Information processing device and information processing method
Provided is an information processing device including an image capture unit that captures an image of a subject and converts the image into digital data to generate a captured image, a calculation unit that calculates, for each predetermined area of the captured image, a probability that the subject included in the predetermined area is a main subject desired to be captured by a camera operator, a determination unit that determines the predetermined area in which the probability exceeds a predetermined threshold as a valid data area and that determines a main subject area based on the valid data area, and a focusing unit that focuses on the determined main subject area. Accordingly, it is possible to appropriately bring the main subject into focus.
1. An information processing device, comprising:
an image capture unit configured to:
capture an image; and
generate a captured image based on a conversion of the image into digital data;
a calculation unit configured to calculate a probability that a first subject included in a predetermined area of the captured image is a main subject, wherein
the main subject corresponds to a second subject desired to be captured by a camera operator,
the predetermined area is included in a plurality of predetermined areas of a frame of the captured image,
the probability is included in a plurality of probabilities, and
the plurality of probabilities is associated with the plurality of predetermined areas;
a determination unit configured to:
determine the predetermined area as a first valid data area of the frame of the captured image, wherein the predetermined area is determined as the first valid data area in an event the probability exceeds a predetermined threshold;
combine the first valid data area with at least one adjacent valid data area of the frame of the captured image; and
determine a first main subject area of the frame of the captured image based on the combination of the first valid data area and the at least one adjacent valid data area; and
a focusing unit configured to focus on the determined first main subject area.
2. The information processing device according to claim 1 , wherein
the calculation unit is further configured to calculate the probability based on a learning model,
wherein a first input of the learning model is the captured image and an output of the learning model is the probability.
3. The information processing device according to claim 1 , wherein the determination unit is further configured to:
detect a rectangular area based on the combination of the first valid data area and the at least one adjacent valid data area; and
determine the rectangular area as the first main subject area.
4. The information processing device according to claim 3 , wherein
at least one of a width of the rectangular area, a height of the rectangular area, and an area of the rectangular area satisfies a predetermined condition.
5. The information processing device according to claim 1 , wherein
the determination unit is further configured to determine a plurality of the main subject areas,
the first main subject area is included in the plurality of the main subject areas, and
the first main subject area corresponds to at least one of a largest main subject area among the plurality of the main subject areas, and a closest main subject area closest to the information processing device among the plurality of the main subject areas.
6. The information processing device according to claim 1 , wherein
the probability exceeds the predetermined threshold for a certain period of time.
7. The information processing device according to claim 1 , further including a tracking unit configured to track the first subject included in the determined first main subject area.
8. The information processing device according to claim 7 , wherein
the determination unit is further configured to determine a second main subject area based on one of the first subject being tracked is out of the frame or the probability of the first main subject area being equal to or smaller than the predetermined threshold for a certain period of time, and
the second main subject area is determined based on a second valid data area.
9. The information processing device according to claim 8 , wherein the focusing unit is further configured to focus on a predetermined center area of the frame of the captured image, in an event the second main subject area is not determined.
10. The information processing device according to claim 5 , further comprising:
a sensor unit configured to measure a distance between the information processing device and the first subject,
wherein the closest main subject area is determined based on the measured distance.
11. The information processing device according to claim 5 , wherein
the image capture unit is further configured to generate a phase-contrast image for the first subject, and
the closest main subject area is determined based on depth information of the phase-contrast image.
12. The information processing device according to claim 2 , wherein a second input of the learning model corresponds to a distance between the first subject and the information processing device.
13. A method, comprising:
capturing an image;
generating a captured image based on a conversion of the image into digital data;
calculating a probability that a first subject included in a predetermined area of the captured image is a main subject, wherein
the main subject corresponds to a second subject desired to be captured by a camera operator,
the predetermined area is included in a plurality of predetermined areas of a frame of the captured image,
the probability is included in a plurality of probabilities, and
the plurality of probabilities is associated with the plurality of predetermined areas;
determining the predetermined area as a first valid data area of the frame of the captured image, wherein the predetermined area is determined as the first valid data area in an event the probability exceeds a predetermined threshold;
combining the first valid data area with at least one adjacent valid data area of the frame of the captured image;
determining a first main subject area of the frame of the captured image based on the combination of the first valid data area and the at least one adjacent valid data area; and
focusing on the determined first main subject area.
14. A non-transitory computer-readable medium having stored thereon, computer-executable instructions which, when executed by a computer, cause the computer to execute operations, the operations comprising:
capturing an image;
generating a captured image based on a conversion of the image into digital data;
calculating a probability that a first subject included in a predetermined area of the captured image is a main subject, wherein
the main subject corresponds to a second subject desired to be captured by a camera operator,
the predetermined area is included in a plurality of predetermined areas of a frame of the captured image,
the probability is included in a plurality of probabilities, and
the plurality of probabilities is associated with the plurality of predetermined areas;
determining the predetermined area as a first valid data area of the frame of the captured image, wherein the predetermined area is determined as the first valid data area in an event the probability exceeds a predetermined threshold;
combining the first valid data area with at least one adjacent valid data area of the frame of the captured image;
determining a first main subject area of the frame of the captured image based on the combination of the first valid data area and the at least one adjacent valid data area; and
focusing on the determined first main subject area.