Neural and Fuzzy Logic Video Rate Prediction for MPEG Buffer Control

Data rate management of compressed digital video has been a technically challenging task since it is vitally important in various audio-visual telecommunication services to achieve an effective video data rate (video rate) control scheme. It has a large influence on video quality and traffic congestion in B-ISDN networks. Up to date, this issue has been treated mainly from the teletraffic control point of view, i.e. by modelling congestion control via network protocols. Relatively less attention has been focused on video rate management in the source coding side. In this chapter we consider that it is more efficient and less costly to control video rate at the video source than handling network congestion (or overloading) due to an extremely large quantity of incoming variable bit rate (VBR) video traffic. Thus this chapter investigates effective rate control algorithms for video encoders. Considering the non-stationary nature of video rate derived from scene variations (i.e. the wide band nature of digital video), we adopted two nonlinear approaches; radial basis function (RBF) estimation using a neural network-based approach and fuzzy logic control as a nonlinear feedback control. The RBF network scheme is primarily discussed and then the fuzzy logic-based scheme is compared to it. The performance is evaluated using the criterion how effectively video rate is maintained within a specified range or at a value while achieving satisfactory video quality.

[1]  Dipankar Raychaudhuri,et al.  TES-based traffic modeling for performance evaluation of integrated networks , 1992, [Proceedings] IEEE INFOCOM '92: The Conference on Computer Communications.

[2]  Chng Eng Siong,et al.  Efficient computational schemes for the orthogonal least squares algorithm , 1995, IEEE Trans. Signal Process..

[3]  Sheng Chen,et al.  Adaptive Bayesian equalizer with decision feedback , 1993, IEEE Trans. Signal Process..

[4]  Yoo-Sok Saw,et al.  Feed-forward buffering and rate control based on scene change featureslll FOR MPEG VIDEO CODER , 1996, 1996 8th European Signal Processing Conference (EUSIPCO 1996).

[5]  Sheng Chen.  Nonlinear time series modelling and prediction using Gaussian RBF networks with enhanced clustering and RLS learning , 1995 .

[6]  Sheng Chen,et al.  Adaptive Bayesian decision feedback equalizer for dispersive mobile radio channels , 1995, IEEE Trans. Commun..

[7]  P.J. King,et al.  The application of fuzzy control systems to industrial processes , 1977, Autom..

[8]  Oscal T.-C. Chen,et al.  Image compression using self-organization networks , 1994, IEEE Trans. Circuits Syst. Video Technol..

[9]  Dipankar Raychaudhuri,et al.  Statistically based buffer control policies for constant rate transmission of compressed digital video , 1991, IEEE Trans. Commun..

[10]  Dipankar Raychaudhuri,et al.  TES-based video source modeling for performance evaluation of integrated networks , 1994, IEEE Trans. Commun..

[11]  S.H. Supangkat,et al.  Quantity Control for JPEG Image Data Compression Using Fuzzy Logic Algorithm , 1994, IEEE International Conference on Consumer Electronics.

[12]  Yoo-Sok Saw,et al.  Rate-distortion analysis of nonlinear quantisers for MPEG video coders: sigmoidal and unimodal quantiser control functions , 1998 .

[13]  R. Guerrieri,et al.  An H.261-compatible fuzzy-controlled coder for videophone sequences , 1994, Proceedings of 1994 IEEE 3rd International Fuzzy Systems Conference.

[14]  C. J. Wu,et al.  Application of fuzzy controller to JPEG , 1994 .

[15]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[16]  E. Kreyszig.  Introductory Functional Analysis With Applications , 1978 .

[17]  Simon Haykin,et al.  Neural network approaches to image compression , 1995, Proc. IEEE.

[18]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[19]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[20]  Hideyuki Takagi.  Application of neural networks and fuzzy logic to consumer products , 1992, Proceedings of the 1992 International Conference on Industrial Electronics, Control, Instrumentation, and Automation.

[21]  Sheng Chen,et al.  A clustering technique for digital communications channel equalization using radial basis function networks , 1993, IEEE Trans. Neural Networks.

[22]  Bart Kosko,et al.  Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence , 1991 .

[23]  Andreas S. Weigend,et al.  The Future of Time Series: Learning and Understanding , 1993 .

[24]  B. Melamed,et al.  Traffic modeling for telecommunications networks , 1994, IEEE Communications Magazine.

[25]  Bernard Mulgrew,et al.  Nonlinear predictive rate control for constant bit rate MPEG video coders , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[26]  H. Tong.  Non-linear time series. A dynamical system approach , 1990 .

[27]  Peter Grant,et al.  Analogue and Digital Signal Processing and Coding , 1989 .

[28]  Chuen-Tsai Sun,et al.  Neuro-fuzzy modeling and control , 1995, Proc. IEEE.

[29]  Chuen-Chien Lee.  FUZZY LOGIC CONTROL SYSTEMS: FUZZY LOGIC CONTROLLER - PART I , 1990 .

[30]  Stephen J. Eglen,et al.  Image compression using neural networks , 1994 .

[31]  Madan M. Gupta,et al.  Approximate reasoning in expert systems , 1985 .

[32]  Bernard Mulgrew,et al.  Video rate control using a radial basis function estimator for constant bit-rate MPEG coders , 1998, Signal Process. Image Commun..

[33]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[34]  Andreas S. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[35]  James D. Keeler,et al.  Layered Neural Networks with Gaussian Hidden Units as Universal Approximations , 1990, Neural Computation.

[36]  Mitsuru Nomura,et al.  Basic characteristics of variable rate video coding in ATM environment , 1989, IEEE J. Sel. Areas Commun..