KR102319084B1 - Intelligent water level detecting apparatus and method - Google Patents

Abstract

The present invention relates to an intelligent water level detecting apparatus and method. The apparatus comprises: a water mark image obtaining unit which recognizes a water surface position from an image photographed by a camera and obtains a water mark image of surroundings near the recognized water surface; a water level representing object recognizing unit which recognizes a water level representing object from the obtained water mark image; a water level analyzing unit which converts the recognized water level representing object into a water level value to calculate a current water level value; and a water level situation warning unit which warns a dangerous situation according to the current water level value. The intelligent water level detecting apparatus accurately detects the current water level and warns the dangerous situation according to the current water level.

Description

INTELLIGENT WATER LEVEL DETECTING APPARATUS AND METHOD

The present invention relates to an intelligent water level detection technology, and more particularly, an intelligent water level detection device capable of accurately detecting the current water level by analyzing an image obtained through photographing of a water level table and notifying a dangerous situation according to the current water level state; it's about how

The recent typhoons and floods are caused by climate change caused by global warming. Unlike in the past, the scale of typhoons and floods is larger and it is very difficult to predict their course. In order to prevent such disaster damage in advance, there is an increasing demand for a system that automatically detects the river level.

In the existing river level detection system, an ultrasonic sensor and a pressure sensor are mainly used. In the case of an ultrasonic sensor, it is installed on the top of a bridge or column of a river, emits ultrasonic waves to the water surface, and measures the reflected ultrasonic waves on the surface of the river and returns to the sensor to detect the water level of the river. Since the ultrasonic sensor is installed on the upper part of the bridge column, the lifespan of the sensor is long, but it has a disadvantage in that it is sensitive to external factors such as snow or rain, and thus measurement error occurs. The pressure sensor is installed below the water surface and detects the water level of the river with the pressure measured from the water surface. Pressure sensors are less sensitive to changes in the external environment such as snow or rain, but have a short lifespan because they are installed under rivers and are constantly under pressure.

Recently, a method of detecting the water level by installing a water level mark on a pier or column of a bridge and photographing the water level detected through the water level mark with a camera is used. The water level mark is a mark made to measure the water level, and the scale and number are displayed, and the water level can be measured by reading the scale and number in contact with the water surface.

However, there is a possibility that an error may occur in recognizing the water level using the camera according to the change of the external environment or the pollution of the water level table due to foreign substances.

Korean Patent Application Laid-Open No. 10-2006-0099496 (2006.09.19) relates to a real-time remote water level monitoring and monitoring system using an image recognition technique. A technology that automatically reads the water level on the water level table by applying the recognition technology and informs the manager is disclosed.

Korea Patent No. 10-1940519 (2019.01.15) relates to an automatic water level measuring device and method, including a light pattern irradiation unit that irradiates a reference light pattern to a pattern irradiation object, and a reference light pattern irradiated to the pattern irradiation object An image acquisition unit for acquiring an image, and a water level analysis unit for measuring the current water level by analyzing the image acquired through the image acquisition unit Disclosed is a technology for automatically measuring the current water level by receiving an input of a light pattern in real time and analyzing/processing the image.

Korean Patent Publication No. 10-2006-0099496 (2006.09.19) Korean Patent Registration No. 10-1940519 (Jan. 15, 2019)

An embodiment of the present invention is to provide an intelligent water level detection device and method capable of accurately detecting a current water level by analyzing an image obtained through photographing of a water level table and notifying a dangerous situation according to the current water level state.

An embodiment of the present invention can reduce the error of water level measurement by accurately recognizing the objects displaying the water level in the water level table captured image through deep learning-based image analysis and determining the current water level based on the recognized water level display objects. To provide an intelligent water level detection device and method.

An embodiment of the present invention provides an intelligent water level detection device and method for generating an alarm according to a dangerous situation of the current water level and notifying the user terminal to check the current water level and to accurately respond according to the dangerous situation. .

Among the embodiments, the intelligent water level detection device recognizes a water surface position in an image taken by a camera and recognizes a water level display object in the obtained water level mark image, a water level mark image acquisition unit for obtaining a water level mark image near the recognized water surface and a water level display object recognition unit that converts the recognized water level display object into a water level value and calculates a current water level value, and a water level condition alarm unit that alerts a dangerous situation according to the current water level value.

A plurality of cameras may be disposed at a site where a water level mark is installed to detect the water level, and may photograph the water level mark and the water surface.

