Abstract
Objective quality measures are usually concerned with overall degradation in quality, disregarding impairments and artifacts such as those due to packet loss error concealment. Unfortunately, it is particularly hard to model due to its unpredictable nature and content-dependency. We propose a human perception based no-reference framework utilizing motion-compensated frame interpolation and colour gradients to identify and localize packet loss impaired regions in video frames. The unique and principal contribution of this work is the attempt to mimic the human visual system throughout the process instead of the traditional approach of trying to replicate the mean opinion score.
Supported by Indian Statistical Institute.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shabtay, D. et al.: Video packet loss concealment detection based on image content. In: EUSIPCO 2008, Lausanne, Switzerland, pp. 1–5, 25–29 August 2008
Farrugia, R.A., et al.: A support vector machine approach for detection and localization of transmission errors within standard H.263++ decoders. IEEE Trans. Multimedia 11(7), 1323–1330 (2009)
Chen, J., et al.: An effective error concealment method based on abrupt scene change detection algorithm. In: ICISCE 2012, pp. 1–4 (2012)
Saad, M.A., et al.: Blind prediction of natural video quality. IEEE Trans. Image Process. 23(3), 1352–1365 (2014)
Argyropoulos, S., et al.: No reference bit stream model for video quality assessment of H.264/AVC video based on packet loss visibility. In: ICASSP-2011, pp. 1169–1172 (2011)
Goodall, T.R., et al.: Detecting and mapping video impairments. IEEE Trans. Image Process. 28(6), 2680–2691 (2019)
Reibman, A.R., et al.: Characterizing packet-loss impairments in compressed video. In: ICIP 2007, pp. V-77–V-80 (2007)
Morais, D., et al.: A Correlation-Based No-Reference Packet-Loss Metric. Anais de XXXIV Simpósio Brasileiro de Telecomunicações (2016)
Manasa, K., et al.: A perceptually motivated no-reference video quality assessment algorithm for packet loss artefacts. In: QOMEX 2014, pp. 67–68, Singapore, 18–20 September 2014
Babu, R.V., et al.: No-Reference metrics for video streaming applications. In: Proceedings International Workshop on Packet Video (2004)
Glavota, I. et al.: Pixel-based statistical analysis of packet loss artefact features. In: ZINC, pp. 16–19 (2016)
Meyer, S. et al.: Phase-Based frame interpolation for video. In: CVPR 2015, pp. 1410–1418 (2016)
Harel, J., et al.: Graph-Based visual saliency. In: NIPS, pp. 545–552 (2006)
Vu, P.V., et al.: ViS3: an algorithm for video quality assessment via analysis of spatial and spatiotemporal slices. J. Elect. Imag. 23(1), 013016 (2014)
Feng, X., et al.: Saliency based objective quality assessment of decoded video affected by packet losses. In: ICIP, pp. 2560–2563 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Sanyal, S., Palit, S. (2021). A No-Reference Perception Based Metric for Detection of Packet Loss Induced Artifacts in Videos. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Communications in Computer and Information Science, vol 1517. Springer, Cham. https://doi.org/10.1007/978-3-030-92310-5_71
Download citation
DOI: https://doi.org/10.1007/978-3-030-92310-5_71
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92309-9
Online ISBN: 978-3-030-92310-5
eBook Packages: Computer ScienceComputer Science (R0)