A supervised neural constant bit rate video controller for MPEG2 encoders

Author

De Castro, Fernando C C ; De Castro, Maria C F ; Arantes, Dalton S.

Author_Institution

Dept. de Comunicacoes, Univ. Estadual de Campinas, Sao Paulo, Brazil

Volume

2

fYear

1998

fDate

9-13 Aug 1998

Firstpage

504

Abstract

A supervised training algorithm is used in a radial basis function neural network in order to improve the performance of a recently introduced nonlinear predictive rate controller for MPEG2 encoders. The algorithm, which is based on the stochastic gradient method, is used for updating the radial basis centers. By means of extensive computer simulation with standard video sequences, practical design parameters are presented for buffer control in constant bit rate MPEG2 video encoders

Keywords

buffer storage; gradient methods; image sequences; learning (artificial intelligence); predictive control; radial basis function networks; stochastic processes; video coding; MPEG2 encoders; buffer control; computer simulation; constant bit rate encoders; nonlinear predictive rate controller; performance; radial basis center updating; radial basis function neural network; stochastic gradient method; supervised training algorithm; video sequences; Artificial neural networks; Bit rate; Electronic mail; Layout; Neural networks; Neurons; Radial basis function networks; Signal to noise ratio; Stochastic processes; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Telecommunications Symposium, 1998. ITS '98 Proceedings. SBT/IEEE International

Conference_Location

Sao Paulo

Print_ISBN

0-7803-5030-8

Type

conf

DOI

10.1109/ITS.1998.718445

Filename

718445