The water level display object may include the number of scales, numbers, colors, and patterns indicating the water level displayed on the water level table.

The water level display object recognition unit may recognize the water level display objects from the water level table image through deep learning-based image analysis.

The water level display object recognition unit recognizes the number of scales by extracting the scale of the water level table appearing on the upper side of the water surface from the water level table image when the water level is marked on the water level table and counting the number of extracted scales, and the water level table When the water level is displayed in color, the color attribute of the water level table is extracted from the water level table image to recognize the color of the water level mark contacting the water surface, and when the water level is displayed in a pattern on the water level table image The shape of the pattern is recognized, and when the water level is numerically displayed on the water level table, the text area can be estimated from the water level table image, and the number in the text area can be recognized by classifying the text area and the non-text area.

The water level analysis unit selects at least one water level display object among the number of scales, numbers, colors, and patterns recognized based on the environment context, and determines the water level value according to the selected water level display object as the current water level value. have.

The water level analysis unit is a water level value according to the number of scales on the water level table on the upper side of the water surface, a water level value according to the number of the water level table in contact with the water surface, a water level range according to the color of the water level table in contact with the water surface, and a water level value according to the pattern shape of the water level table in contact with the water surface It is possible to determine the current water level value through the averaging.

The water level situation alarm unit divides the water level situation into stages of flat water level, surrounding, boundary, danger, and flooding according to the current water level value, and predicts the water level situation based on the water level change to generate a step-by-step alarm according to the current water level situation or the predicted water level situation and may provide the current water level and water level status to the user terminal of the administrator or user.

Among the embodiments, the intelligent water level detection method includes the steps of recognizing a water surface position in an image taken by a camera, acquiring a water level table image near the recognized water level, and analyzing the water level based on deep learning from the obtained water level mark image Recognizing a water level display object including the number of scales, colors, patterns, and numbers indicating the water level displayed in the table, the water level selected by selecting at least one water level display object among the recognized water level display objects based on the environment context Converting a display object to a water level value to calculate a current water level value or converting each of the recognized water level display objects to a water level value and calculating a current water level value by synthesizing, and alerting a dangerous situation according to the current water level value includes steps.

The disclosed technology may have the following effects. However, this does not mean that a specific embodiment should include all of the following effects or only the following effects, so the scope of the disclosed technology should not be construed as being limited thereby.

The intelligent water level detection apparatus and method according to an embodiment of the present invention may analyze an image obtained through photographing of a water level table to accurately detect the current water level and notify a dangerous situation according to the state of the current water level.

An intelligent water level sensing device and method according to an embodiment of the present invention accurately recognizes objects indicating a water level in a water level table captured image through deep learning-based image analysis, and determines the current water level based on the recognized water level display objects This can reduce the error in water level measurement.

The intelligent water level sensing device and method according to an embodiment of the present invention generates an alarm according to a dangerous situation of the current water level and notifies the user terminal to check the current water level and to take an accurate response according to the dangerous situation.

1 is a view for explaining an intelligent water level detection system according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating the physical configuration of the intelligent water level sensing device of FIG. 1 .
FIG. 3 is a block diagram illustrating a functional configuration of the intelligent water level sensing device of FIG. 1 .
4 is an exemplary diagram for explaining a water level table according to an embodiment.
5 is a flowchart illustrating an intelligent water level sensing process according to an embodiment of the present invention.

Since the description of the present invention is merely an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiment described in the text. That is, since the embodiment may have various changes and may have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such effects, it should not be understood that the scope of the present invention is limited thereby.

On the other hand, the meaning of the terms described in the present application should be understood as follows.

Terms such as “first” and “second” are for distinguishing one component from another, and the scope of rights should not be limited by these terms. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component.

When a component is referred to as being “connected” to another component, it should be understood that the component may be directly connected to the other component, but other components may exist in between. On the other hand, when it is mentioned that a certain element is "directly connected" to another element, it should be understood that the other element does not exist in the middle. Meanwhile, other expressions describing the relationship between elements, that is, “between” and “immediately between” or “neighboring to” and “directly adjacent to”, etc., should be interpreted similarly.

The singular expression is to be understood to include the plural expression unless the context clearly dictates otherwise, and terms such as "comprises" or "have" refer to the embodied feature, number, step, action, component, part or these It is intended to indicate that a combination exists, and it should be understood that it does not preclude the possibility of the existence or addition of one or more other features or numbers, steps, operations, components, parts, or combinations thereof.

