US 11,687,587 B2Granted

Video fingerprinting

AssigneeRoku, Inc.

InventorsWilson Harron, Matthew James Wilkinson

Life of this patent

Estimating the term…

Loading patent…

Abstract

A query fingerprint of a set of frames of video content captured at a client device may be generated. Multiple patches of the set of frames of video content may be selected and a value calculated for each of the selected multiple patches. The value for each patch may be indicated as a single bit along with an additional 1-bit value to indicate whether the patch value is weak. A database of known reference fingerprints may be queried using the generated query fingerprint. Matches between the query fingerprint and the reference fingerprints may be identified. Weak bits may be given reduced weight in identifying the match of fingerprints. Based on the matches, an identifier for the video content may be returned to the client device. The client device may use the received identifier to access the supplemental content.

Claims20

Dependent claims

A method comprising:

capturing a first number of frames of video content at a client device, the first number of frames being sampled from the video content over a time period that includes a total number of frames such that the first number of frames is less than the total number of frames, wherein the client device includes a user interface configured to display the video content;
generating, by the client device, a query fingerprint that includes a component based on each frame of the first number of frames;
transmitting, by the client device, a request that includes the query fingerprint to a server having access to a database of reference fingerprints associated with frames of known video content, including at least one matching reference fingerprint that matches the query fingerprint and is associated with an identifier corresponding to the video content, the at least one matching reference fingerprint including a component based on each frame of a second number of frames sampled from video content over the time period, wherein the second number of frames is greater than the first number of frames;
and
receiving, by the client device, from the server, the identifier corresponding to the video content.

2 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/136,412Filed 22 Apr 2016 · continuation
Priority: 7 Jan 2013
Published: US 2016/0267180 A115 Sep 2016
Granted: 27 Jun 2023
Term ends: Not estimatedThe source records don’t support an estimate.

Classification6 codes

G06F 16/7328
Query formulation: query by example, e.g. a complete video frame or video sequence
G06F 16/434
Query formulation: using image data, e.g. images, photos, pictures taken by a user
G06F 16/7335
Query formulation: graphical querying, e.g. query-by-region, query-by-sketch, query-by-trajectory, GUIs for designating a person/face/object as a…
G06F 16/78
Of video data: retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Family

Application13/735,426Parent of this continuation-in-part · filed 7 Jan 2013
Application14/263,647Parent of this continuation · filed 28 Apr 2014
US 2016/0267180 A1Pre-grant publication · published 15 Sep 2016
US 9,323,840 B2Parent of this continuation
US 9,495,451 B2Parent of this continuation-in-part
Application14/263,647Parent of this continuation-in-part
US 2014/0195548 A1Published application
US 2014/0236988 A1Published application
US 11,687,587 B2This patent

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