Image processing device, image processing method, and image processing system
The present disclosure provides an image processing device, image processing method, and image processing system that are capable of freely deciding a position of a cutout region when cutting out an image from an original image. The image processing device includes an object detection unit configured to detect an object in a first image, and a cutout region deciding unit configured to decide, as a cutout region, a region positioned in a relative direction based on a position at which the object is detected in the first image, the relative direction varying depending on a detection condition.
1. An image processing device, comprising:
processing circuitry configured to:
detect a detection target object and a position of the detection target object in an image;
identify a first cutout region based on the position of the detection target object in the image;
determine whether a region size of the detection target object in the image is larger than a size of the first cutout region; and
in response to the region size of the detection target object in the image being determined to be larger than the size of the first cutout region, perform:
identifying a type of the detection target object;
determining a second cutout region according to the first cutout region, including, when the type of the detection target object is identified as a human type or an automobile type, determining the second cutout region by moving the first cutout region in a direction associated with the type of the detection target object for including a detection target of the detection target object in the second cutout region; and
generating a cutout image from the image according to the second cutout region.
2. The image processing device according to claim 1 , wherein when the type of the detection target object is the human type, the processing circuitry is configured to determine the second cutout region by moving the first cutout region in an upper direction relative to the position of the detection target object.
3. The image processing device according to claim 1 , wherein when the type of the detection target object is the automobile type, the processing circuitry is configured to determine the second cutout region by moving the first cutout region in a lower direction relative to the position of the detection target object.
4. The image processing device according to claim 1 , wherein the detection target of the detection target object is located at the center of the second cutout region.
5. The image processing device according to claim 1 , wherein
the image is one of a plurality of frame images of a moving image, and
the processing circuitry is further configured to calculate the region size of the detection target object in the image based on the detection target object in the plurality of frame images.
6. The image processing device according to claim 1 , wherein when a part of the second cutout region is out of the image, the processing circuitry is further configured to generate the cutout image including a portion that corresponds to the part that is out of the image.
7. The image processing device according to claim 6 , wherein the portion of the cutout image that corresponds to the part out of the image is filled with a predetermined color or a predetermined pattern.
8. The image processing device according to claim 6 , wherein a predetermined character string is placed in the portion of the cutout image that corresponds to the part out of the image.
9. An image processing method, comprising:
detecting a detection target object and a position of the detection target object in an image;
identifying a first cutout region based on the position of the detection target object in the image;
determining whether a region size of the detection target object in the image is larger than a size of the first cutout region; and
in response to the region size of the detection target object in the image being determined to be larger than the size of the first cutout region, performing:
identifying a type of the detection target object;
determining a second cutout region according to the first cutout region, including, when the type of the detection target object is identified as a human type or an automobile type, determining the second cutout region by moving the first cutout region in a direction associated with the type of the detection target object for including a detection target of the detection target object in the second cutout region; and
generating a cutout image from the image according to the second cutout region.
10. An image processing system, comprising:
processing circuitry configured to:
detect a detection target object and a position of the detection target object in an image;
identify a first cutout region based on the position of the detection target object in the image;
determine whether a region size of the detection target object in the image is larger than a size of the first cutout region; and
in response to the region size of the detection target object in the image being determined to be larger than the size of the first cutout region, perform:
identifying a type of the detection target object;
determining a second cutout region according to the first cutout region, including, when the type of the detection target object is identified as a human type or an automobile type, determining the second cutout region by moving the first cutout region in a direction associated with the type of the detection target object for including a detection target of the detection target object in the second cutout region; and
generating a cutout image from the image according to the second cutout region; and
a memory coupled to the processing circuitry and configured to store the generated cutout image.
11. The image processing device according to claim 1 , wherein the type of the detection target object is the human type and the detection target is a face of a human.
12. The image processing method according to claim 9 , wherein the type of the detection target object is the human type and the detection target is a face of a human.
13. The image processing system according to claim 10 , wherein the type of the detection target object is the human type and the detection target is a face of a human.
14. The image processing device according to claim 1 , wherein the position of the detection target object is located at the center of the first cutout region.
15. The image processing device according to claim 1 , wherein the processing circuitry is further configured to:
in response to the region size of the detection target object in the image being determined to be not larger than the size of the first cutout region,
generate the cutout image from the image according to the first cutout region.