Dynamic complexity prediction and regulation of MPEG2 decoding in a media processor
AssigneeKoninklijke Philips Electronics N.V.
InventorsTse-Hua Lan, Yingwei Chen, Zhun Zhong
Life of this patent
Estimating the term…
Abstract
A method and system of regulating the computation load of an MPEG decoder in a video processing system are provided. The video processing system processes the header information of a compressed video data stream including a plurality of macroblocks with a motion vector associated therewith. Then, the computation load of each functional block of the MPEG decoder is adjusted according to predetermined criteria; thus, substantial computational overhead is desirably avoided.
Claims30
An MPEG decoder for improving decoding efficiency by scaling the decoding of an encoded digital video signal, comprising:
- means for decoding a compressed video data stream including a plurality of macroblocks, said decoding means being operative to output quantized data from said decoded data stream;
- means for performing an inverse quantization operation on said quantized data;
- means for performing an inverse discrete cosine transform (IDCT) of the output from said means for performing an inverse quantization operation;
- means for extracting header information from said quantized data from said decoding means and for performing a prediction operation according to predetermined criteria;
- means for generating a motion compensated reference value based on said quantized data from said decoding means;
- and,
- means for adding the output from said IDCT means and said motion generating means to produce motion compensated pictures.
A programmable video decoding system, comprising:
- a variable length decoder (VLD) configured to receive and decode a stream of block-based data packets, said VLD being operative to output quantized data from said decoded data packets;
- a complexity estimator configured to extract the header information from said block-based data packets and further configured to execute a video complexity algorithms based on said extracted header information;
- an inverse quantizer coupled to receive the output of said variable length decoder to operatively inverse quantize the quantized data received from said variable length decoder;
- an inverse discrete cosine transformer (IDCT) coupled to the output of said inverse quantizer for transforming the dequantized data from frequency domain to spatial domain;
- a motion compensator (MC) configured to receive motion vector data from said quantized data and to generate a reference signal;
- and,
- an adder for receiving said reference signal and said spatial domain data from said IDCT to form motion compensated pictures.
A method for improving decoding efficiency of an encoded data video signal employing an MPEG digital video decoder having a variable length code (VLC) decoder, an inverse quantizer (IQ), an inverse discrete cosine transformer (IDCT), a motion compensator (MC), and an estimator, said method comprising the steps of:
- receiving a compressed video data stream at said VLC decoder and producing decoded data therefrom;
- retrieving header information from said decoded data;
- calculating a total computation load (Cest) for said IDCT and said MC based on the classification of said header information by said estimator;
- dequantizing said decoded data using said inverse quantizer(IQ) to generate dequantized, decoded data;
- employing said IDCT for transforming said dequantized, decoded data from frequency domain to spatial domain based to said total computation load (Cest) to produce difference data;
- employing said MC for generating a reference data of said encoded digital video signal based on said computation load;
- and,
- combining said reference data and said difference data to produce motion compensated pictures.
A prediction method of improving decoding efficiency of an encoded data video signal employing an MPEG digital video decoding system having a variable length code (VLC) decoder, an inverse quantizer (IQ), an inverse discrete cosine transformer (IDCT), a motion compensator (MC), and an estimator, said method comprising the steps of:
- decoding a compressed bitstream including a plurality of macroblocks to obtain a corresponding decoded macro block;
- obtaining a header classification criteria from the header information of said decoded macroblock;
- employing said estimator for predicting a total computation load (Cest) according to the header information from said decoded macroblock and forwarding said total computation load (Cest) to said IDCT and said MC;
- and,
- adjusting the computation load of said IDCT and said MC according to said total computation load (Cest).
Dependencies are inferred from the claim text.