# US 2019/0244018 A1 · Variable resolution recognition > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0244018 A1 - Document ID: US20190244018A1 - Status: Published application - Kind: A1 - Application number: 15/890,258 - Filed: 2018-02-06 - Published: 2019-08-08 - Earliest claimed: 2018-02-06 - Assignees: Disney Enterprises, Inc. - Applicants: Disney Enterprises, Inc. - Inventors: Douglas Fidaleo - Web page: https://patentgrep.com/patent/US20190244018A1 ## CPC - G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition} - G06F 16/90: Details of database functions independent of the retrieved data types - G06T 7/73: using feature-based methods - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - G06V 30/248: {involving plural approaches, e.g. verification by template match; Resolving confusion among similar patterns, e.g. "O" versus "Q" (G06V30/242 takes precedence)} - G06V 40/16: Human faces, e.g. facial parts, sketches or expressions - G06V 40/172: {Classification, e.g. identification} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## 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. ## Claims ### Claim 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 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, wherein the policy controls an amount of recognition data retrieved by the recognition assembly; and after assigning the recognition data policy, recognizing participants at the event using at least the sensor. ### Claim 2 (depends on 1) The system of claim 1, further comprising: a temporary recognition database, wherein the instructions when executed by the one or more processors, further cause the system to: retrieve, based on the assigned recognition data policy, recognition data from data captured by the sensor; and store the retrieved recognition data in the temporary recognition database. ### Claim 3 (depends on 2) The system of claim 2, wherein the instructions when executed by the one or more processors, further cause the system to: delete the stored recognition data at a predetermined time based on the event. ### Claim 4 (depends on 1) The system of claim 1, wherein the analyzed characteristics of participants comprise a number of participants and a similarity of features between participants. ### Claim 5 (depends on 1) The system of claim 1, wherein the assigned recognition data policy is assigned from a set of a plurality of recognition data policies, wherein each of the plurality of recognition data policies controls an amount of recognition data retrieved by the recognition assembly, and wherein the recognition data policy is assigned to minimize an amount of retrieved recognition data while recognizing participants with a threshold accuracy. ### Claim 6 (depends on 5) The system of claim 5, wherein each of the plurality of recognition data policies sets a respective number of facial points of a participant that are acquired from an image captured by the sensor. ### Claim 7 (depends on 5) The system of claim 5, wherein each of the plurality of recognition data policies sets sensor device acquisition settings of the recognition assembly. ### Claim 8 (depends on 5) The system of claim 5, wherein each of the plurality of recognition data policies sets security settings that are applied to retrieved recognition data. ### Claim 9 (depends on 5) The system of claim of claim 5, wherein the instructions when executed by the one or more processors, further cause the system to create the plurality of recognition data policies, wherein creating the plurality of recognition data policies comprises: determining first recognition data retrieval settings for a first level recognition data policy associated with the event; creating the first level recognition data policy based on the determined first recognition data retrieval settings; determining second recognition data retrieval settings for a second level recognition data policy associated with the event, wherein the second recognition data retrieval settings are determined using the first level recognition data policy as a starting point; and creating the second level recognition data policy based on the determined second recognition data retrieval settings. ### Claim 10 (depends on 2) The system of claim 2, wherein the stored recognition data is stored as a plurality of templates, and wherein the instructions when executed by the one or more processors, further cause the system to: retrieve, based on the assigned recognition data policy, second recognition data from an image captured by the sensor; and compare the second recognition data with each of the plurality of templates to recognize a participant. ### Claim 11 A method, comprising: analyzing characteristics of participants of an event to determine an amount of recognition data needed to recognize participants of the event; assigning a recognition data policy to a recognition assembly based on the determined amount of recognition data needed to recognize participants of the event, wherein the policy controls an amount of recognition data retrieved by the recognition assembly; and after assigning the recognition data policy, recognizing participants at the event using at least a sensor of the recognition assembly. ### Claim 12 (depends on 11) The method of claim 11, further comprising: retrieving, based on the assigned recognition data policy, recognition data from an image captured by the sensor; and storing the retrieved recognition data in a temporary recognition database. ### Claim 13 (depends on 12) The method of claim 12, further comprising: deleting the stored recognition data at a predetermined time based on the event. ### Claim 14 (depends on 11) The method of claim 11, wherein the analyzed characteristics of participants comprise a number of participants and a similarity of features between participants. ### Claim 15 (depends on 11) The method of claim 11, wherein the assigned recognition data policy is assigned from a set of a plurality of recognition data policies, wherein each of the plurality of recognition data policies controls an amount of recognition data retrieved by the recognition assembly, and wherein the recognition data policy is assigned to minimize an amount of retrieved recognition data while recognizing participants with a threshold accuracy. ### Claim 16 (depends on 15) The method of claim 15, wherein each of the plurality of recognition data policies sets a respective number of facial points of a participant that are acquired from an image captured by the sensor. ### Claim 17 (depends on 15) The method of claim 15, wherein each of the plurality of recognition data policies sets sensor device acquisition settings of the recognition assembly. ### Claim 18 (depends on 15) The method of claim of claim 15, further comprising: creating the plurality of recognition data policies, wherein creating the plurality of recognition data policies comprises: determining first recognition data retrieval settings for a first level recognition data policy associated with the event; creating the first level recognition data policy based on the determined first recognition data retrieval settings; determining second recognition data retrieval settings for a second level recognition data policy associated with the event, wherein the second recognition data retrieval settings are determined using the first level recognition data policy as a starting point; and creating the second level recognition data policy based on the determined second recognition data retrieval settings. ### Claim 19 (depends on 12) The method of claim 12, wherein the stored recognition data is stored as a plurality of templates, and wherein the method further comprises: retrieving, based on the assigned recognition data policy, second recognition data from an image captured by the sensor; and comparing the second recognition data with each of the plurality of templates to recognize a participant. ### Claim 20 A recognition assembly, comprising: an image sensor device to acquire image sensor data of one or more participants at an event; a recognition data processor to acquire recognition data from the image sensor data based on an assigned recognition data policy, wherein the policy controls an amount of recognition data retrieved by the recognition data processor to minimize an amount of retrieved recognition data while recognizing participants with a threshold accuracy; and a temporary recognition database for storing the acquired recognition data, wherein the temporary recognition database is configured to deleted the stored data after a predetermined amount of time based on the assigned recognition data policy.