Content adaptive video encoder

• US 7,715,475 B1
• Filed: 10/21/2004
• Issued: 05/11/2010
• Est. Priority Date: 06/05/2001
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Civanlar, Mehmet Reha, Puri, Atul
• Primary Examiner(s): Philippe; Gims S
• Application Number:
  US10/970,607
• Time in Patent Office: 2,028 Days
• Field of Search: 375/240.01, 375/240.08, 375/240.24, 375/240.1, 707/6, 709/224, 382/190
• US Class Current: 375/240
• CPC Class Codes: H04N 19/103 Selection of coding mode or of prediction mode
• CPC Class Codes: H04N 19/117 Filters, e.g. for pre-processing or post-processing sub-band filter banks H04N19/635
• CPC Class Codes: H04N 19/12 Selection from among a plurality of transforms or standards, e.g. selection between discrete cosine transform [DCT] and sub-band transform or selection between H.263 and H.264
• CPC Class Codes: H04N 19/132 Sampling, masking or truncation of coding units, e.g. adaptive resampling, frame skipping, frame interpolation or high-frequency transform coefficient masking
• CPC Class Codes: H04N 19/137 Motion inside a coding unit, e.g. average field, frame or block difference
• CPC Class Codes: H04N 19/14 Coding unit complexity, e.g. amount of activity or edge presence estimation H04N19/146 takes precedence
• CPC Class Codes: H04N 19/162 User input
• CPC Class Codes: H04N 19/17 the unit being an image region, e.g. an object
• CPC Class Codes: H04N 19/172 the region being a picture, frame or field
• CPC Class Codes: H04N 19/179 the unit being a scene or a shot
• CPC Class Codes: H04N 19/46 Embedding additional information in the video signal during the compression process H04N19/517, H04N19/68, H04N19/70 take precedence
• CPC Class Codes: H04N 19/587 involving temporal sub-sampling or interpolation, e.g. decimation or subsequent interpolation of pictures in a video sequence
• CPC Class Codes: H04N 19/59 involving spatial sub-sampling or interpolation, e.g. alteration of picture size or resolution
• CPC Class Codes: H04N 19/70 characterised by syntax aspects related to video coding, e.g. related to compression standards
• CPC Class Codes: H04N 19/86 involving reduction of coding artifacts, e.g. of blockiness

Abstract

A system for content adaptive encoding and decoding video is disclosed. The system comprises modules for segmenting video content into segments based on predefined classifications or models. Examples of such classifications comprise action scenes, slow scenes, low or high detail scenes, and brightness of the scenes. Based on the segment classifications, each segment is encoded with a different encoder chosen from a plurality of encoders. Each encoder is associated with a model. The chosen encoder is particularly suited to encoding the unique subject matter of the segment. The coded bit-stream for each segment includes information regarding which encoder was used to encode that segment. A matching decoder of a plurality of decoders is chosen using the information in the coded bitstream to decode each segment using a decoder suited for the classification or model of the segment. If scenes exist which do not fall in a predefined classification, or where classification is more difficult based on the scene content, these scenes are segmented, coded and decoded using a generic coder and decoder.

Claims

1. A system for content adaptive encoding of video content, the video content being divided into portions, the system comprising:

means for associating descriptors to each portion based on portion content;

means for mapping each portion of the video content to a model from a plurality of models based on the portion descriptors, the means for mapping further comprising;

a plurality of content model units, each content model unit of the plurality of content model units being associated with a model of the plurality of models;

a plurality of comparators, each comparator of the plurality of comparators connected to a content model unit and an output from an extractor or an output from the means for associating descriptors; and

a plurality of selectors, wherein each selector of the plurality of selectors is connected to two of the comparators; and

a plurality of encoders, each encoder of the plurality of encoders configured to encode portions according to the model associated with the portion.

2. The system of claim 1, further comprising:

a generic encoder included in the plurality of encoders, wherein portions not associated with any model from the plurality of models are encoded using the generic encoder.

3. The system of claim 1, wherein the locator further locates subsegments.

4. The system of claim 3, wherein the locator further locates regions of interest.

5. The system of claim 4, wherein the plurality of content model units further comprises a generic content model unit.

6. The system of claim 5, wherein the means for mapping outputs from the selectors a signal that controls a switch to route portions to one of the plurality of encoders.

7. The system of claim 1, further comprising:

a buffer for storing the portions, the buffer having outputs connected to a switch; and

wherein each encoder of the plurality of encoders is connected to the output of the switch and configured to encode segments according to the model associated with the portion.

8. A video extractor used for content adaptive encoding of video, the video extractor comprising:

a video segment extractor receiving the video;

a plurality of characteristic extractors each receiving the video and outputting a signal associated with an attribute of the video to an analyzer, the analyzer determining a characteristic of the video, wherein the plurality of characteristic video content extractors comprises a shot concept extractor, a scene properties extractor, a camera operation extractor, and a special effects extractor;

a manual segment extraction module receiving the video and an output from the analyzer, wherein the manual segment extraction module provides an output signal associated with the video divided into temporal segments;

a plurality of encoders, each encoder of the plurality of encoders configured to encode temporal segments according to a model associated with the determined characteristic of the respective temporal segment;

a plurality of memory units for storing encoded segments; and

a switch for routing encoded video segments into the plurality of memory units for storing segments.

9. The video extractor of claim 8, further comprising:

a header extractor for extracting header information from video.

10. The video extractor of claim 9, further comprising:

an interpreter receiving output from the analyzer for automatically determining video segments.

11. The video extractor of claim 10, further comprising:

a switch connected to an output from the interpreter and the manual video content extractor module, wherein manual or automatic segment extraction may be output.

12. The video extractor of claim 8, wherein the analyzer performs semantic and statistical analysis on the video.

13. A video segment extractor comprising:

a human operated module for determining video segments from input video;

an automatic video segment determining module for automatically determining video segments having an output connected to the human operated module, the automatic video segment determining module further comprising a shot concept extractor, a scene properties extractor, and a textual transcript keyword extractor;

a plurality of encoders, each encoder of the plurality of encoders configured to encode human determined video segments and automatically determined video segments according to a model associated with a determined characteristic of the respective video segment;

a switch for choosing encoded output from either the human operated module or the automatic video segment determining module.

14. The video segment extractor of claim 13, further comprising:

a segment extractor connected to a second switch which routes video segments to one of a plurality of storage units.

15. The video segment extractor of claim 14, wherein the automatic video segment determining module further comprises a plurality of characteristic extractors each receiving the video and outputting a signal associated with an attribute of the video.

16. The video segment extractor of claim 15, wherein the automatic video segment determining module further comprises an analyzer, the analyzer receiving input from each of the plurality of characteristic extractors, and the analyzer further outputting a signal to the human operated module.

17. The video segment extractor of claim 16, wherein the human operated module

optionally provides the output of the analyzer to a human operator for assigning video segments.