US 10,592,750 B1Granted

Video rule engine

AssigneeAmazon Technlogies, Inc.

InventorsDeepak Suresh Yavagal, Matthew Alan Townsend, Robert James Hanson

Life of this patent

Estimating the term…

Loading patent…

Abstract

A system and method is provided for using rules to perform a set of actions on video data when conditions are satisfied by the video data. The system receives rules to select a theme, portions of the video data and/or a type of output. For example, based on annotation data associated with the video data, the system may apply rules to select one or more themes, with each of theme associated with a portion of the video data. In some examples, the system may apply rules to determine the portion of the video data associated with the theme. The system may apply rules to generate various types of output data associated with each of the selected themes, the types of output data may include a video summarization, individual video clips, individual video frames, a photo album including video frames selected from the video data or the like.

Claims20

Dependent claims

A computer-implemented method for selecting a theme for a video summarization, the method comprising:

receiving input video data including a plurality of video clips;
receiving annotation data associated with the plurality of video clips, the annotation data indicating characteristics represented in individual frames in the input video data;
receiving a rule indicating a set of conditions associated with output video data, the set of conditions including a date range condition and a scene type condition;
selecting a portion of the input video data corresponding to first video clips of the plurality of video clips;
determining, using the annotation data, that the first video clips correspond to a capture date on which the first video clips were generated by an image capture device, the capture date satisfying the date range condition;
determining, using the annotation data, that the first video clips correspond to the scene type condition, the annotation data indicating that the first video clips satisfy the scene type condition;
determining to apply the rule to the first video clips due to the first video clips satisfying the date range condition and the scene type condition;
determining a theme associated with the rule, the theme indicating candidate layouts, transitions, or special effects to be used in generating the output video data;
and
generating the output video data using the theme, the output video data including the first video clips.

7 more elements

A computer-implemented method, comprising:

receiving first input video data;
receiving annotation data associated with the first input video data;
receiving a first condition associated with generation of a video summarization of the first input video data;
receiving a second condition associated with generation of the video summarization;
determining that a first portion of the annotation data satisfies the first condition;
determining that a second portion of the annotation data satisfies the second condition;
selecting, based at least in part on determining that the first portion of the annotation data satisfies the first condition, a first portion of the first input video data corresponding to the first portion of the annotation data;
selecting, based at least in part on determining that the second portion of the annotation data satisfies the second condition, a second portion of the first input video data corresponding to the second portion of the annotation data;
determining a theme associated with the first condition and the second condition;
and
generating the video summarization from the first portion of the first input video data and the second portion of the first input video data, the video summarization corresponding to the theme.

8 more elements

A system, comprising:

at least one processor;
and
at least one memory including instructions that, when executed by the at least one processor, cause the system to:
receive first input video data;
receive annotation data associated with the first input video data;
receive a first condition associated with generation of a video summarization of the first input video data;
receive a second condition associated with generation of the video summarization;
determine that a first portion of the annotation data satisfies the first condition;
determine that a second portion of the annotation data satisfies the second condition;
select, based at least in part on determining that the first portion of the annotation data satisfies the first condition, a first portion of the first input video data corresponding to the first portion of the annotation data;
select, based at least in part on determining that the second portion of the annotation data satisfies the second condition, a second portion of the first input video data corresponding to the second portion of the annotation data;
determine a theme associated with the first condition and the second condition;
and
generate the video summarization from the first portion of the first input video data and the second portion of the first input video data, the video summarization corresponding to the theme.

11 more elements

Dependencies are inferred from the claim text.

Facts

Application: 14/976,037Filed 21 Dec 2015
Granted: 17 Mar 2020
Term ends: Not estimatedThe source records don’t support an estimate.

Classification15 codes

G11B 27/031
Editing, e.g. varying the order of information signals recorded on, or reproduced from, record carriers: electronic editing of digitised analogue…
G06F 18/24765
Classification techniques: rule-based classification
G06V 10/765
Using classification, e.g. of video objects: using rules for classification or partitioning the feature space
G06V 20/41
In video content: higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian…