System and method for multiple channel video transcoding

• US 7,675,972 B1
• Filed: 07/30/2001
• Issued: 03/09/2010
• Est. Priority Date: 07/30/2001
• Status: Active Grant

• Current Assignee: Pixelworks Incorporated
• Original Assignee: VIXS Systems Incorporated (Pixelworks Incorporated)
• Inventors: Chow, Hugh, Laksono, Indra
• Primary Examiner(s): DIEP, NHON THANH
• Application Number:
  US09/918,380
• Time in Patent Office: 3,144 Days
• Field of Search: 37524001-24029, 348/423.1, 382/232, 382/236
• US Class Current: 375/240.12
• CPC Class Codes: H04N 19/40 using video transcoding, i.e. partial or full decoding of a coded input stream followed by re-encoding of the decoded output stream
• CPC Class Codes: H04N 19/433 characterised by techniques for memory access
• CPC Class Codes: H04N 19/51 Motion estimation or motion compensation
• CPC Class Codes: H04N 19/52 by predictive encoding
• CPC Class Codes: H04N 19/59 involving spatial sub-sampling or interpolation, e.g. alteration of picture size or resolution

Abstract

A system and a method for transcoding multiple media channels is disclosed herein. The system includes a first processor to parse a media data stream having one or more media data channels and a vector processor to decompress, scale, and then compress the parsed media channel. A parsed media data channel, in one embodiment, is accessed using a bit manipulator and packetized into decoder instruction packets and transmitted to the vector processor using a sequencer. The vector processor decompresses the decoder instruction packets, scales a macroblock generated from the packets, and then compresses the scaled macroblock. As a result, the scaled and compressed output has less data associated with the media channel, allowing for faster and/or more efficient storage or transmission. A reduced sized scale buffer is associated with another disclosed embodiment.

Claims

1. A system comprising:

a memory;

a memory controller to access the memory;

a first processor to parse received video data to generate a plurality of packets, each packet having a video data payload and information related to the video data payload, and provide the plurality of packets for storage in the memory, wherein a format of the plurality of packets is independent of a video standard of the video data and wherein the first processor comprises a general purpose processor;

a second processor comprising a video transcoder, the first processor and the second processor integrated at the same package substrate; and

a decoder instruction packet (DIP) sequencer to;

access one or more packets of the plurality of packets from the memory via the memory controller;

configure the second processor based on opcodes of the one or more packets;

provide the one or more packets to the second processor; and

wherein the second processor is to transcode the video payload of each of the one or more packets to generate a channel of compressed video data.

2. The system of claim 1, wherein the second processor further includes:

a data decompression portion;

a scalar; and

a data compression portion.

3. The system of claim 2, wherein the decompression portion includes a portion to perform a frequency domain to time domain transform.

4. The system of claim 3, wherein the frequency domain to time domain transform portion is a portion to perform an inverse discrete cosine transform portion.

5. The system of claim 3, wherein the decompression portion includes a portion to perform a de-quantization of data.

6. The system of claim 3, wherein the decompression portion includes a portion to perform a DeZigZag of data.

7. The system of claim 6, wherein the decompression portion includes a motion compensation portion.

8. The system of claim 3, wherein the decompression portion includes a motion compensation portion.

9. The system of claim 2, wherein the decompression portion includes a motion compensation portion.

10. The system of claim 9, wherein the compression portion includes a motion vector generator.

11. The system of claim 10, wherein the motion vector generator includes a buffered motion predictor.

12. The system of claim 11, wherein the compression portion further includes a portion to perform a time domain to frequency domain transform.

13. The system of claim 12, wherein the time domain to frequency domain transform portion includes a discrete cosine transform portion.

14. The system of claim 12, wherein the motion vector generator includes a buffered motion predictor.

15. The system of claim 2, wherein the compression portion includes a motion vector generator.

16. A system comprising:

a memory;

a memory controller to access the memory;

a decoder instruction packet (DIP) sequencer to;

access from the memory via the memory controller one or more packets having a video data payload and information related to the video data payload from the memory, wherein the video data payloads of the one or more packets represent a first channel of compressed video data having a characteristic represented by a first value; and

configure a first processor based on opcodes of the one or more packets;

the first data processor to transcode the video data payloads of the one or more packets to generate a representation of a second channel of compressed video data having the characteristic represented by a second value; and

a second data processor comprising a general purpose processor, the second data processor to;

receive a data stream including video data at a first data processor;

parse the data stream to identify video data associated with a first channel;

packetize the video data associated with the first channel to generate the one or more packets, wherein a format of the one of more packets is independent of a video standard of the data stream; and

provide the one or more packets for storage in the memory.

