The Journal of Supercomputing

, Volume 75, Issue 4, pp 1751–1765 | Cite as

Efficient video quality assessment for on-demand video transcoding using intensity variation analysis

  • Hyoungseok Kim
  • Joonseok ParkEmail author


Due to the wide spread usage of smart devices, adopting video contents service to the diverse end user’s service environment is an essential process. The heterogeneity of end users’ devices, usually referred as the device fragmentation, requires video transcoding which is a lossy process. Accordingly, the subsequent video quality degrading is inevitable. In such circumstances, minimizing perceptible quality loss of video is a key issue for the video contents service provider. However, the video quality loss caused in the process of transcoding is very difficult to measure. Because the “video quality” is a subjective term, it is almost impossible to estimate before video contents are delivered and actually serviced. To address this issue, many research efforts have been pursued for estimating subjective quality evaluation score using objective quality assessment metric. Structural Similarity (SSIM) is a well-known objective quality assessment method. Based on previous studies, this method has been used as a very effective quality assessment tool in video coding system. In this paper, we propose new video quality assessment metric using intensity variation analysis. The intensity metric-based video quality assessment has a high correlation with the SSIM regardless of the category of video contents, resolutions and even bitrate setting. The proposed method that measures inter-frame intensity variation (IV) is more efficient than SSIM in VBR transcoding system. Our experimental results show that the proposed video quality assessment shows up to 22 times faster than SSIM in the execution time. Ultimately, to take its advantage of the short latency and low execution overhead, IV-based video assessment is applicable to real on-demand transcoding and streaming environments while minimizing video quality degradation of transcoding.


Video transcoding Intensity variation Video quality assessment Structural Similarity 



This work was supported by INHA UNIVERSITY Research Grant.


  1. 1.
    Stockhammer T (2011) Dynamic adaptive streaming over HTTP–design principles and standards. In: Proceedings of the Second Annual ACM Conference on Multimedia Systems, pp 133–144Google Scholar
  2. 2.
    Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612CrossRefGoogle Scholar
  3. 3.
    Xin J, Lin C-W, Sun M-T (2005) Digital video transcoding. Proc IEEE 93(1):84–97CrossRefGoogle Scholar
  4. 4.
    Gonzalez RC, Woods RE (2008) Digital image processing, 3rd edn. Pearson Prentice Hall, Upper Saddle RiveGoogle Scholar
  5. 5.
    Paulikas S (2013) Estimation of degraded video quality of mobile H.264/AVC video streaming. In: Proceeding of EuroCon. IEEE, pp 694–699.
  6. 6.
    Ries M, Nemethova O, Rupp M (2008) Video quality estimation for mobile H.264/AVC video streaming. J Commun 3(1):41–50CrossRefGoogle Scholar
  7. 7.
    ITU-R Rec. BT. 500-10. Methodology for the subjective assessment of quality for television pictures (2012)Google Scholar
  8. 8.
    Furht B, Marqure O (eds) (2003) The handbook of video databases: design and applications. CRC Press, Boca Raton, pp 1041–1078Google Scholar
  9. 9.
    Yang C, Wang H, Po L (2007) Improved inter prediction based on structural similarity in H.264. In: IEEE International Conference on Signal Processing and Communications, vol 2, pp 340–343Google Scholar
  10. 10.
    Mai Z, Yang C, Kuang K, Po L (2006) A novel motion estimation method based on structural similarity for H.264 inter prediction. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, vol 2, pp 913–916Google Scholar
  11. 11.
    Ou T, Huang Y, Chen H (2010) A perceptual-based approach to bit allocation for H. 264 encoder. In: Proceeding of SPIE 7744, Visual Communications and Image Processing.
  12. 12.
    Wang S, Rehman A et al (2012) SSIM-motivated rate-distortion optimization for video coding. IEEE Trans Circuits Syst Video Technol 22(4):516–529CrossRefGoogle Scholar
  13. 13.
    Ou T-S, Huang Y-H, Chen HH (2011) SSIM-based perceptual rate control for video coding. IEEE Trans Circuits Syst Video Technol 21(5):682–690CrossRefGoogle Scholar
  14. 14.
    Sheikh HR, Bovik AC (2006) Image information and visual quality. IEEE Trans Image Process 15(2):430–444CrossRefGoogle Scholar
  15. 15.
    Han Y et al (2013) A new image fusion performance metric based on visual information fidelity. Inf Fusion 14(2):127–135CrossRefGoogle Scholar
  16. 16.
    Geisler WS, Banks MS (1995) Visual performance. In: Bass M (ed) Handbook of optics. McGraw-Hill, New YorkGoogle Scholar
  17. 17.
    Cormack LK (2000) Computational models, of early human vision. In: Bovik A (ed) Handbook of image and video processing. Academic Press, LondonGoogle Scholar
  18. 18.
    Chuang H-M, Chen Y-S, Lin C-Y, Yu P-C (2016) Featuring the e-service quality of online website from a varied perspective. Hum Centric Comput Inf Sci 6:6. CrossRefGoogle Scholar
  19. 19.
    Sarif BA, Pourazad MT, Nasiopoulos P et al (2015) Fairness scheme for energy efficient H.264/AVC-based video sensor network. Hum Centric Comput Inf Sci 5:7. CrossRefGoogle Scholar
  20. 20.
    Lee SG, Cha EY (2016) Style classification and visualization of art painting’s genre using self-organizing maps. Hum Centric Comput Inf Sci 6:7. CrossRefGoogle Scholar
  21. 21.
  22. 22.
    FFmpeg project.

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.LG Electronics Inc.SeoulRepublic of Korea
  2. 2.Inha UniversityIncheonRepublic of Korea

Personalised recommendations