Outer Rim Archives
Archives · 2020 · 10832043

Granted patent

Variable resolution recognition

Number
10832043
Published
2020-11-10
Filed
2018-02-06
Assignee
Disney Enterprises, Inc.
Inventors
Fidaleo; Douglas
CPC
G06V20/52; G06F16/90; G06V40/103; G06T7/73; G06V30/248; G06V40/16; G06V40/172
Verdict
Set aside generic image recognition, no clear creative/physical hook
Source
Google Patents · FreePatentsOnline

Abstract

Systems and methods are described for dynamically adjusting an amount of retrieved recognition data based on the needs of a show, experience, or other event where participants are recognized. The retrieved recognition data may be deleted once it is no longer needed for the event. Recognition data retrieval is limited to just what is needed for the particular task, minimizing the uniqueness of any retrieved recognition data to respect participant privacy while providing an enhanced participant experience through recognition.

Background

BRIEF SUMMARY OF THE DISCLOSURE(1) Techniques described herein are directed to dynamically adjusting the amount, resolution, or accuracy of retrieved recognition data based on the needs of a show, experience, or other event where the participants are recognized.(2) In one embodiment, a system includes: a recognition assembly comprising a sensor; and one or more non-transitory computer-readable mediums having instructions stored thereon that, when executed by one or more processors, cause the system to: analyze characteristics of participants of an event to determine an amount of recognition data needed to recognize participants of the event; assign a recognition data policy to the recognition assembly based on the determined amount of recognition data needed to recognize participants of the event; and after assigning the recognition data policy, recognizing participants at the event using at least the sensor. In this embodiment, the assigned policy may control an amount of recognition data retrieved by the recognition assembly. In implementations, the analyzed characteristics of participants comprise a number of participants and a similarity of features between participants.(3) In some implementations, the system may further include: a temporary recognition database, and the instructions when executed by the one or more processors, may further cause the system to: retrieve, based on the assigned recognition data policy, recognition data from data captured by the sensor; and s

Claims

1. A system, comprising: a recognition assembly comprising a sensor; one or more non-transitory computer-readable mediums having instructions stored thereon that, when executed by one or more processors, causes the system to: analyze characteristics of participants present at an event, the analyzed characteristics comprising a uniqueness of features between the participants present at the event; determine, based on the uniqueness of features between the participants present at the event, an amount of recognition data needed to distinguish between the participants present at the event with a threshold confidence level; assign a recognition data policy to the recognition assembly based on the determined amount of recognition data needed to distinguish between the participants present at the event with the threshold confidence level, wherein the policy controls an amount of recognition data retrieved by the recognition assembly; and after assigning the recognition data policy, recognizing, using at least the sensor, the participants at the event. 11. A method, comprising: analyzing characteristics of participants present at an event, the analyzed characteristics comprising a uniqueness of features between the participants; determine, based on the uniqueness of features between the participants present at the event, an amount of recognition data needed to distinguish between the participants present at the event with a threshold confidence level; assigning a recognition data policy to a recognition assembly based on the determined amount of recognition data needed to distinguish between the participants present at the event with the threshold confidence level, wherein the policy controls an amount of recognition data retrieved by the recognition assembly; and after assigning the recognition data policy, recognizing, using at least a sensor of the recognition assembly, the participants at the event. 20. A recognition assembly, comprising: an image sensor configured to acquire image sensor data of one or more participants present at an event; a recognition data processor configured to limit recognition data from the image sensor data based on an assigned recognition data policy that controls, based on a uniqueness of features between the participants present at the event, an amount of the recognition data limited by the recognition data processor to distinguish between the participants present at the event with a threshold accuracy; and a data storage configured to store the acquired recognition data, wherein the data storage is configured to delete the stored data after a predetermined amount of time based on the assigned recognition data policy.