Heterogeneous video processing using private or public cloud computing resources

• US 9,888,051 B1
• Filed: 06/20/2011
• Issued: 02/06/2018
• Est. Priority Date: 03/31/2011
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Rosenzweig, Jesse J., Blackman, Samuel S., Lewis, Brian G.
• Primary Examiner(s): Salad, Abdullahi E
• Application Number:
  US13/164,060
• Time in Patent Office: 2,423 Days
• CPC Class Codes: H04L 65/612 for unicast
• CPC Class Codes: H04L 65/70 Media network packetisation
• CPC Class Codes: H04L 65/752 adapting media to network capabilities
• CPC Class Codes: H04L 65/762 at the source reformatting of additional data in video distribution servers H04N21/2355
• CPC Class Codes: H04L 65/765 intermediate
• CPC Class Codes: H04L 65/80 Responding to QoS

Abstract

A system including one or more cloud computing units and a ground unit. The one or more cloud computing units may be configured to process video content. The ground unit may be configured to pre-process the video content and deliver the video content to the one or more cloud computing units.

Claims

1. A system comprising:

one or more cloud computing units configured to receive video content in an intermediate video file or streaming format, transcode the video content to generate one or more video streams compatible with one or more end user devices, and communicate the transcoded video content in one or more video streams to a network for distribution to the one or more end user devices;

a file based video processing system configured in a first mode, to fully process said video content to generate said one or more video streams containing the video content and compatible with the one or more end user devices using only local resources and, in a second mode, to convert said video content to said intermediate video file or streaming format using encoding settings determined based on network characteristics, the network characteristics including at least available bandwidth, and deliver said intermediate video file or streaming formatted video content to said one or more cloud computing units; and

a management node comprising at least a processor and memory, the management node configured to determine whether utilization of said file based video processing system has exceeded a predefined cost threshold, wherein when said predefined cost threshold is not exceeded said first mode of said file based video processing system is used to generate said one or more video streams locally and when said predefined cost threshold is exceeded said second mode of said file based video processing system is used to generate said one or more video streams using a combination of said local resources and the one or more cloud computing units.

2. The system according to claim 1, wherein said file based video processing system is further configured to compress, encrypt, and deliver said video content to the one or more cloud computing units in said second mode.

3. The system according to claim 2, wherein said file based video processing system is further configured to encrypt said video content with proprietary encryption.

4. The system according to claim 2, wherein said file based video processing system is further configured to prevent the intermediate video file streaming formatted video content from being stored on said one or more cloud computing units by delivering said video content to said one or more cloud computing units in a container-based stream suitable for chunked transfers.

5. The system according to claim 1, wherein said file based video processing system is pooled in a cluster with one or more additional file based video processing systems.

6. The system according to claim 5, wherein said cluster of file based video processing systems is configured to dynamically handle average and peak loads.

7. The system according to claim 1, wherein said file based video processing system is used to fully process said video content while demand is below the predefined cost threshold, said file based video processing system is used to convert said video content for transfer to and final processing by said one or more cloud computing units when said demand is above said predefined cost threshold, and said management node is further configured to balance processing of said video content between said file based video processing system and said one or more cloud computing units based upon a user input.

8. The system according to claim 1, wherein said file based video processing system is configured to provide fast, high-quality video transcoding for multi-screen video applications.

9. The system according to claim 1, wherein said file based video processing system utilizes massively parallel hardware combined with intelligent software to provide fast, high-quality video transcoding for multi-screen video applications.

10. The system according to claim 1, wherein said file based video processing system utilizes graphics processing units (GPUs) to deliver simultaneous, faster-than-real-time conversion of multiple high density (HD) and standard density (SD) video streams across an array of said end user devices.

11. The system according to claim 10, wherein said array of said end user devices comprises one of more of a television, a personal computer, a tablet computer, a personal digital assistants (PDA), a mobile phone, and a smart phone.

12. A method for heterogeneous video processing using private or public cloud computing resources, said method comprising:

generating one or more video streams compatible with one or more end user devices from video content in a file based video processing system using only local resources when utilization of the file based video processing system has not exceeded a predefined cost threshold;

converting said video content to an intermediate video file or streaming format using encoding settings determined based on network characteristics, the network characteristics including at least available bandwidth, and delivering said video content in said intermediate video file or streaming format to one or more cloud computing units when utilization of the file based video processing system exceeds said predefined cost threshold;

generating at least a portion of said one or more video streams by transcoding said video content in said intermediate video file or streaming format to one or more formats compatible with at least a portion of said one or more end user devices using said one or more cloud computing units; and

communicating said portion of said one or more video streams from said one or more cloud computing units to a network for distribution to said at least a portion of the one or more end user devices.

13. The method according to claim 12, wherein converting said video content comprises:

compressing said video content; and

encrypting said video content.

14. The method according to claim 13, wherein encrypting said video content utilizes a proprietary encryption technique.

15. The method according to claim 13, further comprising preventing the intermediate video file or streaming formatted video content from being stored on said one or more cloud computing units by delivering said video content to said one or more cloud computing units in a container-based stream suitable for chunked transfers.

16. The method according to claim 12, wherein said file based video processing system is pooled in a cluster with one or more additional file based video processing systems.

17. The method according to claim 16, further comprising:

dynamically handling average and peak loads using said cluster of file based video processing systems and said one or more cloud computing units based upon a user input.

18. The method according to claim 12, further comprising:

fully processing said video content in said file based video processing system while demand is below said predefined cost threshold; and

converting said video content in said file based video processing system for transfer to and final processing by said one or more cloud computing units when said demand is above said predefined cost threshold.

19. The method according to claim 12, further comprising:

utilizing a plurality of graphics processing units (GPUs) to deliver simultaneous, faster-than-real-time conversion of multiple high density (HD) and standard density (SD) video streams across an array of said end user devices, wherein said array of said end user devices comprises one or more of a television, a personal computer, a tablet computer, a personal digital assistants (PDA), a mobile phone, and a smart phone.

20. A system comprising:

one or more cloud computing resources configured to receive video content in an intermediate video file or streaming format and transcode the video content to generate one or more video streams compatible with one or more end user devices, wherein the transcoded video content in the one or more video streams is distributed to an array of end user devices via a network;

an encoder, wherein, in a first mode, said encoder fully processes said video content to generate said one or more video streams compatible with the one or more end user devices using only local resources and, in a second mode, said encoder converts said video content to said intermediate video file or streaming format, encoding settings for the intermediate video file or streaming format determined based on network characteristics, the network characteristics including at least available bandwidth, and the converted video content is delivered to said one or more cloud computing resources as a compressed and encrypted stream or intermediate video file; and

a management node comprising at least a processor and memory, the management node configured to determine whether utilization of said encoder has exceeded a predefined cost threshold, wherein when said utilization of said encoder does not exceed said predefined cost threshold said encoder generates said one or more video streams using only local resources and when said utilization of said encoder generates said one or more video streams using a combination of said local resources and the one or more cloud computing resources.