Information processing device and method for detection of a sound image object

1. An information processing device, comprising:

an image object detection unit configured to:

receive a moving image with sound; and

detect an image object based on the received moving image with sound;

a sound object detection unit configured to:

estimate a simultaneous occurrence probability of a plurality of sound objects based on the detection of the image object, wherein the plurality of sound objects is associated with the moving image with sound;

determine a set of sound objects from the plurality of sound objects based on the estimated simultaneous occurrence probability of the plurality of sound objects; and

detect a sound object from the determined set of sound objects based on a basis of the moving image with sound; and

a sound image object detection unit configured to detect a sound image object based on a detection result of the detection of the image object and a detection result of the detection of the sound object.

2. The information processing device according to claim 1 , wherein

the sound object detection unit is further configured to extract a separated sound of the sound object from a sound of the moving image with sound,

the sound image object detection unit is further configured to output image area information of the sound image object and sound image object information of the sound image object, and

the sound image object information includes the separated sound of the sound object.

3. The information processing device according to claim 1 , wherein the sound image object detection unit is further configured to:

associate the image object with the sound object; and

detect the sound image object based on the association of the image object with the sound object.

4. The information processing device according to claim 1 , wherein the sound image object detection unit is further configured to detect the sound image object based on a co-occurrence probability of the image object and the sound object.

5. The information processing device according to claim 1 , wherein the sound image object detection unit is further configured to detect the sound image object based on position information of the image object and position information of the sound object.

6. The information processing device according to claim 1 , wherein the image object detection unit is further configured to detect the image object based on a basis of at least one of a sound constituting the moving image with sound, a detection result of an acoustic event from the sound constituting the moving image with sound, or the detection result of the detection of the sound object, and a moving image constituting the moving image with sound.

7. The information processing device according to claim 1 , wherein the sound object detection unit is further configured to detect the sound object based on at least one of a moving image constituting the moving image with sound, a result of image body recognition for the moving image constituting the moving image with sound, or the detection result of the detection of the image object, and a sound constituting the moving image with sound.

8. The information processing device according to claim 1 , wherein the sound object detection unit is further configured to determine the set of sound objects based on at least one of a sound source position of a sound source, an image body position of the image object, or a type of the sound object.

9. The information processing device according to claim 1 , wherein the sound object detection unit is further configured to:

detect an acoustic event based on the moving image with sound; and

detect the sound object based on the detection of the acoustic event.

10. The information processing device according to claim 1 , wherein the sound object detection unit is further configured to execute a sound source separation process to detect the sound object.

11. The information processing device according to claim 1 , further comprising a sound image object selection unit configured to:

receive information of a plurality of sound image objects including the sound image object; and

select, based on the received information, at least one sound image object from the plurality of the sound image objects.

12. The information processing device according to claim 11 , further comprising a processing unit configured to:

receive a selection result of the selection of the at least one sound image object; and

execute a process based on the selection result.

13. The information processing device according to claim 12 , wherein the processing unit is further configured to execute, as the process, at least one of:

a zoom process on the selected at least one sound image object of the moving image with sound,

a focus process on the selected at least one sound image object of the moving image with sound,

a removal process of the selected at least one sound image object from the moving image with sound,

a notification process with respect to the selected at least one sound image object,

a search process for the selected at least one sound image object, or

a shutter operation control process based on the selected at least one sound image object.

14. An information processing method, comprising:

receiving a moving image with sound;

detecting an image object based the received moving image with sound;

estimating a simultaneous occurrence probability of a plurality of sound objects based on the detection of the image object, wherein the plurality of sound objects is associated with the moving image with sound;

determining a set of sound objects from the plurality of sound objects based on the estimated simultaneous occurrence probability of the plurality of sound objects;

detecting a sound object from the determined set of sound objects based on the moving image with sound; and

detecting a sound image object based on a detection result of the detection of the image object and a detection result of the detection of the sound object.

15. A non-transitory computer-readable medium having stored thereon computer-executable instructions which, when executed by a processor, cause the processor to execute operations, the operations comprising:

receiving a moving image with sound;

detecting an image object based on the received moving image with sound;

estimating a simultaneous occurrence probability of a plurality of sound objects based on the detection of the image object, wherein the plurality of sound objects is associated with the moving image with sound;

determining a set of sound objects from the plurality of sound objects based on the estimated simultaneous occurrence probability of the plurality of sound objects;

detecting a sound object from the determined set of sound objects based on the moving image with sound; and

detecting a sound image object based on detection result of the detection of the image object and a detection result of the detection of the sound object.