No-reference video quality assessment using MPEG analysis

Jacob Søgaard; Søren Forchhammer; Jari Korhonen

doi:10.1109/PCS.2013.6737708

No-reference video quality assessment using MPEG analysis

Jacob Søgaard, Søren Forchhammer, Jari Korhonen

Computing Science

Technical University of Denmark

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

5 Citations (Scopus)

Abstract

We present a method for No-Reference (NR) Video Quality Assessment (VQA) for decoded video without access to the bitstream. This is achieved by extracting and pooling features from a NR image quality assessment method used frame by frame. We also present methods to identify the video coding and estimate the video coding parameters for MPEG-2 and H.264/AVC which can be used to improve the VQA. The analysis differs from most other video coding analysis methods since it is without access to the bitstream. The results show that our proposed method is competitive with other recent NR VQA methods for MPEG-2 and H.264/AVC.

Original language	English
Title of host publication	2013 Picture Coding Symposium, PCS 2013 - Proceedings
Publisher	IEEE Computer Society
Pages	161-164
Number of pages	4
ISBN (Print)	9781479902941
DOIs	https://doi.org/10.1109/PCS.2013.6737708
Publication status	Published - 2013
Event	2013 Picture Coding Symposium, PCS 2013 - San Jose, CA, United States Duration: 8 Dec 2013 → 11 Dec 2013

Conference

Conference	2013 Picture Coding Symposium, PCS 2013
Country/Territory	United States
City	San Jose, CA
Period	8/12/13 → 11/12/13

Keywords

H.264/AVC analysis
MPEG-2 analysis
No-reference
Quantization estimation
Video quality assessment

Access to Document

10.1109/PCS.2013.6737708

Cite this

@inproceedings{665714017f954cac8c663fc200ec0955,

title = "No-reference video quality assessment using MPEG analysis",

abstract = "We present a method for No-Reference (NR) Video Quality Assessment (VQA) for decoded video without access to the bitstream. This is achieved by extracting and pooling features from a NR image quality assessment method used frame by frame. We also present methods to identify the video coding and estimate the video coding parameters for MPEG-2 and H.264/AVC which can be used to improve the VQA. The analysis differs from most other video coding analysis methods since it is without access to the bitstream. The results show that our proposed method is competitive with other recent NR VQA methods for MPEG-2 and H.264/AVC.",

keywords = "H.264/AVC analysis, MPEG-2 analysis, No-reference, Quantization estimation, Video quality assessment",

author = "Jacob S{\o}gaard and S{\o}ren Forchhammer and Jari Korhonen",

year = "2013",

doi = "10.1109/PCS.2013.6737708",

language = "English",

isbn = "9781479902941",

pages = "161--164",

booktitle = "2013 Picture Coding Symposium, PCS 2013 - Proceedings",

publisher = "IEEE Computer Society",

note = "2013 Picture Coding Symposium, PCS 2013 ; Conference date: 08-12-2013 Through 11-12-2013",

}

TY - GEN

T1 - No-reference video quality assessment using MPEG analysis

AU - Søgaard, Jacob

AU - Forchhammer, Søren

AU - Korhonen, Jari

PY - 2013

Y1 - 2013

N2 - We present a method for No-Reference (NR) Video Quality Assessment (VQA) for decoded video without access to the bitstream. This is achieved by extracting and pooling features from a NR image quality assessment method used frame by frame. We also present methods to identify the video coding and estimate the video coding parameters for MPEG-2 and H.264/AVC which can be used to improve the VQA. The analysis differs from most other video coding analysis methods since it is without access to the bitstream. The results show that our proposed method is competitive with other recent NR VQA methods for MPEG-2 and H.264/AVC.

AB - We present a method for No-Reference (NR) Video Quality Assessment (VQA) for decoded video without access to the bitstream. This is achieved by extracting and pooling features from a NR image quality assessment method used frame by frame. We also present methods to identify the video coding and estimate the video coding parameters for MPEG-2 and H.264/AVC which can be used to improve the VQA. The analysis differs from most other video coding analysis methods since it is without access to the bitstream. The results show that our proposed method is competitive with other recent NR VQA methods for MPEG-2 and H.264/AVC.

KW - H.264/AVC analysis

KW - MPEG-2 analysis

KW - No-reference

KW - Quantization estimation

KW - Video quality assessment

UR - http://www.scopus.com/inward/record.url?scp=84897710278&partnerID=8YFLogxK

U2 - 10.1109/PCS.2013.6737708

DO - 10.1109/PCS.2013.6737708

M3 - Published conference contribution

AN - SCOPUS:84897710278

SN - 9781479902941

SP - 161

EP - 164

BT - 2013 Picture Coding Symposium, PCS 2013 - Proceedings

PB - IEEE Computer Society

T2 - 2013 Picture Coding Symposium, PCS 2013

Y2 - 8 December 2013 through 11 December 2013

ER -

No-reference video quality assessment using MPEG analysis

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this