No-Reference Model for Video Quality Assessment Based on SVM

Abstract:

This paper focuses on the video distortion which is caused by the packet loss. Considering the relationship between the human visual perception which is caused by the packet loss and the visual characteristic of the video content, we present a no-reference model for video quality assessment based on Support Vector Machine. The feature vector of the SVM contain temporal complexity, spatial complexity, the average number of bits per frame and the packet loss rate. Temporal complexity, spatial complexity and the average number of bits per frame represent the visual characteristic of the video content. The value of the packet loss rate means the distortion which is caused by the packet loss intuitively. Experimental results show that this model has a good consistency with the subjective.

• Periodical: Advanced Materials Research (Volumes 846-847)
• Pages: 1024-1030
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.846-847.1024
• Online since: November 2013
• Authors: Li Li Wu*, Chun Yan Yu
• Keywords: Bits, Discrete Cosine Transform, Motion Vector, No-Reference Video Quality, Packet Loss Rate, Support Vector Machine (SVM)

References

[1] Feng X, Liu T, Yang D, et al. Saliency inspired full-reference quality metrics for packet-loss-impaired video [J]. IEEE Transactions on Broadcasting, 2011: 57 (1): 81-88.

DOI: 10.1109/tbc.2010.2092150

[2] ITU-T Recommendation P. 910. Subjective video quality assessment methods for multimedia applications [S]. Geneva: International Telecommunication Inion, (1999).

[3] ITU-T Recommendation J. 148. Requirements for an objective perceptual multimedia quality model [S]. Geneva: International Telecommunication Inion, (2003).

[4] Narwaria M, Lin W, Liu A. Low-complexity video quality assessment using temporal quality variations [J]. IEEE Transactions on Multimedia, 2012: 14 (3): 525-535.

DOI: 10.1109/tmm.2012.2190589

[5] Zhang X, Wu L, Fang Y, et al. A Study of FR Video Quality Assessment of Real Time Video Stream [J]. International Journal, 2012: 3 (6): 1-7.

[6] Makar M, Lin Y C, de Araujo A F, et al. Compression of VQM features for low bit-rate video quality monitoring [A]. Proceedings of 2011 IEEE 13th International Workshop on Multimedia Signal Processing [C]. New York: Institute of Electrical and Electronics Engineers, 2011: 1-6.

DOI: 10.1109/mmsp.2011.6093809

[7] Babu R V, Bopardikar A S, Perkis A, et al. No-reference metrics for video streaming applications [A]. Proceedings of International Workshop on Packet Video [C]. New York: Institute of Electrical and Electronics Engineers, (2004).

[8] Yang Y, Lu Z, Wen X, et al. A No-Reference Video Quality Estimation Model over Wireless Networks [A]. Proceedings of 2011 IEEE Vehicular Technology Conference [C]. New York: Institute of Electrical and Electronics Engineers, 2011: 1-5.

DOI: 10.1109/vetecf.2011.6092829

[9] Wang B, Zou D, Ding R. Support Vector Regression Based Video Quality Prediction [A]. Proceedings of 2011 IEEE International Symposium on Multimedia [C]. New York: Institute of Electrical and Electronics Engineers, 2011: 476-481.

DOI: 10.1109/ism.2011.84

[10] Argyropoulos S, Raake A, Garcia M N, et al. No-reference bit stream model for video quality assessment of h. 264/AVC video based on packet loss visibility [A]. Proceedings of 2011 IEEE International Conference on Acoustics, Speech and Signal Processing [C]. New York: Institute of Electrical and Electronics Engineers, 2011: 1169-1172.

DOI: 10.1109/icassp.2011.5946617

[11] Christopher J C Burges. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998: 2 (2): 121-167.

[12] Yang Y, Lu Z, Wen X, et al. A transmission-aware video quality metric for lossy wireless network [A]. Proceedings of 2011 14th International Symposium on Wireless Personal Multimedia Communications [C]. New York: Institute of Electrical and Electronics Engineers, 2011: 1-5.

[13] Weston J, Watkins C. Multi-class support vector machines[R]. Technical Report CSD-TR-98-04, Department of Computer Science, Royal Holloway, University of London, May, (1998).

[14] Collobert R, Bengio S. SVMTorch: Support vector machines for large-scale regression problems[J]. The Journal of Machine Learning Research, 2001: 1: 143-160.

[15] ITU-R Recommendation BT. 500-11. Methodology for the subjective assessment of the quality of television pictures[S]. Geneva: International Telecommunication Inion, (2002).