# US 12,002,290 B2 · Systems and methods for hybrid edge/cloud processing of eye-tracking image data > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,002,290 B2 - Document ID: US12002290B2 - Status: Granted - Kind: B2 - Application number: 17/680,998 - Filed: 2022-02-25 - Published: 2023-08-31 - Granted: 2024-06-04 - Earliest claimed: 2022-02-25 - Assignees: EyeTech Digital Systems, Inc. - Applicants: EyeTech Digital Systems, Inc. - Inventors: Caleb Robert Hinton; Miles Kirkland Manning; Robert Jacob Nelson - Web page: https://patentgrep.com/patent/US12002290B2 ## CPC - G06V 40/19: Sensors therefor - H04N 23/56: provided with illuminating means - H04N 23/64: {Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract Systems and methods provide for intelligently switching between cloud processing mode and edge processing mode based on a variety of criteria, such as the desired eye-tracker settings (e.g., minimum tracker rate, ideal tracker rate, and processing mode) and the available network capabilities (e.g., latency, bandwidth, and the like). The criteria used for determining whether buffered cloud processing is viable include such parameters as upload bandwidth, tolerable processing delay, buffer drain rate, buffer fill rate, and maximum session duration. The cloud processing system may be used instead of available edge processing in cases where there are benefits to doing so, e.g., the cloud processing system provides added functionality, such as improved data analytics. ## Claims ### Claim 1 An eye-movement data acquisition system comprising: an illumination source configured to produce infrared light; a camera assembly configured to receive a portion of the infrared light reflected from a user's face during activation of the infrared illumination source and produce a plurality of image data frames; an edge processing system communicatively coupled to the camera assembly and the illumination sources, the edge processing system configured to produce eye-movement data based on the plurality of image data frames; a cloud processing system communicatively coupled to the camera assembly and the illumination sources, the cloud processing system configured to produce the eye-movement data based on the plurality of the image data frames; and a decision module configured to select between the edge processing system and the cloud processing system based on a set of desired tracker settings and a set of capabilities of the cloud processing system, wherein the set of capabilities includes at least a minimum tracker rate and a processing mode, the processing mode selected from the group consisting of real-time processing and buffered processing. ### Claim 2 (depends on 1) The system of claim 1, wherein the set of capabilities includes ideal tracker rate. ### Claim 3 (depends on 1) The system of claim 1, wherein the set of desired tracker settings includes network latency. ### Claim 4 (depends on 3) The system of claim 3, wherein the set of desired tracker settings includes network bandwidth. ### Claim 5 (depends on 1) The system of claim 1, wherein the decision module is configured to select the cloud processing system over the edge processing system if predetermined criteria are met, the predetermined criteria including at least improved analytics capabilities of the cloud processing system. ### Claim 6 (depends on 1) The system of claim 1, wherein the decision module enters a “gracefully failing” mode if neither the cloud processing system nor the edge processing system provides the desired tracker settings. ### Claim 7 A method for acquiring eye-movement data, the method comprising: Producing infrared light with an illumination source; receiving, with a camera assembly, a portion of the infrared light reflected from a user's face during activation of the infrared illumination source and produce a plurality of image data frames; providing an edge processing system communicatively coupled to the camera assembly and the illumination sources, the edge processing system configured to produce eye-movement data based on the plurality of image data frames; providing a cloud processing system communicatively coupled to the camera assembly and the illumination sources, the cloud processing system configured to produce eye-movement data based on the plurality of image data frames; selecting between the edge processing system and the cloud processing system based on a set of desired tracker settings and a set of capabilities of the cloud processing system, wherein the set of capabilities includes at least a minimum tracker rate and a processing mode, the processing mode selected from the group consisting of real-time processing and buffered processing; and transmitting the image data frames to the selected processing system and producing the eye-movement data therewith. ### Claim 8 (depends on 7) The method of claim 7, wherein the set of capabilities includes ideal tracker rate. ### Claim 9 (depends on 7) The method of claim 7, wherein the set of desired tracker settings includes network latency. ### Claim 10 (depends on 9) The method of claim 9, wherein the set of desired tracker settings includes network bandwidth. ### Claim 11 (depends on 7) The method of claim 7, wherein the decision module is configured to select the cloud processing system over the edge processing system if predetermined criteria are met, the predetermined criteria including at least improved analytics capabilities of the cloud processing system. ### Claim 12 (depends on 7) The method of claim 7, wherein the decision module enters a “gracefully failing” mode if neither the cloud processing system nor the edge processing system provides the desired tracker settings. ### Claim 13 A decision module for use in connection with an eye-movement data acquisition system of the type comprising an illumination source configured to produce infrared light, a camera assembly configured to receive a portion of the infrared light reflected from a user's face during activation of the infrared illumination source and produce a plurality of image data frames, the decision module comprising: a processor configured to communicate with an edge processing system and a cloud processing system, wherein the edge processing system and the cloud processing system are each configured to produce eye-movement data based on the plurality of image data frames; the processor further configured to select between the edge processing system and the cloud processing system for processing of the image data frames based on a set of desired tracker settings and a set of capabilities of the cloud processing system, wherein the set of capabilities includes at least a minimum tracker rate and a processing mode, the processing mode selected from the group consisting of real-time processing and buffered processing. ### Claim 14 (depends on 13) The decision module of claim 13, wherein the set of desired tracker settings includes network latency and network bandwidth. ### Claim 15 (depends on 1) The system of claim 1, wherein the decision module is configured to select the cloud processing system over the edge processing system if predetermined criteria are met, the predetermined criteria including at least improved analytics capabilities of the cloud processing system.