Information processing device, information processing system, and information processing method
An information processing device includes: an image acquisition unit configured to acquire an image captured by an imaging unit mounted on a vehicle; a target detection unit configured to detect a target region including a target in the acquired image; a classification identification unit configured to identify classification including a type of the detected target and a size of the detected target region; and a region determination unit configured to determine a region obtained by adding a margin corresponding to the identified classification to the target region as an image processing region.
1. An information processing device comprising:
at least one memory storing instructions, and
at least one processor configured to execute the instructions to:
acquire an image captured by an imaging unit mounted on a vehicle;
detect a target region including a target in the acquired image;
identify classification including a type of the detected target and a size of the detected target region;
determine a region obtained by adding a margin corresponding to the identified classification to the target region as an image processing region;
identify accuracy with which a remote monitoring device monitoring the vehicle recognizes the target in accordance with the type of the detected target and the size of the detected target region, and
set a margin corresponding to the type of the detected target and the size of the detected target region in accordance with the identified accuracy.
2. The information processing device according to claim 1 , wherein the margin is set so that, even when image processing is performed on an image in which the region obtained by adding the margin corresponding to the identified classification is set, recognition accuracy of the image is equal to or greater than a threshold.
3. The information processing device according to claim 1 , wherein the at least one processor configured to execute the instructions to determine the region obtained by adding the margin to the target region as an image processing region with higher image quality than other regions.
4. The information processing device according to claim 1 , wherein the at least one processor configured to execute the instructions to:
identify classification of training image data in which a type of target included in an image is determined, in accordance with the determined type of target and size of the determined target:
set a region obtained by adding a margin to the target region including a target included in the training image data;
identify accuracy with which the remote monitoring device recognizes the target when image processing is performed on the training image data such that a region to which the margin is added has higher image quality than other regions; and
set a margin in which the recognition accuracy is equal to or greater than a threshold as the margin corresponding to the classification.
5. The information processing device according to claim 4 , wherein
the at least one processor configured to execute the instructions to:
set a region to which a different margin is added to each of the plurality of pieces of training image data:
identify accuracy with which the remote monitoring device recognizes the target when image processing is performed on each of the plurality of pieces of training image data to which the different margin is added; and
set a margin in which the recognition accuracy is equal to or greater than a threshold as the margin corresponding to the classification.
6. The information processing device according to claim 1 , further comprising a storage unit configured to store the margin corresponding to the classification.
7. An information processing system comprising:
at least one memory storing instructions, and
at least one processor configured to execute the instructions to:
acquire an image captured by an imaging unit mounted on a vehicle;
detect a target region including a target in the acquired image;
identify classification including a type of the detected target and a size of the detected target region;
determine a region obtained by adding a margin corresponding to the identified classification to the target region as an image processing region;
identify accuracy with which a remote monitoring device monitoring the vehicle recognizes the target in accordance with the type of the detected target and the size of the detected target region, and
to set the margin corresponding to the type of the detected target and the size of the detected target region in accordance with the identified accuracy.
8. The information processing system according to claim 7 , wherein the margin is set so that, even when image processing is performed on an image in which the region obtained by adding the margin corresponding to the identified classification is set, recognition accuracy of the image is equal to or greater than a threshold.
9. The information processing system according to claim 7 , wherein the at least one processor configured to execute the instructions to determine the region obtained by adding the margin to the target region as an image processing region with higher image quality than other regions.
10. The information processing system according to claim 7 , wherein the at least one processor configured to execute the instructions to:
identify classification of training image data in which a type of target included in an image is determined in accordance with the determined type of target and size of the determined target:
set a region obtained by adding a margin to the target region including a target included in the training image data:
identify accuracy with which the remote monitoring device recognizes the target when image processing is performed on the training image data such that a region to which the margin is added has higher image quality than other regions; and
set a margin in which the recognition accuracy is equal to or greater than a threshold as the margin corresponding to the classification.
11. The information processing system according to claim 10 , wherein the at least one processor configured to execute the instructions to:
set a region to which a different margin is added to each of the plurality of pieces of training image data;
identify accuracy with which the remote monitoring device recognizes the target when image processing is performed on each of the plurality of pieces of training image data to which the different margin is added; and
set a margin in which the recognition accuracy is equal to or greater than a threshold as a margin corresponding to the classification.
12. The information processing system according to claim 7 , further comprising a storage configured to store a margin corresponding to the classification.
13. An information processing method comprising:
acquiring an image captured by an imaging unit mounted on a vehicle;
detecting a target region including a target in the acquired image;
identifying classification including a type of the detected target and a size of the detected target region;
determining a region obtained by adding a margin corresponding to the identified classification to the target region as an image processing region;
identifying accuracy with which a remote monitoring device monitoring the vehicle recognizes the target in accordance with the type of the detected target and the size of the detected target region; and
setting a margin corresponding to the type of the detected target and the size of the detected target region in accordance with the identified accuracy.
14. The information processing method according to claim 13 , wherein the margin is set so that, even when image processing is performed on an image in which the region obtained by adding the margin corresponding to the identified classification is set, recognition accuracy of the image is equal to or greater than a threshold.
15. The information processing method according to claim 13 , further comprising determining the region obtained by adding the margin to the target region as an image processing region with higher image quality than other regions.
16. The information processing method according to claim 13 , further comprising:
identifying classification of training image data in which a type of target included in an image is determined in accordance with the determined type of target and size of the determined target;
setting a region obtained by adding a margin to the target region including a target included in the training image data;
identifying accuracy with which the remote monitoring device recognizes the target when image processing is performed on the training image data such that a region to which the margin is added has higher image quality than other regions; and
setting a margin in which the recognition accuracy is equal to or greater than a threshold as the margin corresponding to the classification.
17. The information processing method according to claim 16 , further comprising:
setting a region to which a different margin is added to each of the plurality of pieces of training image data;
identifying accuracy with which the remote monitoring device recognizes the target when image processing is performed on each of the plurality of pieces of training image data to which the different margin is added; and
setting a margin in which the recognition accuracy is equal to or greater than a threshold as the margin corresponding to the classification.