# US 12,118,747 B2 · Gaze detection apparatus > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,747 B2 - Document ID: US12118747B2 - Status: Granted - Kind: B2 - Application number: 18/064,084 - Filed: 2022-12-09 - Published: 2023-06-15 - Granted: 2024-10-15 - Earliest claimed: 2021-12-13 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kabushiki Kaisha - Inventors: Shu Tanaka - Web page: https://patentgrep.com/patent/US12118747B2 ## CPC - G06T 7/80: Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration - H04N 17/002: {for television cameras} - G06F 3/012: {Head tracking input arrangements} - G06F 3/013: {Eye tracking input arrangements (G06F3/015 takes precedence)} - G06V 10/766: using regression, e.g. by projecting features on hyperplanes - G06V 10/82: using neural networks - G06V 40/161: {Detection; Localisation; Normalisation} - G06V 40/18: Eye characteristics, e.g. of the iris - G06V 40/19: Sensors therefor - G06V 40/193: {Preprocessing; Feature extraction} - H04N 23/611: where the recognised objects include parts of the human body - H04N 23/617: Upgrading or updating of programs or applications for camera control - H04N 23/63: by using electronic viewfinders - H04N 23/672: {based on the phase difference signals} - H04N 23/675: {comprising setting of focusing regions} - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30201: Face - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A gaze detection apparatus includes at least one memory and at least one processor which function as: a gaze detection unit configured to detect, based on an eye image in which an eye of a user is imaged, a gaze position which is a position at which the user looks; an orientation detection unit configured to detect a head orientation which is an orientation of a head of the user, based on the eye image; a calibration unit configured to acquire a first correction value for reducing a detection error of the gaze position by a predetermined calibration operation; and a correction unit configured to correct the first correction value, based on gaze information related to a current gaze position, a head orientation during the predetermined calibration operation, and a current head orientation. ## Claims ### Claim 1 A gaze detection apparatus comprising at least one memory and at least one processor which function as: a gaze detection unit configured to detect, based on an eye image in which an eye of a user is imaged, a gaze position which is a position at which the user looks; an orientation detection unit configured to detect a head orientation which is an orientation of a head of the user, based on the eye image; a calibration unit configured to acquire a first correction value for reducing a detection error of the gaze position by a predetermined calibration operation; and a correction unit configured to correct the first correction value, based on gaze information related to a current gaze position, a head orientation during the predetermined calibration operation, and a current head orientation. ### Claim 2 (depends on 1) The gaze detection apparatus according to claim 1, wherein the at least one memory and the at least one processor further function as: an acquisition unit configured to acquire a second correction value, based on the gaze information related to the current gaze position, the head orientation during the predetermined calibration operation, and the current head orientation, and the correction unit corrects the first correction value by using the second correction value. ### Claim 3 (depends on 2) The gaze detection apparatus according to claim 2, wherein the acquisition unit is a computation unit using a neural network which receives, as inputs, the gaze information related to the current gaze position, first orientation information related to the head orientation during the predetermined calibration operation, and second orientation information related to the current head orientation, and outputs the second correction value. ### Claim 4 (depends on 3) The gaze detection apparatus according to claim 3, wherein the at least one memory and the at least one processor further function as: an update unit configured to update a parameter of the neural network by using a difference between the gaze position and a center position of a target object, which is an object closest to the gaze position, as an error. ### Claim 5 (depends on 4) The gaze detection apparatus according to claim 4, wherein the update unit does not update the parameter of the neural network in a case where a size of the target object is larger than a predetermined size. ### Claim 6 (depends on 1) The gaze detection apparatus according to claim 1, wherein the correction unit does not correct the first correction value in a case where a difference between the head orientation during the predetermined calibration operation and the current head orientation is less than a predetermined value. ### Claim 7 (depends on 1) The gaze detection apparatus according to claim 1, wherein the gaze detection unit detects the gaze position, based on a right eye image in which a right eye of the user is imaged and a left eye image in which a left eye of the user is imaged, and the orientation detection unit detects the head orientation, based on the right eye image and the left eye image. ### Claim 8 (depends on 1) The gaze detection apparatus according to claim 1, wherein the gaze information is information on a center position of a pupil in the eye image, a center-of-gravity position of a plurality of corneal reflection images, and an interval between the plurality of corneal reflection images. ### Claim 9 (depends on 1) The gaze detection apparatus according to claim 1, wherein the gaze information is information on an angle of a gaze direction, which is a direction in which the user looks, with respect to an optical axis of imaging unit for imaging the eye of the user. ### Claim 10 A gaze detection apparatus comprising at least one memory and at least one processor which function as: a gaze detection unit configured to detect, based on an eye image in which an eye of a user is imaged, a gaze position which is a position at which the user looks; and a calibration unit configured to acquire a correction value for reducing a detection error of the gaze position by a predetermined calibration operation, wherein after the predetermined calibration operation is performed in a state in which a head of the user has a first orientation, a gaze position which is detected in a state in which the head of the user has the first orientation and the user looks at a predetermined position and a gaze position which is detected in a state in which the head of the user has a second orientation different from the first orientation and the user looks at the predetermined position substantially match each other. ### Claim 11 A control method of a gaze detection apparatus, comprising: detecting, based on an eye image in which an eye of a user is imaged, a gaze position which is a position at which the user looks; detecting a head orientation which is an orientation of a head of the user, based on the eye image; acquiring a first correction value for reducing a detection error of the gaze position by a predetermined calibration operation; and correcting the first correction value, based on gaze information related to a current gaze position, a head orientation during the predetermined calibration operation, and a current head orientation. ### Claim 12 A non-transitory computer readable medium that stores a program, wherein the program causes a computer to execute a control method of a gaze detection apparatus, the control method comprising: detecting, based on an eye image in which an eye of a user is imaged, a gaze position which is a position at which the user looks; detecting a head orientation which is an orientation of a head of the user, based on the eye image; acquiring a first correction value for reducing a detection error of the gaze position by a predetermined calibration operation; and correcting the first correction value, based on gaze information related to a current gaze position, a head orientation during the predetermined calibration operation, and a current head orientation.