Information processing device, information processing method, and computer program product

1. An information processing device comprising:

a memory; and

processing circuitry configured to:

acquire a captured image;

detect a plurality of targets included in the captured image;

calculate target information representing at least one of a state or an attribute and reliability of the target information for each of the plurality of detected targets on the basis of the captured image; and

estimate a distribution of the target information of the plurality of targets on the basis of a distribution of the target information of targets for which the reliability is higher than a set value, wherein

the processing circuitry is further configured to lower the set value when the number of targets for which the reliability is higher than the set value is equal to or less than a predetermined number.

2. The device according to claim 1 , wherein the processing circuitry is further configured to:

discriminate whether each of the plurality of detected targets is in a predetermined state or has a predetermined attribute, and

estimate the distribution of targets in the predetermined state or having the predetermined attribute on the basis of targets for which reliability is higher than the set value and which are discriminated to be in the predetermined state or have the predetermined attribute.

3. The device according to claim 1 , wherein the processing circuitry is further configured to:

discriminate whether each of the plurality of detected targets is in a predetermined state and has a predetermined attribute, and

calculate a number of targets in the predetermined state and having the predetermined attribute on the basis of targets for which reliability is higher than the set value and which are discriminated to be in the predetermined state and have the predetermined attribute.

4. The device according to claim 2 , wherein the processing circuitry is configured to calculate the number of targets in the predetermined state or having the predetermined attribute on the basis of a ratio of the number of the targets for which the reliability is higher than the set value and which are discriminated to be in the predetermined state or have the predetermined attribute to a number of targets for which the reliability is higher than the set value.

5. The device according to claim 2 , wherein the processing circuitry is further configured to:

classify each of the plurality of detected targets into a first group for which the reliability is higher than the set value and a second group for which reliability is lower than or equal to the set value;

select a predetermined number of targets from among the first group in order from closest to each target belonging to the second group;

determine whether the target belonging to the second group is in the predetermined state or has the predetermined attribute on the basis of discrimination results of the predetermined number of selected targets; and

calculate the number of targets in the predetermined state or having the predetermined attribute on the basis of a discrimination result for each of the targets belonging to the first group and a determination result for each of the targets belonging to the second group.

6. The device according to claim 2 , wherein

each of the plurality of targets is a person,

the predetermined state is a state in which a person is looking at an object installed at a predetermined position, and

the processing circuitry is configured to discriminate whether each of the plurality of detected targets is looking at the object.

7. The device according to claim 6 , wherein

the object is a display device that displays an advertisement, and

the processing circuitry is configured to calculate the number of targets looking at the display device.

8. The device according to claim 6 , wherein the predetermined state is a state in which the target is oriented toward the object.

9. The device according to claim 6 , wherein the predetermined state is a state in which the target is moving at a predetermined speed or less.

10. The device according to claim 1 , wherein the processing circuitry is further configured to:

identify partial image corresponding to a first space in the captured image, and

detect each of the plurality of targets included in the partial image.

11. The device according to claim 8 , wherein the processing circuitry is further configured to:

detect a blocked area where the object cannot be seen on the basis of a detection result of each of the plurality of targets, and

discriminate a state of each of the plurality of targets according to whether the target is included in the blocked area.

12. An information processing method executed by an information processing device, the method comprising:

acquiring a captured image by the information processing device;

detecting a plurality of targets included in the captured image by the information processing device;

calculating, by the information processing device, target information representing at least one of a state or an attribute and reliability of the target information for each of the plurality of detected targets on the basis of the captured image; and

estimating, by the information processing device, a distribution of the target information of the plurality of targets on the basis of a distribution of the target information of targets for which the reliability is higher than a set value, wherein

the set value is lowered when the number of targets for which the reliability is higher than the set value is equal to or less than a predetermined number.

13. The method according to claim 12 , wherein

the detecting includes discriminating whether each of the plurality of detected targets is in a predetermined state or has a predetermined attribute, and

the estimating includes estimating the distribution of targets in the predetermined state or having the predetermined attribute on the basis of targets for which reliability is higher than the set value and which are discriminated to be in the predetermined state or have the predetermined attribute.

14. The method according to claim 12 , wherein

the detecting includes discriminating whether each of the plurality of detected targets is in a predetermined state and has a predetermined attribute, and

the estimating includes calculating a number of targets in the predetermined state and having the predetermined attribute on the basis of targets for which reliability is higher than the set value and which are discriminated to be in the predetermined state and have the predetermined attribute.

15. The method according to claim 13 , wherein

the estimating includes calculating the number of targets in the predetermined state or having the predetermined attribute on the basis of a ratio of the number of the targets for which the reliability is higher than the set value and which are discriminated to be in the predetermined state or have the predetermined attribute to a number of targets for which the reliability is higher than the set value.

16. The method according to claim 13 , wherein

the estimating includes:

classifying, each of the plurality of detected targets into a first group for which the reliability is higher than the set value and a second group for which reliability is lower than or equal to the set value;

selecting, a predetermined number of targets from among the first group in order from closest to each target belonging to the second group;

determining, whether the target belonging to the second group is in the predetermined state or has the predetermined attribute on the basis of discrimination results of the predetermined number of selected targets; and

calculating, the number of targets in the predetermined state or having the predetermined attribute on the basis of a discrimination result for each of the targets belonging to the first group and a determination result for each of the targets belonging to the second group.

17. A computer program product comprising:

a non-transitory computer readable storage medium including programmed instructions, the instructions causing a computer to execute the information processing method according to claim 12 .

18. An information processing device comprising:

a memory; and

processing circuitry configured to:

acquire a captured image;

detect a plurality of targets included in the captured image;

calculate target information of a plurality of types, each of the target information representing at least one of a state or an attribute, and calculate each reliability of the target information of the plurality of types for each of the plurality of detected targets on the basis of the captured image; and

estimate a distribution of the target information of the plurality of types for the plurality of targets on the basis of a distribution of the target information of the plurality of types for the targets for which the reliability is higher than the set value.