Image processing system and image processing method

1 . An image processing system comprising:

a first image processing apparatus configured to generate data of a first silhouette image illustrating a region in which an object exists in a first input image by inputting data of the first input image to a learned model, the data of the first input image being data of an image obtained through image capturing of the object by a first image capturing device configured to capture an image of a region including at least part of a specific region, wherein the first image processing apparatus is not configured to calculate a difference between an input image and a background image for generating the first silhouette image; and

a second image processing apparatus configured to generate data of a second silhouette image illustrating a region in which the object exists in a second input image by calculating a difference between the second input image and a background image that is an image obtained through image capturing by a second image capturing device different from the first image capturing device in a state in which the object does not exist in a region subjected to image capturing by the second image capturing device, as data of the second input image being data of an image obtained through image capturing of the object by the second image capturing device, wherein the second image processing apparatus is not configured to use a learned model for generating the second silhouette image.

2 . The image processing system according to claim 1 , wherein the second image capturing device captures an image of a region not including the specific region.

3 . The image processing system according to claim 1 , wherein the specific region is a region in which the object potentially exists substantially at rest.

4 . The image processing system according to claim 1 , wherein the specific region is a region in which a difference between color of the object and background color of a region subjected to image capturing by the first image capturing device or the second image capturing device is smaller than a predetermined reference.

5 . The image processing system according to claim 1 , wherein the specific region is a region in which a shadow of the object or a virtual image due to image reflection of the object in part of a region subjected to image capturing by the first image capturing device or the second image capturing device potentially occurs.

6 . The image processing system according to claim 1 , wherein some of one or more image capturing devices each including at least part of the specific region in an angle of view are each set as the first image capturing device.

7 . The image processing system according to claim 1 , wherein image capturing devices an angle between optical axis vectors of which is equal to or larger than a predetermined angle among two or more image capturing devices each including at least part of the specific region in an angle of view are set as the first image capturing devices.

8 . The image processing system according to claim 1 , wherein among one or more image capturing devices each including at least part of the specific region in an angle of view, an image capturing device an angle between an optical axis vector of which and a field surface of an image capturing target of the image capturing device is equal to or larger than or equal to or smaller than a predetermined angle is set as the first image capturing device.

9 . The image processing system according to claim 1 , wherein

the first image processing apparatus comprising:

one or more processors; and

one or more memories storing one or more programs configured to be executed by the one or more processors, the one or more programs including instructions for

obtaining, as the data of the first input image, data of an image obtained through image capturing of the object by the first image capturing device;

generating the data of the first silhouette image by inputting the obtained data of the first input image to the learned model; and

outputting the generated first silhouette image, and

the second image processing apparatus comprising:

one or more processors; and

one or more memories storing one or more programs configured to be executed by the one or more processors, the one or more programs including instructions for

obtaining, as the data of the second input image, data of an image obtained through image capturing of the object by the second image capturing device;

generating the data of the second silhouette image by calculating a difference between the obtained second input image and the background image; and

outputting the generated second silhouette image.

10 . The image processing system according to claim 1 , further comprising a third image processing apparatus configured to generate three-dimensional shape data indicating a shape of the object by using the data of the first silhouette image generated by the first image processing apparatus and the data of the second silhouette image generated by the second image processing apparatus.

11 . The image processing system according to claim 10 , wherein

the third image processing apparatus comprising:

one or more processors; and

one or more memories storing one or more programs configured to be executed by the one or more processors, the one or more programs including instructions for

obtaining the data of the first silhouette image output from the first image processing apparatus and the data of the second silhouette image output from the second image processing apparatus, and

generating the three-dimensional shape data by using the obtained data of the first silhouette image and the obtained data of the second silhouette image.

12 . An image processing method comprising:

a first image processing process executed by a first image processing apparatus, the first image processing process including a first obtaining process of obtaining, as data of a first input image, data of an image obtained through image capturing of an object by a first image capturing device configured to capture an image of a region including at least part of a specific region, a first process of generating data of a first silhouette image illustrating a region in which the object exists in the first input image by inputting the data of the first input image into a learned model, and a first outputting process of outputting the data of the first silhouette image, wherein the first image processing apparatus is not configured to calculate a difference between an input image and a background image for generating the first silhouette image; and

a second image processing process executed by a second image processing apparatus, the second image processing process including a second obtaining process of obtaining, as data of a second input image, data of an image obtained through image capturing of the object by a second image capturing device different from the first image capturing device, a second generating process of generating data of a second silhouette image illustrating a region in which the object exists in a second input image by calculating a difference between the second input image and a background image that is an image obtained through image capturing by a second image capturing device in a state in which the object does not exist in a region subjected to image capturing by the second image capturing device, and a second outputting process of outputting the data of the second silhouette image, wherein the second image processing apparatus is not configured to use a learned model for generating the second silhouette image.