Identifiers (eg, a, b, c, etc.) in each step are used for convenience of description, and the identification code does not describe the order of each step, and each step clearly indicates a specific order in context. Unless otherwise specified, it may occur in a different order from the specified order. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

The present invention can be embodied as computer-readable codes on a computer-readable recording medium, and the computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. . Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like. In addition, the computer-readable recording medium may be distributed in a network-connected computer system, and the computer-readable code may be stored and executed in a distributed manner.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Terms defined in general used in the dictionary should be interpreted as being consistent with the meaning in the context of the related art, and cannot be interpreted as having an ideal or excessively formal meaning unless explicitly defined in the present application.

1 is a view for explaining an intelligent water level detection system according to an embodiment of the present invention.

Referring to FIG. 1 , the intelligent water level detection system 100 may include a water level table 110 , a camera 130 , an intelligent water level detection device 150 , and a user terminal 170 .

The water level table 110 is installed on the pole of the bridge 10 and may display the water level with a scale and characters. The water level table 110 may be easily readable by an observer by attaching it to a concrete or wooden post by marking a minimum scale of 1 cm and 1 m on a material such as stainless or aluminum that is not easily corroded by water. The water level mark 110 may be displayed by printing scales and characters on the pillars of the bridge 10 . The water level display method of the water level table 110 may be displayed with scales and characters, and may be displayed with different colors and patterns for each specific scale unit.

A plurality of cameras 130 may be disposed in the field to detect the water level. In one embodiment, the camera 130 may be implemented in the form of a CCTV, but is not necessarily limited thereto, and may be implemented in various forms capable of photographing the water surface including the water level mark 110 installed on the pillar of the bridge 10 . have. Here, the camera 130 may be connected to the intelligent water level sensing device 150 through a network. In one embodiment, the camera 130 may be implemented by being included in the intelligent water level sensing device 150 unlike FIG. 1 , and in this case, the camera 130 may serve as the water level table image acquisition unit 310 . have.

The intelligent water level detection device 150 may be implemented as a server corresponding to a computer or program capable of detecting the water level by analyzing the captured image of the camera 130 and notifying the occurrence of an alarm and a dangerous situation according to the water level situation. Here, the intelligent water level detection device 150 may be connected to the camera 130 and the user terminal 150 for water level detection through a wired network or a wireless network such as Bluetooth or WiFi. In addition, the intelligent water level detection device 150 may be connected to an external system (not shown in FIG. 1 ), for example, may be connected to a water level observatory system, a control station system, a disaster safety system, and the like.

In an embodiment, the intelligent water level detection device 150 may provide a notification of a current water level value and a dangerous situation to the user terminal 170 . In an embodiment, the intelligent water level sensing device 150 may store information necessary in the process of detecting the water level in conjunction with a database. In addition, the intelligent water level sensing device 150 may be implemented as a system configuration including a processor, a memory, a user input/output unit, and a network input/output unit, which will be described in more detail with reference to FIG. 2 .

The user terminal 170 may correspond to a computing device capable of being notified of the current water level and dangerous situation, and may correspond to a mobile device of an administrator or a user who uses the bridge 10 or is nearby. The user terminal 170 may be connected to the intelligent water level sensing device 150 through a network, and a plurality of user terminals 170 may be simultaneously connected to the intelligent water level sensing device 150 .

FIG. 2 is a block diagram illustrating the physical configuration of the intelligent water level sensing device of FIG. 1 .

Referring to FIG. 2 , the intelligent water level sensing device 150 may include a processor 210 , a memory 230 , a user input/output unit 250 , and a network input/output unit 270 .

The processor 210 may execute each procedure for intelligent water level detection, manage the memory 230 to be read or written throughout the process, and synchronize the volatile and non-volatile memories in the memory 230 . You can schedule time. The processor 210 may control the overall operation of the intelligent water level sensing device 150 , and is electrically connected to the memory 230 , the user input/output unit 250 , and the network input/output unit 270 to control the flow of data therebetween. can do. The processor 210 may be implemented as a central processing unit (CPU) of the intelligent water level sensing device 150 .

The memory 230 is implemented as a non-volatile memory, such as a solid state disk (SSD) or a hard disk drive (HDD), and may include an auxiliary storage device used to store overall data required for the intelligent water level detection device 150 and , and may include a main memory implemented as a volatile memory such as random access memory (RAM).

