WE CLAIM:
1. A water level measurement device comprising:
a pixel selection unit for selecting a pixel of interest from an image area designated from a captured image captured by a monitoring camera;
an identification image extraction unit for extracting, as identification images, a plurality of image areas that come in contact with the pixel of interest selected by the pixel selection unit;
an identification unit for calculating an identification strength indicating a degree to which an area corresponding to each of the plurality of identification images is a water area, on a basis of a result of machine learning related to identification between the water area and a non-water area;
a shoreline extraction unit for extracting a shoreline in the captured image on a basis of the identification strength calculated by the identification unit; and
a water level calculation unit for calculating a water level within an image capturing range of the monitoring camera on a basis of the shoreline extracted by the shoreline extraction unit.
2. The water level measurement device according to claim 1, comprising:
a learning image extraction unit for extracting a learning image from the captured image; and
a learning unit for executing the machine learning related to the identification between the water area and the non-water area by using the learning image extracted by the learning image extraction unit.
3. A water level measurement device comprising:

an identification image extraction unit for extracting a plurality of identification images from an image area designated from a captured image captured by a monitoring camera;
an identification unit for calculating an identification strength indicating a degree to which an area corresponding to each of the plurality of identification images is an water's edge, on a basis of a result of machine learning related to identification between a water area, the water's edge and a non-water area;
a shoreline extraction unit for calculating a position of a shoreline in the captured image on a basis of the identification strength calculated by the identification unit; and
a water level calculation unit for calculating a water level within an image capturing range of the monitoring camera on a basis of a position of the shoreline calculated by the shoreline extraction unit.
4. The water level measurement device according to claim 3, comprising:
a learning image extraction unit for extracting a learning image from the captured image; and
a learning unit for executing the machine learning related to the identification between the water area, the water's edge and the non-water area by using the learning image extracted by the learning image extraction unit.
5. A water level measurement device comprising:
an identification image extraction unit for extracting an identification image from a captured image captured by a monitoring camera;
an identification unit for identifying a position of a shoreline in the

identification image, on a basis of a result of machine learning related to identification between a water area, a water's edge and a non-water area; and
a water level calculation unit for calculating a water level within an image capturing range of the monitoring camera on a basis of the position of the shoreline identified by the identification unit.
6. The water level measurement device according to claim 5, comprising:
a learning image extraction unit for extracting a learning image from the captured image; and
a learning unit for executing machine learning related to identification of the water's edge by using the learning image extracted by the learning image extraction unit.
7. The water level measurement device according to claim 6, wherein
the learning unit executes the machine learning related to the identification of the water's edge, by using, as a label of teacher data, a position of a shoreline in the learning image extracted by the learning image extraction unit.
8. The water level measurement device according to any one of claims 1 to 7,
wherein
the monitoring camera is a camera having a function of three-dimensional measurement within the image capturing range, and
the water level calculation unit calculates the water level within the image capturing range of the monitoring camera, on a basis of three-dimensional measured data by the monitoring camera.

9. A shoreline extraction method comprising:
a step of selecting, by a pixel selection unit, a pixel of interest from an image area designated from a captured image captured by a monitoring camera;
a step of extracting, as identification images, a plurality of image areas that come in contact with the pixel of interest selected by the pixel selection unit, the step being executed by an identification image extraction unit;
a step of calculating, by an identification unit, an identification strength indicating a degree to which an area corresponding to each of the plurality of identification images is a water area, on a basis of a result of machine learning related to identification between the water area and a non-water area; and
a step of extracting, by a shoreline extraction unit, a shoreline in the captured image on a basis of the identification strength calculated by the identification unit.