense of a 2.2x increase in area and a 1.23x increase in power.

Original languageEnglish (US)
Title of host publicationIEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation
Pages116-121
Number of pages6
DOIs
StatePublished - 2010
Event2010 IEEE Workshop on Signal Processing Systems, SiPS 2010 - San Francisco, CA, United States
Duration: Oct 6 2010Oct 8 2010

Other

Other2010 IEEE Workshop on Signal Processing Systems, SiPS 2010
CountryUnited States
CitySan Francisco, CA
Period10/6/1010/8/10

Fingerprint

Consecutive
Throughput
Filter
Adaptive filtering
Adaptive Filtering
Hardware Architecture
Hardware
Proportion
Filtering
Processing
Synthesis
Demonstrate
Architecture

Keywords

  • Deblocking filter
  • Parallel architecture

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Applied Mathematics
  • Hardware and Architecture

Cite this

Vijay, S., Chakrabarti, C., & Karam, L. (2010). Parallel deblocking filter for H.264 AVC/SVC. In IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation (pp. 116-121). [5624773] https://doi.org/10.1109/SIPS.2010.5624773

Parallel deblocking filter for H.264 AVC/SVC. / Vijay, S.; Chakrabarti, Chaitali; Karam, Lina.

IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation. 2010. p. 116-121 5624773.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Vijay, S, Chakrabarti, C & Karam, L 2010, Parallel deblocking filter for H.264 AVC/SVC. in IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation., 5624773, pp. 116-121, 2010 IEEE Workshop on Signal Processing Systems, SiPS 2010, San Francisco, CA, United States, 10/6/10. https://doi.org/10.1109/SIPS.2010.5624773
Vijay S, Chakrabarti C, Karam L. Parallel deblocking filter for H.264 AVC/SVC. In IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation. 2010. p. 116-121. 5624773 https://doi.org/10.1109/SIPS.2010.5624773
Vijay, S. ; Chakrabarti, Chaitali ; Karam, Lina. / Parallel deblocking filter for H.264 AVC/SVC. IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation. 2010. pp. 116-121
@inproceedings{253b46225b204fa1b061de259dca4386,
title = "Parallel deblocking filter for H.264 AVC/SVC",
abstract = "This paper presents a parallel and scalable solution for adaptive deblocking filtering in H.264/AVC. While traditionally in deblocking filtering, the edges in a macroblock are processed in a sequential order, this paper demonstrates how algorithm modifications can be used to enable processing multiple consecutive edges at the same time. The proposed method increases the throughput in proportion to the number of edges that are being processed simultaneously without affecting the PSNR and bit-rate. Details of the method to process 2 consecutive edges in parallel as well as extensions to process 4 and 8 consecutive edges, are provided. A dedicated hardware architecture to process 2 edges is presented along with synthesis results. The architecture achieves a 2x increase in throughput at the expense of a 2.2x increase in area and a 1.23x increase in power.",
keywords = "Deblocking filter, Parallel architecture",
author = "S. Vijay and Chaitali Chakrabarti and Lina Karam",
year = "2010",
doi = "10.1109/SIPS.2010.5624773",
language = "English (US)",
isbn = "9781424489336",
pages = "116--121",
booktitle = "IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation",

}

TY - GEN

T1 - Parallel deblocking filter for H.264 AVC/SVC

AU - Vijay, S.

AU - Chakrabarti, Chaitali

AU - Karam, Lina

PY - 2010

Y1 - 2010

N2 - This paper presents a parallel and scalable solution for adaptive deblocking filtering in H.264/AVC. While traditionally in deblocking filtering, the edges in a macroblock are processed in a sequential order, this paper demonstrates how algorithm modifications can be used to enable processing multiple consecutive edges at the same time. The proposed method increases the throughput in proportion to the number of edges that are being processed simultaneously without affecting the PSNR and bit-rate. Details of the method to process 2 consecutive edges in parallel as well as extensions to process 4 and 8 consecutive edges, are provided. A dedicated hardware architecture to process 2 edges is presented along with synthesis results. The architecture achieves a 2x increase in throughput at the expense of a 2.2x increase in area and a 1.23x increase in power.

AB - This paper presents a parallel and scalable solution for adaptive deblocking filtering in H.264/AVC. While traditionally in deblocking filtering, the edges in a macroblock are processed in a sequential order, this paper demonstrates how algorithm modifications can be used to enable processing multiple consecutive edges at the same time. The proposed method increases the throughput in proportion to the number of edges that are being processed simultaneously without affecting the PSNR and bit-rate. Details of the method to process 2 consecutive edges in parallel as well as extensions to process 4 and 8 consecutive edges, are provided. A dedicated hardware architecture to process 2 edges is presented along with synthesis results. The architecture achieves a 2x increase in throughput at the expense of a 2.2x increase in area and a 1.23x increase in power.

KW - Deblocking filter

KW - Parallel architecture

UR - http://www.scopus.com/inward/record.url?scp=78650325284&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650325284&partnerID=8YFLogxK

U2 - 10.1109/SIPS.2010.5624773

DO - 10.1109/SIPS.2010.5624773

M3 - Conference contribution

AN - SCOPUS:78650325284

SN - 9781424489336

SP - 116

EP - 121

BT - IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation

ER -