Automated video content display control using eye detection
First Claim
Patent Images
1. A method, comprising:
- capturing, with an image sensor, an image of a plurality of users, wherein the capturing is performed according to a timing policy, wherein the timing policy is tuned by a user;
detecting, using a processor, at least one eye of more than one of the plurality of users within the image, wherein the detecting comprises estimating, using an eye tracking system, a focal point of the user, wherein a sensitivity of the detecting is tuned by the user;
performing a predetermined action based upon a current state of the at least one eye of the more than one of the plurality of users, wherein the predetermined action to be performed is selected from a plurality of predetermined actions, wherein the predetermined action to be performed is based upon a length of time that has elapsed between a previous state of the at least one eye and the current state of the at least one eye, wherein the current state is different than the previous state and wherein the predetermined action is selected by the user;
the performing a predetermined action comprising maintaining display of video content based upon the state of the at least one eye being open and marking, based upon the state of the at least one eye being not open, a position of the video content in cache and transferring contents of the cache to non-volatile memory, and performing an additional predetermined action selected from the group consisting of;
pausing the video content, stopping the video content, adjusting a volume of audio associated with the video content, powering off a device displaying the video content, and continuing the video content for a predetermined time; and
resuming the video content from the position upon detecting an active viewer.
2 Assignments
0 Petitions
Accused Products
Abstract
An embodiment provides a method, including: capturing, with an image sensor, an image of a user; detecting, using a processor, at least one open eye of the user within the image; and responsive to said detecting, maintaining display of video content for a predetermined time. Other aspects are described and claimed.
38 Citations
25 Claims
-
1. A method, comprising:
-
capturing, with an image sensor, an image of a plurality of users, wherein the capturing is performed according to a timing policy, wherein the timing policy is tuned by a user; detecting, using a processor, at least one eye of more than one of the plurality of users within the image, wherein the detecting comprises estimating, using an eye tracking system, a focal point of the user, wherein a sensitivity of the detecting is tuned by the user; performing a predetermined action based upon a current state of the at least one eye of the more than one of the plurality of users, wherein the predetermined action to be performed is selected from a plurality of predetermined actions, wherein the predetermined action to be performed is based upon a length of time that has elapsed between a previous state of the at least one eye and the current state of the at least one eye, wherein the current state is different than the previous state and wherein the predetermined action is selected by the user; the performing a predetermined action comprising maintaining display of video content based upon the state of the at least one eye being open and marking, based upon the state of the at least one eye being not open, a position of the video content in cache and transferring contents of the cache to non-volatile memory, and performing an additional predetermined action selected from the group consisting of;
pausing the video content, stopping the video content, adjusting a volume of audio associated with the video content, powering off a device displaying the video content, and continuing the video content for a predetermined time; andresuming the video content from the position upon detecting an active viewer. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 11, 12, 13, 14, 15)
-
-
10. The method of 9, wherein the predetermined action performed comprises marking a position of video content.
-
16. An information handling device, comprising:
-
an image sensor; a processor operatively coupled to the image sensor; and a memory device storing instructions executable by the processor to; capture, with the image sensor, an image of a plurality of users, wherein the capturing is performed according to a timing policy, wherein the timing policy is tuned by a user; detect at least one eye of more than one of the plurality of users within the image, wherein to detect comprises to estimate, using an eye tracking system, a focal point of the user, wherein a sensitivity of the detecting is tuned by the user; perform a predetermined action based upon a current state of the at least one eye of the more than one of the plurality of users, wherein the predetermined action to be performed is selected from a plurality of predetermined actions, wherein the predetermined action to be performed is based upon a length of time that has elapsed between a previous state of the at least one eye and the current state of the at least one eye, wherein the current state is different than the previous state and wherein the predetermined action is selected by the user; to perform a predetermined action comprising maintaining display of video content based upon the state of the at least one eye being open and marking, based upon the state of the at least one eye being not open, a position of the video content in cache and transferring contents of the cache to non-volatile memory, and performing an additional predetermined action selected from the group consisting of;
pausing the video content, stopping the video content, adjusting a volume of audio associated with the video content, powering off a device displaying the video content, and continuing the video content for a predetermined time; andresume the video content from the position upon detecting an active viewer. - View Dependent Claims (17, 18, 19, 20, 21, 22)
-
-
23. An information handling device, comprising:
-
a display device; a processor operatively coupled to the display device; and a memory device storing instructions executable by the processor to; track a user gaze associated with each of a plurality of users, the user gaze indicating that at least one open eye of at least one of the plurality of users is viewing the display device, wherein to track comprises to estimate, using an eye tracking system, a focal point of the user, wherein the tracking is performed according to a timing policy, wherein both the timing policy and a sensitivity of the tracking are tuned by a user; responsive to tracking the user gaze, maintain display of video content; detect that none of the plurality of users are viewing the display device based upon tracking the user gaze of the plurality of users; and perform a predetermined action based upon the plurality of users not viewing the display device, wherein the predetermined action to be performed is selected from a plurality of predetermined actions, wherein the predetermined action to be performed is based upon the length of time that has elapsed between at least one of the plurality of users viewing the display device and no user viewing the display device wherein the predetermined action comprises marking a position of the video content in cache and transferring contents of the cache to non-volatile memory and performing an additional predetermined action and wherein the additional predetermined action is selected by the user and wherein the additional predetermined action is selected from the group consisting of;
pausing the video content, stopping the video content, adjusting a volume of audio associated with the video content, powering off a device displaying the video content, and continuing the video content for a predetermined time; andresume the video content from the position upon detecting an active viewer. - View Dependent Claims (24)
-
-
25. A method, comprising:
-
capturing, with an image sensor, an image of a plurality of users viewing a display device, wherein the capturing is performed according to a timing policy, wherein the timing policy is tuned by a user; thereafter detecting, using a processor, that no user captured within the image is viewing the display device, wherein the detecting occurs at a predetermined frequency selected by the user, wherein the detecting comprises estimating, using an eye tracking system, a focal point of the user, wherein a sensitivity of the detecting is tuned by the user; responsive to said detecting no user is viewing the display device, performing a predetermined action to be performed is selected from a plurality of predetermined actions, wherein the predetermined action to be performed is selected by the user and is based upon a length of time that has elapsed between at least one of the plurality of users viewing the display device and no user viewing the display device, wherein the predetermined action comprises marking a position of the video content in cache and transferring contents of the cache to non-volatile memory, and performing an additional predetermined action selected from the group consisting of;
pausing the video content, stopping the video content, adjusting a volume of audio associated with the video content, powering off a device displaying the video content, and continuing the video content for a predetermined time; andresuming the video content from the position upon detecting an active viewer.
-
Specification