17. The system of claim 16, wherein the characteristic is a compression factor.

18. The system of claim 16, wherein the characteristic is a scale factor.

19. The system of claim 16, wherein the first data processor is further to:

decompress the video data payloads to generate a first intermediate data;

scale the first intermediate data to generate a second intermediate data; and

compress the second intermediate data to generate the representation of the second channel.

20. The system of claim 16, wherein the first processor is further to:

decompress the video data payloads to generate a first intermediate data, wherein the first intermediate data is frequency domain data;

convert the first intermediate data to a second intermediate data, wherein the second intermediate data is time domain data having the characteristic represented by the first value;

convert the second intermediate data to a third intermediate data having the characteristic represented by the second value; and

compress the third intermediate data to generate the representation of the second channel.

21. The system of claim 16, wherein the first processor transcodes the video data payloads based at least in part on the information associated with the video data payloads.

22. The system of claim 21, wherein the information associated with a video data payload indicates that the video data payload includes one or more of video time stamp information, picture configuration information, slice information, macroblock information, motion vector information, quantizer matrix information, or specific picture location information.

23. The system of claim 16, wherein the first data processor comprises a video processor.

24. A method comprising:

receiving, using a first processor, a data stream including video data;

parsing, using the first processor, the data stream to identify video data associated with a first channel;

packetizing, using the first processor, the video data associated with the first channel to generate the one or more packets, each packet having a video data payload and information related to the video data payload, wherein the video data payloads of the one or more packets represent a first channel of compressed video data having a characteristic represented by a first value and wherein a format of the one of more packets is independent of a video standard of the data stream;

storing the one or more packets at a memory;

accessing the one or more packets from the memory using a decoder instruction packet (DIP) sequencer;

providing, from the DIP sequencer, the one or more packets to a second processor;

configuring, using the DIP sequencer, the second processor based on opcodes of the one or more packets; and

transcoding, using the second processor, the video data payloads of the one or more packets to generate a representation of a second channel of compressed video data having the characteristic represented by a second value.

25. The method of claim 24, wherein the characteristic is a compression factor.

26. The method of claim 24, wherein the characteristic is a scale factor.

27. The method of claim 26, wherein transcoding the video data payloads comprises:

decompressing the video data payloads to generate a first intermediate data;

scaling the first intermediate data to generate a second intermediate data; and

compressing the second intermediate data to generate the representation of the second channel.

28. The method of claim 24, wherein transcoding the video data payloads comprises:

decompressing the video data payloads to generate a first intermediate data, wherein the first intermediate data is frequency domain data;

converting the first intermediate data to a second intermediate data, wherein the second intermediate data is time domain data having the characteristic represented by the first value;

converting the second intermediate data to a third intermediate data having the characteristic represented by the second value; and

compressing the third intermediate data to generate the representation of the second channel.

29. The method of claim 24, wherein receiving the one or more packets includes:

storing the video data payloads of the one or more packets in a first memory of the second processor; and

storing the information associated with the video data payloads in a second memory of the second processor.

30. The method of claim 29, wherein the first memory and the second memory comprise a same memory.

31. The method of claim 24, wherein the video data payloads are transcoded based at least in part on the information associated with the video data payloads.

32. The method of claim 31, wherein the information associated with a video data payload indicates that the video data payload includes one or more of video time stamp information, picture configuration information, slice information, macroblock information, motion vector information, quantizer matrix information, or specific picture location information.

33. The method of claim 24, wherein receiving the one or more packets and transcoding the video data payloads support a real-time play back of the representation of the second channel.

34. The method of claim 24, further comprising:

providing the representation of the second channel of compressed video data for reception by at least one multimedia device.

35. The method of claim 24, wherein the first data processor includes a general purpose processor and the second data processor includes a video processor.