US 11,057,606 B2
Method and display system for information display based on positions of human gaze and object
Wei-Lin Hsu, Taichung (TW); Tzu-Yi Yu, Kaohsiung (TW); and Heng-Yin Chen, Hsinchu County (TW)
Assigned to Industrial Technology Research Institute, Hsinchu (TW); and Intellectual Property Innovation Corporation, Hsinchu (TW)
Filed by Industrial Technology Research Institute, Hsinchu (TW); and Intellectual Property Innovation Corporation, Hsinchu (TW)
Filed on Mar. 21, 2019, as Appl. No. 16/360,013.
Claims priority of application No. 107129992 (TW), filed on Aug. 28, 2018.
Prior Publication US 2020/0077072 A1, Mar. 5, 2020
Int. Cl. H04N 13/239 (2018.01); H04N 13/246 (2018.01); G06T 7/80 (2017.01); G06N 20/20 (2019.01); G06T 7/73 (2017.01); G06T 15/20 (2011.01); H04N 13/383 (2018.01); H04N 13/279 (2018.01); H04N 13/38 (2018.01); H04N 13/376 (2018.01)
CPC H04N 13/239 (2018.05) [G06N 20/20 (2019.01); G06T 7/75 (2017.01); G06T 7/85 (2017.01); H04N 13/246 (2018.05); H04N 13/383 (2018.05)] 18 Claims
OG exemplary drawing
 
1. A display system, comprising:
a light-transmissive display;
at least one first information extraction device comprising an image sensor, configured to capture a user image of a user to generate position information of the user;
at least one second information extraction device comprising an image sensor, configured to capture an object image of an object to generate position information of the object; and
a processing device, connected to the display, the at least one first information extraction device and the at least one second data information extraction device, configured to:
transform the position information of the user and the position information of the object to a same coordinate system;
generate human eye gaze information and stereo scene calibration information of a scene in which the object is located according to a result of a coordinate transformation comprising the transformed position information of the user and the transformed position information of the object;
compute a gaze point of the user on the display according to the human eye gaze information, and perform image recognition on the object according to the object image to generate an image recognition result;
generate fused information between the user and the target according to the human eye gaze information, the image recognition result, and the stereo scene calibration information, wherein the fused information is a displaying position on the display; and
display related information of the object on the display according to the fused information.