Image processing apparatus, imaging apparatus, image processing method, and program for obtaining a composite image utilizing characteristics of a plurality of images
The image processing apparatus includes a processor. The processor is configured to: acquire a second image, which is obtained by performing first AI processing on a first image, and a fourth image, which is obtained without performing the first AI processing on the first image or a third image; and combine the second image and the fourth image according to an indicator of the first image and/or the third image.
1 . An image processing apparatus comprising:
a processor,
wherein the processor is configured to:
acquire a second image, which is obtained by performing first AI processing on a first image, and a fourth image, which is obtained without performing the first AI processing on the first image or a third image; and
combine the second image and the fourth image according to an indicator of the first image and/or the third image,
wherein the first image is an image obtained by imaging a subject that includes haze,
the fourth image is an image obtained by performing non-AI method processing of reducing reflection of the haze from the first image,
the second image is an image in which the reflection of the haze is reduced from the first image by performing the first AI processing on the first image,
the indicator includes information that is capable of specifying a haze region, which is an image region in the first image where the haze is captured, and
in a case where the second image and the fourth image are combined, an image region in the fourth image, which corresponds to the haze region specified based on the indicator, is combined at a higher ratio than an image region in the second image, which corresponds to the haze region specified based on the indicator.
2 . An image processing apparatus comprising:
a processor,
wherein the processor is configured to:
acquire a second image, which is obtained by performing first AI processing on a first image, and a fourth image, which is obtained without performing the first AI processing on the first image or a third image; and
combine the second image and the fourth image according to an indicator of the first image and/or the third image,
wherein the third image is an infrared light image obtained by imaging an imaging target region,
the fourth image is a first temperature distribution image that shows a distribution of temperature within the imaging target region and that is based on the infrared light image,
the second image is a second temperature distribution image that shows a distribution of temperature within the imaging target region and that is obtained by performing the first AI processing on the first image,
the indicator includes information that is capable of distinguishing between a first region, which is an image region showing a thermal radiator that is not captured in the first temperature distribution image, and a second region, which is an image region other than the first region, in the second temperature distribution image, and
in a case where the second image and the fourth image are combined, and based on the indicator,
an image region in the first temperature distribution image, which corresponds to the second region, is combined at a higher ratio than the second region, and
the first region is combined at a higher ratio than an image region in the first temperature distribution image, which corresponds to the first region.
3 . An image processing apparatus comprising:
a processor,
wherein the processor is configured to:
acquire a second image, which is obtained by performing first AI processing on a first image, and a fourth image, which is obtained without performing the first AI processing on the first image or a third image; and
combine the second image and the fourth image according to an indicator of the first image and/or the third image,
wherein the third image is a multispectral image obtained by imaging a subject,
the fourth image is an image based on the multispectral image,
the second image is an image obtained by performing the first AI processing on the multispectral image,
the indicator includes information that is capable of distinguishing between a specific subject region, which is an image region that shows a specific subject, and a non-specific subject region, which is an image region other than the specific subject region, in the second image, and
in a case where the second image and the fourth image are combined, and based on the indicator,
an image region in the fourth image, which corresponds to the non-specific subject region, is combined at a higher ratio than the non-specific subject region, and
the specific subject region is combined at a higher ratio than an image region in the fourth image, which corresponds to the specific subject region.
4 . An image processing method comprising:
acquiring a second image, which is obtained by performing first AI processing on a first image, and a fourth image, which is obtained without performing the first AI processing on the first image or a third image; and
combining the second image and the fourth image according to an indicator of the first image and/or the third image,
wherein the first image is an image obtained by imaging a subject that includes haze,
the fourth image is an image obtained by performing non-AI method processing of reducing reflection of the haze from the first image,
the second image is an image in which the reflection of the haze is reduced from the first image by performing the first AI processing on the first image,
the indicator includes information that is capable of specifying a haze region, which is an image region in the first image where the haze is captured, and
in a case where the second image and the fourth image are combined, an image region in the fourth image, which corresponds to the haze region specified based on the indicator, is combined at a higher ratio than an image region in the second image, which corresponds to the haze region specified based on the indicator.
