# US 2020/0402385 A1 · Region determining device, monitoring system, region determining method, and recording medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0402385 A1
- Document ID: US20200402385A1
- Status: Published application
- Kind: A1
- Application number: 16/977,529
- Filed: 2019-03-11
- Published: 2020-12-24
- Earliest claimed: 2018-03-14
- Assignees: NEC Corporation
- Applicants: NEC Corporation
- Inventors: Masumi ISHIKAWA; Takahiro TOIZUMI
- Web page: https://patentgrep.com/patent/US20200402385A1

## CPC

- G08B 21/10: responsive to calamitous events, e.g. tornados or earthquakes
- G01C 13/00: Surveying specially adapted to open water, e.g. sea, lake, river or canal (liquid level metering G01F)
- G01F 23/292: Light {, e.g. infrared or ultraviolet}
- G06T 7/11: Region-based segmentation
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30181: Earth observation
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S)
- G01F: MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A region determining device includes a likelihood calculating unit that calculates a likelihood of wetness of a pixel in an image including a plurality of frames, a non-water pixel measuring unit that measures the number of non-water pixels in which the likelihood falls within a first non-water range in any one of determination regions to be determined in the respective frames, a boundary pixel measuring unit that measures the number of boundary pixels in which the likelihood falls within a first water range in any one of the determination regions and the likelihood falls within a second non-water range in any one of the determination regions, and a region determining unit that determines whether the determination region satisfies a predetermined determination condition based on the number of non-water pixels and the number of boundary pixels.

## Claims

### Claim 1

A region determining device comprising:
at least one processor configured to:
calculate a likelihood of wetness of a pixel in an image including a plurality of frames;
measure the number of non-water pixels in which the likelihood falls within a first non-water range in any one of determination regions to be determined in the respective frames;
measure the number of boundary pixels in which the likelihood falls within a first water range in any one of the determination regions and the likelihood falls within a second non-water range in any one of the determination regions; and
determine region satisfies a predetermined determination condition based on the number of non-water pixels and the number of boundary pixels.

### Claim 2 (depends on 1)

The region determining device according to claim 1, wherein
the at least one processor is further configured to measure the number of water pixels in which the likelihood falls within a second water range in any one of the determination regions, wherein
the at least one processor further determines the determination region by using the number of water pixels.

### Claim 3 (depends on 2)

The region determining device according to claim 2, wherein
the non-water pixel is a pixel in which the likelihood falls within the first non-water range in the determination regions equal to or more than the first number of frames,
the boundary pixel is a pixel in which the likelihood falls within the first water range in the determination regions equal to or more than the second number of frames and the likelihood falls within the second non-water range in the determination regions equal to or more than the third number of frames, and
the water pixel is a pixel in which the likelihood falls within the second water range in the determination regions equal to or more than the fourth number of frames.

### Claim 4 (depends on 1)

The region determining device according to claim 1 wherein
the at least one processor is further configured to set the determination region based on a predetermined setting rule, wherein
the at least one processor repeats the setting of the determination region until the determination region satisfies the determination condition and outputs the determination region that satisfies the determination condition.

### Claim 5 (depends on 1)

The region determining device according to claim 1 wherein
the at least one processor is further configured to set a plurality of the determination regions in the image based on a predetermined setting rule, wherein
the at least one processor outputs the determination region that satisfies the determination condition from among the set determination regions.

### Claim 6 (depends on 4)

The region determining device according to claim 4, wherein
the at least one processor is further configured to detect, in the image, an unrecommended region that is better not to be included in the determination region and/or a recommended region that is better to be included in the determination region, wherein
the at least one processor sets the determination region by referring to the unrecommended region and/or the recommended region.

### Claim 7 (depends on 6)

The region determining device according to claim 6, wherein
the at least one processor is further configured to determine an additional region to be added to the determination region based on a position of a water level in a predetermined reference image; and
add the additional region to the determination region.

### Claim 8 (depends on 1)

A monitoring system comprising:
a monitoring camera configured to capture the image;
the region determining device according to claim 1 configured to determine the determination region by using the image; and
a warning device configured to determine whether the determination region in the image is used for determination of a warning based on a result determined by the region determining device.

### Claim 9

A region determining method comprising:
by at least one processor,
calculating a likelihood of wetness of a pixel in an image including a plurality of frames;
measuring the number of non-water pixels in which the likelihood falls within a first non-water range in any one of determination regions to be determined in the respective frames;
measuring the number of boundary pixels in which the likelihood falls within a first water range in any one of the determination regions and the likelihood falls within a second non-water range in any one of the determination regions; and
determining whether the determination region satisfies a predetermined determination condition based on the number of non-water pixels and the number of boundary pixels.

### Claim 10

A non-transitory recording medium for recording a program for causing a computer to execute:
calculating a likelihood of wetness of a pixel in an image including a plurality of frames;
measuring the number of non-water pixels in which the likelihood falls within a first non-water range in any one of determination regions to be determined in the respective frames;
measuring the number of boundary pixels in which the likelihood falls within a first water range in any one of the determination regions and the likelihood falls within a second non-water range in any one of the determination regions; and
determining whether the determination region satisfies a predetermined determination condition based on the number of non-water pixels and the number of boundary pixels.
