IP Library › Granted Patent US 12671898
Granted Patent B2
US 12671898 · App. 18/714,449 · Granted Jun 30, 2026

Information processing device, information processing method, and program

Inventor: Shinsuke Toda (Saitama, JP)
Assignee: Sony Group Corporation
H04N23/671G06T5/70G06T7/20G06T7/521H04N23/61H04N23/667G06T2207/20081
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12671898
App. No.
18/714,449
Granted
Jun 30, 2026
Kind
B2
Abstract

Information processing devices, methods, and programs that enable an appropriate subject to be a predetermined processing target are disclosed. In one example, an information processing device includes a processing target determination unit that determines a processing target in predetermined processing on an input image, using processing target determination Depth information selected from first Depth information indicating a distance to a subject included in the input image, the first Depth information being based on an output of a distance sensor, and second Depth information based on an output when the input image is input to an inference model that infers the distance to the subject.

Claims (50)

1 . An information processing device comprising:

a memory storing a program,

at least one processor configured to execute the program to perform operations comprising:

determining a processing target in predetermined processing on an input image, using processing target determination depth information selected from first depth information indicating a distance to a subject included in the input image, the first depth information being based on an output of a distance sensor, and second depth information based on an output when the input image is input to an inference model that infers the distance to the subject; and

determining the processing target on a basis of main subject degree information indicating a main subject degree that is a degree of main subject similarity of a subject included in the input image and the processing target determination depth information.

2 . The information processing device according to claim 1 , wherein the operations further comprise:

selecting the processing target determination depth information on a basis of reliability of the second depth information.

3 . The information processing device according to claim 2 , wherein the operations further comprise:

selecting the processing target determination depth information on a basis of a comparison result between the reliability of the second depth information and a threshold.

4 . The information processing device according to claim 2 , wherein the reliability of the second depth information is a value based on an output when the input image is input to an inference model that infers reliability of the second depth information.

5 . The information processing device according to claim 1 , wherein the operations further comprise:

selecting the processing target determination depth information on a basis of brightness of a subject included in the input image.

6 . The information processing device according to claim 5 , wherein the operations further comprise:

selecting the second depth information as the processing target determination depth information in a case where a value indicating the brightness of the subject is equal to or greater than a threshold.

7 . The information processing device according to claim 1 , wherein the operations further comprise:

selecting the processing target determination depth information on a basis of reliability of the first depth information.

8 . The information processing device according to claim 1 , wherein the operations further comprise:

selecting the processing target determination depth information on a basis of an imaging mode when the input image is captured.

9 . The information processing device according to claim 8 , wherein the operations further comprise:

selecting the first depth information as the processing target determination depth information in a case where the imaging mode is any of a dark place mode, a night scene mode, and a night mode.

10 . The information processing device according to claim 1 , wherein the operations further comprise:

determining the processing target on a basis of composition information generated by composition processing of the main subject degree information and the processing target determination depth information.

11 . The information processing device according to claim 1 , wherein the operations further comprise:

in a case where the main subject degree information is a main subject degree map in which the main subject degree is a pixel value of each pixel, and the processing target determination depth information is a processing target determination depth map in which a value indicating a distance to a subject of the input image is a pixel value of each pixel,

determining the processing target on a basis of a composite map generated by composition processing of the main subject degree map and the processing target determination depth map.

12 . The information processing device according to claim 11 , wherein the operations further comprise:

determining a subject corresponding to a region having a predetermined value in the composite map as the processing target.

13 . An information processing device comprising:

a memory storing a program,

at least one processor configured to execute the program to perform operations comprising:

determining a processing target in predetermined processing on an input image, using processing target determination depth information selected from first depth information indicating a distance to a subject included in the input image, the first depth information being based on an output of a distance sensor, and second depth information based on an output when the input image is input to an inference model that infers the distance to the subject, wherein

the predetermined processing is autofocus control processing, and the processing target is a focus target that is a subject to be focused by the autofocus control processing.

14 . An information processing device comprising:

a memory storing a program,

at least one processor configured to execute the program to perform operations comprising:

determining a processing target in predetermined processing on an input image, using processing target determination depth information selected from first depth information indicating a distance to a subject included in the input image, the first depth information being based on an output of a distance sensor, and second depth information based on an output when the input image is input to an inference model that infers the distance to the subject, wherein

the predetermined processing is background blurring control processing, and the processing target is an emphasis target that is a subject to be emphasized by the background blurring control processing.

15 . An information processing device comprising:

a memory storing a program,

at least one processor configured to execute the program to perform operations comprising:

determining a processing target in predetermined processing on an input image, using processing target determination depth information selected from first depth information indicating a distance to a subject included in the input image, the first depth information being based on an output of a distance sensor, and second depth information based on an output when the input image is input to an inference model that infers the distance to the subject, wherein

the predetermined processing is a tracking control processing, and the processing target is a tracking target that is a subject to be tracked in the tracking control processing.

16 . The information processing device according to claim 1 , further comprising an imaging unit that captures the input image.

17 . The information processing device according to claim 1 , wherein the first depth information and the second depth information are both depth maps in which a value indicating a distance to a subject at a position corresponding to each pixel of the input image is set as a pixel value of each pixel.

18 . An information processing method comprising:

determining a processing target in predetermined processing on an input image, using processing target determination depth information selected from first depth information indicating a distance to a subject included in the input image, the first depth information being based on an output of a distance sensor, and second depth information based on an output when the input image is input to an inference model that infers the distance to the subject by an information processing device; and

determining the processing target on a basis of main subject degree information indicating a main subject degree that is a degree of main subject similarity of a subject included in the input image and the processing target determination depth information.

19 . A non-transitory computer readable medium storing a program, the program being executable by a processor to perform operations comprising:

determining a processing target in predetermined processing on an input image, using processing target determination depth information selected from first depth information indicating a distance to a subject included in the input image, the first depth information being based on an output of a distance sensor, and second depth information based on an output when the input image is input to an inference model that infers the distance to the subject; and

determining the processing target on a basis of main subject degree information indicating a main subject degree that is a degree of main subject similarity of a subject included in the input image and the processing target determination depth information.