DOI QR코드

DOI QR Code

Realtime No-Reference Quality-Assessment Over Packet Video Networks

패킷 비디오 네트워크상의 실시간 무기준법 동영상 화질 평가방법

  • Sung, Duk-Gu (School of Information & Communication Eng., Sungkyunkwan Univ.) ;
  • Kim, Yo-Han (School of Information & Communication Eng., Sungkyunkwan Univ.) ;
  • Hana, Jung-Hyun (School of Information & Communication Eng., Sungkyunkwan Univ.) ;
  • Shin, Ji-Tae (School of Information & Communication Eng., Sungkyunkwan Univ.)
  • 성덕구 (성균관대학교 정보통신공학부) ;
  • 김요한 (성균관대학교 정보통신공학부) ;
  • 한정현 (성균관대학교 정보통신공학부) ;
  • 신지태 (성균관대학교 정보통신공학부)
  • Published : 2009.07.30

Abstract

No-Reference video-quality assessments are divided into two kinds of metrics based on decoding pixel domain or the bitstream one. Traditional full-/reduced- reference methods have difficulty to be deployed as realtime video transmission because it has problems of additional data, complexity, and assessment accuracy. This paper presents simple and highly accurate no-reference video-quality assessment in realtime video transmission. Our proposed method uses quantization parameter, motion vector, and information of transmission error. To evaluate performance of the proposed algorithm, we perform subjective test of video quality with the ITU-T P.910 Absolute Category Rating(ACR) method and compare our proposed algorithm with the subjective quality assessment method. Experimental results show the proposed quality metric has a high correlation (85%) in terms of subjective quality assessment.

기존의 무기준 동영상 화질 평가는 디코딩 픽셀 단에서 평가와 전송 에러를 고려한 비트스트림단에서 화질 평가 방법으로 나눌 수 있다. 기존의 방법은 추가 데이터 필요하고 복잡도와 평가 정확도등의 문제가 있어 실제적인 실시간 화질평가에 적용하기에 문제가 많다. 본 연구에서는 실시간 비디오 전송 환경에서 이용될 수 있는 간단하면서도 정확도가 높은 무기준법 화질 평가 방법을 제안한다. 본 논문에서 제안된 무기준법 화질평가 방법은 양자화 파라미터, 전송에러정보, 움직임 벡터정보를 이용한다. 제안된 방법을 검증하기 위해서, ITU-T P.910 ACR(Absolute Category Rating)을 사용하여, 기존의 전체 기준법과 주관적 화질 평가 대비의 상관도를 비교하였는데 제안방법이 85%이상의 상관도를 보여 주었다.

Keywords

References

  1. B. Girod, "What's wrong with mean-sqared error", Digital Images and human Vision, MIT Press, pp. 207-220, 1993
  2. VQEG Web Site, "http://www.its.bldrdoc.gov/vqeg/"
  3. ITU-T P.910 "Subjective Video Quality Assessment Methods For Multimedia Applications"
  4. Zhou Wang, "Blind measurement of blocking artifacts in images" Proc. IEEE Int. Conf. Image Proc, 2000 https://doi.org/10.1109/ICIP.2000.899622
  5. Pina Marziliano, 'A No-Reference perceptyal blur metric' Proc. IEEE Int. Conf. Image Proc, 2002 https://doi.org/10.1109/ICIP.2002.1038902
  6. Tao Liu “Subjective Quality Evaluation of Decoded Video in the Presence of Packet Losses”, ICASSP, 2007
  7. Yamada, Toru, Miyamoto, Yoshihiro, Serizawa, Masahiro "No-Reference Video Quality Estimation Based on Error-Concealment Effectiveness" Packet Video 2007, 2007
  8. H.264/AVC JM Reference Software home page, "http://iphome.hhi.de/suehring/tml"
  9. Yi Guo, Houqiang Li “"SVC/AVC loss simulator”", JVT-Q.069
  10. VQEG "Hybrid Perceptual/Bitstream Group Test Plan Draft Version 1.3", 2009
  11. J.-G.Kim, J. Kim, J. Shin, and C.-C. J. Kuo, "Coordinated packet-level protection with a corruption model for robust video transmission,"in Proc. of SPIE Visual Communications and Image Processing, pp.410-421, Dec. 2000 https://doi.org/10.1117/12.411818
  12. Stephen D. Voran, Stephen Wolf, "An objective video quality assessment system based on human perception", SPIE Human Vision, Visual Processing and Digital Display, 1993
  13. Minitab homepage, "http://www.minitab.co.kr/minitab/index.asp"
  14. ITU-T J.144 "Objective perceptual video quality measurement techniques for digital cable television in the presence of a full reference"
  15. ITS Video Quality Research home page, "http://www.its.bldrdoc.gov/ n3/video/"