5 . An image processing method comprising:
acquiring a second image, which is obtained by performing first AI processing on a first image, and a fourth image, which is obtained without performing the first AI processing on the first image or a third image; and
combining the second image and the fourth image according to an indicator of the first image and/or the third image,
wherein the third image is an infrared light image obtained by imaging an imaging target region,
the fourth image is a first temperature distribution image that shows a distribution of temperature within the imaging target region and that is based on the infrared light image,
the second image is a second temperature distribution image that shows a distribution of temperature within the imaging target region and that is obtained by performing the first AI processing on the first image,
the indicator includes information that is capable of distinguishing between a first region, which is an image region showing a thermal radiator that is not captured in the first temperature distribution image, and a second region, which is an image region other than the first region, in the second temperature distribution image, and
in a case where the second image and the fourth image are combined, and based on the indicator,
an image region in the first temperature distribution image, which corresponds to the second region, is combined at a higher ratio than the second region, and
the first region is combined at a higher ratio than an image region in the first temperature distribution image, which corresponds to the first region.
6 . An image processing method comprising:
acquiring a second image, which is obtained by performing first AI processing on a first image, and a fourth image, which is obtained without performing the first AI processing on the first image or a third image; and
combining the second image and the fourth image according to an indicator of the first image and/or the third image,
wherein the third image is a multispectral image obtained by imaging a subject,
the fourth image is an image based on the multispectral image,
the second image is an image obtained by performing the first AI processing on the multispectral image,
the indicator includes information that is capable of distinguishing between a specific subject region, which is an image region that shows a specific subject, and a non-specific subject region, which is an image region other than the specific subject region, in the second image, and
in a case where the second image and the fourth image are combined, and based on the indicator,
an image region in the fourth image, which corresponds to the non-specific subject region, is combined at a higher ratio than the non-specific subject region, and
the specific subject region is combined at a higher ratio than an image region in the fourth image, which corresponds to the specific subject region.
7 . A non-transitory computer-readable storage medium storing a program executable by a computer to perform a process comprising:
acquiring a second image, which is obtained by performing first AI processing on a first image, and a fourth image, which is obtained without performing the first AI processing on the first image or a third image; and
combining the second image and the fourth image according to an indicator of the first image and/or the third image,
wherein the first image is an image obtained by imaging a subject that includes haze,
the fourth image is an image obtained by performing non-AI method processing of reducing reflection of the haze from the first image,
the second image is an image in which the reflection of the haze is reduced from the first image by performing the first AI processing on the first image,
the indicator includes information that is capable of specifying a haze region, which is an image region in the first image where the haze is captured, and
in a case where the second image and the fourth image are combined, an image region in the fourth image, which corresponds to the haze region specified based on the indicator, is combined at a higher ratio than an image region in the second image, which corresponds to the haze region specified based on the indicator.
8 . A non-transitory computer-readable storage medium storing a program executable by a computer to perform a process comprising:
acquiring a second image, which is obtained by performing first AI processing on a first image, and a fourth image, which is obtained without performing the first AI processing on the first image or a third image; and
combining the second image and the fourth image according to an indicator of the first image and/or the third image,
wherein the third image is an infrared light image obtained by imaging an imaging target region,
the fourth image is a first temperature distribution image that shows a distribution of temperature within the imaging target region and that is based on the infrared light image,
the second image is a second temperature distribution image that shows a distribution of temperature within the imaging target region and that is obtained by performing the first AI processing on the first image,
the indicator includes information that is capable of distinguishing between a first region, which is an image region showing a thermal radiator that is not captured in the first temperature distribution image, and a second region, which is an image region other than the first region, in the second temperature distribution image, and
in a case where the second image and the fourth image are combined, and based on the indicator,
an image region in the first temperature distribution image, which corresponds to the second region, is combined at a higher ratio than the second region, and
the first region is combined at a higher ratio than an image region in the first temperature distribution image, which corresponds to the first region.
9 . A non-transitory computer-readable storage medium storing a program executable by a computer to perform a process comprising:
acquiring a second image, which is obtained by performing first AI processing on a first image, and a fourth image, which is obtained without performing the first AI processing on the first image or a third image; and
combining the second image and the fourth image according to an indicator of the first image and/or the third image,
wherein the third image is a multispectral image obtained by imaging a subject,
the fourth image is an image based on the multispectral image,
the second image is an image obtained by performing the first AI processing on the multispectral image,
the indicator includes information that is capable of distinguishing between a specific subject region, which is an image region that shows a specific subject, and a non-specific subject region, which is an image region other than the specific subject region, in the second image, and
in a case where the second image and the fourth image are combined, and based on the indicator,
an image region in the fourth image, which corresponds to the non-specific subject region, is combined at a higher ratio than the non-specific subject region, and
the specific subject region is combined at a higher ratio than an image region in the fourth image, which corresponds to the specific subject region.