US 10,381,045 B2Granted

Annotating media content for automatic content understanding

AssigneeLiveClips LLC

InventorsEric David Petajan, David Eugene Weite, Douglas W. Vunic

Life of this patent

Estimating the term…

Loading patent…

Abstract

A system for annotating frames in a media stream 114 includes a pattern recognition system (PRS) 108 to generate PRS output metadata for a frame; an archive 106 for storing ground truth metadata (GTM); a device to merge the GTM and PRS output metadata and thereby generate proposed annotation data (PAD) 110; and a user interface 109 for use by the human annotator HA 118. The user interface 104 includes an editor 111 and an input device 107 used by the HA 118 to approve GTM for the frame. An optimization system 105 receives the approved GTM and metadata output by the PRS 108, and adjusts input parameters for the PRS to minimize a distance metric corresponding to a difference between the GTM and PRS output metadata.

Claims20

Dependent claims

A non-transitory machine-readable storage medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, comprising:

performing pattern recognition on video frames of a media stream to generate pattern recognition metadata associated with the video frames of the media stream;
comparing the pattern recognition metadata associated with the video frames of the media stream and ground-truth metadata associated with the video frames of the media stream to generate a single distance metric, wherein the ground-truth metadata and the pattern recognition metadata comprise a first type of metadata;
adjusting a set of input parameters associated with the pattern recognition according to the single distance metric, wherein the single distance metric is weighted according to the first type;
and
merging the pattern recognition metadata associated with the video frames of the media stream with ground-truth metadata associated with the video frames of the media stream to generate proposed annotation data associated with the video frames of the media stream.

2 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/044,084Filed 24 Jul 2018 · continuation
Priority: 24 Apr 2012
Published: US 2018/0336928 A122 Nov 2018
Granted: 13 Aug 2019
Term ends: Not estimatedThe source records don’t support an estimate.

Classification12 codes

G11B 27/036
Electronic editing of digitised analogue information signals, e.g. audio or video signals: insert-editing
G06F 16/48
Of multimedia data, e.g. slideshows comprising image and additional audio data: retrieval characterised by using metadata, e.g. metadata not…
G06F 40/169
Editing, e.g. inserting or deleting: annotation, e.g. comment data or footnotes
G11B 27/19
Indexing; Addressing; Timing or synchronising; Measuring tape travel: by using information detectable on the record carrier

Family

Application61/637,344Us provisional application · filed 24 Apr 2012
Application13/836,605Parent of this continuation-in-part · filed 15 Mar 2013
PCT/US2013/037545Parent of this continuation · filed 22 Apr 2013
Application15/491,031Parent of this continuation · filed 19 Apr 2017
US 9,659,597 B2Parent of this continuation · filed 23 May 2017
US 2018/0336928 A1Pre-grant publication · published 22 Nov 2018
US 10,056,112 B2Parent of this continuation
Application14/385,989Parent of this continuation
Application14/385,989Parent of this continuation-in-part
US 2013/0283143 A1Published application
US 2015/0071618 A1Published application
US 2017/0221523 A1Published application
US 10,381,045 B2This patent

From the US filing history. Foreign family members aren’t listed.