Objective quality assessment of MPEG-2 video streams by using CBP neural networks

IEEE Transactions on Neural Networks - Tập 13 Số 4 - Trang 939-947 - 2002
P. Gastaldo1, S. Rovetta2, R. Zunino1
1Department of Biophysical and Electronic Engineering-DIBE, University of Genoa, Genoa, Italy
2Department of Computer and Information Sciences-DISI, University of Genoa, Genoa, Italy

Tóm tắt

The increasing use of compression standards in broadcasting digital TV has raised the need for established criteria to measure perceived quality. Novel methods must take into account the specific artifacts introduced by digital compression techniques. This paper presents a methodology using circular backpropagation (CBP) neural networks for the objective quality assessment of motion picture expert group (MPEG) video streams. Objective features are continuously extracted from compressed video streams on a frame-by-frame basis; they feed the CBP network estimating the corresponding perceived quality. The resulting adaptive modeling of subjective perception supports a real-time system for monitoring displayed video quality. The overall system mimics perception but does not require an analytical model of the underlying physical phenomenon. The ability to process compressed video streams represents a crucial advantage over existing approaches, as avoiding the decoding process greatly enhances the system's real-time performance. Experimental evidence confirmed the approach validity. The system was tested on real test videos; they included different contents ranging from fiction to sport. The neural model provided a satisfactory, continuous-time approximation for actual scoring curves, which was validated statistically in terms of confidence analysis. As expected, videos with slow-varying contents such as fiction featured the best performances.

Từ khóa

#Quality assessment #Streaming media #Neural networks #Video compression #Transform coding #Real time systems #System testing #Measurement standards #Digital video broadcasting #TV broadcasting

Tài liệu tham khảo

mood, 1974, Introduction to the Theory of Statistics 10.1016/S0925-2312(97)00080-5 10.1109/82.769777 10.1109/72.914531 10.1117/12.371210 10.1109/76.875525 10.1049/el:20000847 10.1016/S0923-5965(98)00014-9 rumelhart, 1986, Parallel Distributed Processing, 10.7551/mitpress/5236.001.0001 10.1109/72.554194 vapnik, 1998, Statist Learning Theory 10.1109/72.774275 10.1007/BF00332914 1996, Information Technology&#x2014 Generic Coding of Moving Pictures and Associated Audio Video Information Video 10.5594/J04353 10.1049/cp:19950676 schiffman, 1996, Sensation and Perception&#x2014 An Integrated Approach zou, 1997, methods for evaluation of digital television picture quality, IEEE Broadcast Tech Soc &#x2014 4th Meet G-2 1 6 Audio Video Techniques Committee G-2 1 Compression Processing Subcommittee 10.5594/J06425 voran, 1992, the development and evaluation of an objective video quality assessment system that emulates human viewing panels, Broadcasting Convention 1992 IBC International, 504 10.1109/72.238311 10.5594/J04308 10.5594/J06401 10.1109/11.664028 10.5594/J04354 2000, Methodology for the Subjective Assessment of the Quality of Television Pictures 1996, Introduction of a New Method for Single Stimulus Continuous Quality Evaluation (SSCQE) 10.1109/T-C.1974.224051 joliffe, 1986, Principal Component Analysis, 10.1007/978-1-4757-1904-8 10.1016/S0923-5965(99)00061-2 10.1080/01621459.1987.10478427 10.5594/J04356 10.5594/J15812