# US 10,769,803 B2 · Sight vector detecting method and device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,769,803 B2 - Document ID: US10769803B2 - Status: Granted - Kind: B2 - Application number: 16/231,724 - Filed: 2018-12-24 - Published: 2020-05-21 - Granted: 2020-09-08 - Earliest claimed: 2018-11-16 - Assignees: Industrial Technology Research Institute - Applicants: Industrial Technology Research Institute - Inventors: Yu-Ying Lan; Hsin-Cheng Lin; Sen-Yih Chou - Web page: https://patentgrep.com/patent/US10769803B2 ## CPC - G06T 7/50: Depth or shape recovery - G06F 3/013: {Eye tracking input arrangements (G06F3/015 takes precedence)} - G06T 7/75: {involving models} - G06T 2207/30201: Face - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A sight vector detecting method includes: capturing a user image by an image capture unit and a depth capture unit to obtain a first image and a distance information; based on the first image and the distance information, finding an eye center location of the user; predicting a user sight location by a gaze model to find a target sight location of the user on a target; based on the eye center location of the user, finding a first word coordinate of the eye center location of the user; based on the target sight location of the user, finding a second word coordinate of the target sight location of the user; and based on the first word coordinate of the eye center location of the user and the second word coordinate of the target sight location of the user, calculating a sight vector of the user. ## Claims ### Claim 1 A sight vector detection method comprising: capturing an image of a user by an image capture element and a depth capture element to obtain a first image and a distance information, respectively; based on the first image and the distance information, finding an eye center location of the user: based on a gaze model, predicting a user sight location to find a target object sight location of the user on a target object; based on the eye center location of the user, calculating a first world coordinates of the eye center of the user; based on the target object sight location of the user, calculating a second world coordinates of the target object sight location of the user; and based on the first world coordinates of the eye center of the user and the second world coordinates of the target object sight location of the user, calculating a sight vector of the user. ### Claim 2 (depends on 1) The sight vector detection method according to claim 1, wherein the distance information is a depth information of a user head image in the first image captured by the depth capture element. ### Claim 3 (depends on 1) The sight vector detection method according to claim 1, wherein the first image includes two images, one of the two images being obtained by flipping the image of the user captured by the image capture element while the other one of the two images being obtained by flipping the image of the user captured by the depth capture element. ### Claim 4 (depends on 1) The sight vector detection method according to claim 1, further comprising performing a background erase operation on the first image. ### Claim 5 (depends on 1) The sight vector detection method according to claim 1, wherein the target object include any transparent material or any non-transparent material. ### Claim 6 (depends on 1) The sight vector detection method according to claim 1, further comprising: performing a resolution calibration to calculate a pixel resolution. ### Claim 7 (depends on 1) The sight vector detection method according to claim 1, further comprising: based on the eye center location of the user, finding a third world coordinates of a standing location of the user; and based on the third world coordinates of the standing location of the user and a user height, calculating the first world coordinates of the eye center of the user. ### Claim 8 (depends on 1) The sight vector detection method according to claim 1, wherein the gaze model stores a user location information in the first image; a user face information in the first image, the user face information including a face size and a face rotation angle; and a user eye information in the first image. ### Claim 9 A sight vector detection device comprising; an image capture element and a depth capture element for capturing an image of a user to obtain a first image and a distance information, respectively, and a processing circuit, coupled to the image capture element and the depth capture element, the processing circuit being configured for: based on the first image and the distance information, finding an eye center location of the user; based on a gaze model, predicting a user sight location to find a target object sight location of the user on a target object; based on the eye center location of the user, calculating a first world coordinates of the eye center of the user; based on the target object sight location of the user, calculating a second world coordinates of the target object sight location of the user; and based on the first world coordinates of the eye center of the user and the second world coordinates of the target object sight location of the user, calculating a sight vector of the user. ### Claim 10 (depends on 9) The sight vector detection device according to claim 9, wherein the distance information is a depth information of a user head image in the first image captured by the depth capture element. ### Claim 11 (depends on 9) The sight vector detection device according to claim 9, wherein the first image includes two images, one of the two images being obtained by flipping the image of the user captured by the image capture element while the other one of the two images being obtained by flipping the image of the user captured by the depth capture element. ### Claim 12 (depends on 9) The sight vector detection device according to claim 9, wherein the processing circuit performs a background erase operation on the first image. ### Claim 13 (depends on 9) The sight vector detection device according to claim 9, wherein the target object include any transparent material or any non-transparent material. ### Claim 14 (depends on 9) The sight vector detection device according to claim 9, wherein the processing circuit further performs a resolution calibration to calculate a pixel resolution. ### Claim 15 (depends on 9) The sight vector detection device according to claim 9, wherein the processing circuit is further configured for. based on the eye center location of the user, finding a third world coordinates of a standing location of the user; and based on the third world coordinates of the standing location of the user and a user height, calculating the first world coordinates of the eye center of the user. ### Claim 16 (depends on 9) The sight vector detection device according to claim 9, wherein the gaze model stores a user location information in the first image; a user face information in the first image, the user face information including a face size and a face rotation angle; and a user eye information in the first image.