Camera focus based on subject priority
In one aspect, a device includes a processor and storage accessible to the processor. The storage includes instructions executable by the processor to determine on which of a first person and a second person to auto-focus using a digital camera, with the determination being based on data that indicates a priority of which person to focus on. Based on the determination, the instructions are executable to control the camera to auto-focus on one of the first and second people and to generate an image using the camera according to the auto-focus.
1 . A device, comprising:
at least one processor; and
storage accessible to the at least one processor and comprising instructions executable by the at least one processor to:
receive input from a camera;
identify, based on the input, a first person and a second person;
execute one or more eye tracking algorithms to determine at which of the first person and the second person a third person is looking, the third person being a user of the camera;
based on a determination that the third person is looking at the first person, control the camera to focus on the first person and present first text indicating a first reason why the first person is being focused on a first non-text graphical icon indicating that the first person is being focused on; and
based on a determination that the third person is looking at the second person, control the camera to focus on the second person and present second text indicating a second reason why the second person is being focused on a second non-text graphical icon indicating that the second person is being focused on;
wherein at least one of the first and second reasons comprise the respective first or second person being shown in a high volume of images accessible to the at least one processor.
2 . The device of claim 1 , comprising the camera.
3 . The device of claim 1 , wherein the instructions are executable to:
based on the determination that the third person is looking at the first person, present first third text concurrently with presentation of the first non-text graphical icon, the first third text indicating that the first person is being focused on; and
based on the determination that the third person is looking at the second person, present second fourth text concurrently with presentation of the second non-text graphical icon, the second fourth text indicating that the second person is being focused on.
4 . The device of claim 1 , wherein the instructions are executable to:
based on the determination that the third person is looking at the first person, present a first non-text graphical icon indicating that the first person is being focused on first text concurrently with presentation of the first non-text graphical icon, the first text indicating a first reason why the first person is being focused on; and
based on the determination that the third person is looking at the second person, present a second non-text graphical icon indicating that the second person is being focused on second text concurrently with presentation of the second non-text graphical icon, the second text indicating a second reason why the second person is being focused on.
5 . The device of claim 1 , wherein the high volume of images is established by a threshold number of images.
6 . The device of claim 1 , wherein the input is first input, and wherein the instructions are executable to:
access an email account associated with the third person and execute natural language understanding on text of the third person's emails to identify a relationship between the third person and a fourth person indicated in the third person's emails;
execute facial recognition on second input from the camera to determine that the fourth person is indicated in the second input; and
based on the identification of the relationship and the determination that the fourth person is indicated in the second input, control the camera to focus on the fourth person.
7 . The device of claim 1 , comprising a display on which the first and second non-text graphical icons are presentable.
8 . A method, comprising:
receiving input from a camera;
identifying, based on the input, a first person and a second person;
executing one or more eye tracking algorithms to determine at which of the first person and the second person a third person is looking, the third person being a user of the camera;
based on determining that the third person is looking at the first person, controlling the camera to auto-focus on the first person for generation of an image and presenting first text indicating a first reason why the first person is being focused on first text indicating that the first person is being focused on; and
based on determining that the third person is looking at the second person, controlling the camera to auto-focus on the second person for generation of the image and presenting second text indicating a second reason why the second person is being focused on second text indicating that the second person is being focused on;
wherein at least one of the first and second reasons comprise the respective first or second person being shown in a high volume of images.
9 . The method of claim 8 , comprising:
based on determining that the third person is looking at the first person, presenting a first non-text graphical icon indicating that the first person is being focused on; and
based on determining that the third person is looking at the second person, presenting a second non-text graphical icon indicating that the second person is being focused on.
10 . The method of claim 8 , comprising:
based on determining that the third person is looking at the first person, presenting third text indicating that the first person is being focused on a first reason why the first person is being focused on; and
based on determining that the third person is looking at the second person, presenting fourth text indicating that the second person is being focused on a second reason why the second person is being focused on.
11 . The method of claim 8 , wherein the high volume of images is established by a threshold number of images.
12 . The method of claim 8 , wherein the input is first input, and wherein the method comprises:
accessing an email account associated with the third person and execute natural language understanding on text of the third person's emails to identify a relationship between the third person and a fourth person indicated in the third person's emails;
executing facial recognition on second input from the camera to determine that the fourth person is indicated in the second input; and
based on the identification of the relationship and the determination that the fourth person is indicated in the second input, controlling the camera to auto-focus on the fourth person.
13 . At least one computer readable storage medium (CRSM) that is not a transitory signal, the at least one CRSM comprising instructions executable by at least one processor to:
determine on which of a first person and a second person to auto-focus using a digital camera, the determination being based on execution of eye tracking to identify at which of the first person and the second person a third person is looking, the third person being a user of the digital camera;
based on the third person being identified as looking at the first person, control the camera to auto-focus on the first person and present first text indicating a first reason why the first person is being focused on; and
based on the third person being identified as looking at the second person, control the camera to auto-focus on the second person and present second text indicating a second reason why the second person is being focused on;
wherein at least one of the first and second reasons comprise the respective first or second person being shown in a high volume of images accessible to the at least one processor.
14 . The at least one CRSM of claim 13 , wherein the instructions are executable to:
based on the third person being identified as looking at the first person, present a first non-text graphical icon indicating that the first person is being focused on; and
based on the third person being identified as looking at the second person, present a second non-text graphical icon indicating that the second person is being focused on.
15 . The at least one CRSM of claim 13 , wherein the instructions are executable to:
based on the third person being identified as looking at the first person, present third text indicating a name of the first person; and
based on the third person being identified as looking at the second person, present fourth text indicating a name of the second person.
16 . The at least one CRSM of claim 13 , wherein the high volume of images is established by a threshold number of images.
17 . The at least one CRSM of claim 13 , wherein the instructions are executable to:
access an email account associated with the third person and execute natural language understanding on text of the third person's emails to identify a relationship between the third person and a fourth person indicated in the third person's emails;
execute facial recognition on input from the camera to determine that the fourth person is indicated in the input; and
based on the identification of the relationship and the determination that the fourth person is indicated in the input, control the camera to auto-focus on the fourth person.