The user input/output unit 250 may include an environment for receiving a user input and an environment for outputting specific information to the user. For example, the user input/output unit 250 may include an input device including an adapter such as a touch pad, a touch screen, an on-screen keyboard, or a pointing device, and an output device including an adapter such as a monitor or a touch screen. In an embodiment, the user input/output unit 250 may correspond to a computing device accessed through remote access, and in such a case, the intelligent water level sensing device 150 may be implemented as a server.

The network input/output unit 270 includes an environment for connecting with an external device or system through a network, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and a VAN (Wide Area Network) (VAN). It may include an adapter for communication such as Value Added Network).

FIG. 3 is a block diagram illustrating a functional configuration of the intelligent water level sensing device of FIG. 1 .

Referring to FIG. 3 , the intelligent water level detection device 130 includes a water level table image acquisition unit 310 , a water level display object recognition unit 330 , a water level analysis unit 350 , a water level situation alarm unit 370 and a control unit 390 . may include.

The water level table image acquisition unit 310 may photograph the water level table 110 with the camera 130 to recognize the position of the water surface, and acquire a water level mark image near the recognized water level. In an embodiment, the water level mark image acquisition unit 310 may photograph the water level mark 110 installed on the pole of the bridge 10 while moving the camera 130 up and down. That is, the plurality of cameras 130 may always photograph the water level table 110 and the water surface. The plurality of cameras 130 may be installed on a lower portion of the leg 10 that is relatively less affected by external environmental factors such as snow or rain. The plurality of cameras 130 are configured to adjust the shooting angle up and down according to the change of the water level in order to accurately calculate the water level. In an embodiment, the watermark image acquisition unit 310 analyzes the images captured by the plurality of cameras 130 by a cross-correlation method to recognize the position of the water surface and acquire a watermark image near the recognized water surface position. can

The water level display object recognition unit 330 may recognize water level display objects from the acquired water level table image through deep learning-based image analysis.

Deep learning technology is an artificial intelligence (AI) technology that enables computers to think and learn like humans. Based on artificial neural network theory, machines can learn and solve complex nonlinear problems on their own. Deep learning is a technology that trains a machine so that a computer can distinguish an object by mimicking the information processing method that the human brain discovers patterns in numerous data and then distinguishes objects.

In other words, deep learning is defined as a set of machine learning algorithms that attempt high-level abstraction through a combination of several nonlinear transformation techniques.

Methods for recognizing an image and an object using such deep learning include a convolutional neural network (CNN), a recurrent neural network (RNN), and a deep Q-network (DQN). Among them, a convolutional neural network (CNN) is a method specialized for two-dimensional image processing and can recognize an object by using the pixel value of the image itself.

The water level display object recognition unit 330 may extract the water level display object from the water level table image based on pre-learned content based on deep learning. Here, the water level display object may include a scale, color, pattern, number, etc. indicating the water level marked on the water level table 110 . In an embodiment, the water level display object recognition unit 330 may recognize the number of divisions by extracting the divisions of the water level table 110 appearing above the water surface from the acquired water level table image and counting the number of the extracted divisions. The water level display object recognition unit 330 extracts the color properties through a neural network (CNN) structure in which the red (R), green (G), and blue (B) channels of the obtained water level table image are convolved to the water surface. The color of the water level table 110 in contact can be recognized.

In an embodiment, the water level display object recognition unit 330 may recognize the shape of the pattern in contact with the water surface from the acquired water level table image when the water level is displayed separately in a specific shape pattern on the water level table 110 . The water level display object recognition unit 330 may recognize a number in the text area by estimating the text area from the acquired water level table image and classifying the text area and the non-text area.

The water level analyzer 350 may determine the water level value by selecting at least one object among the recognized water level display objects according to the installation environment of the water level table 110 . The water level analyzer 350 may comprehensively analyze the recognized water level display objects to determine the current water level. The water level analysis unit 350 stores in advance the water level values according to the water level display objects such as scales and numbers, colors, and patterns constituting the water level table 110 , and the water level recognized based on the water level values according to the previously stored water level display objects. Calculates the level values of display objects. In an embodiment, the water level analyzer 350 may collect an environment context by itself or through communication, and select a water level display object to be used in determining a water level value based on the collected environment context. Here, the environment context may include at least one of location, time, season, temperature, weather, and illuminance. For example, when the current water level detection time is night, an error may occur in color recognition, and in the daytime, sunlight may be reflected off the water to cause an error in number recognition. Accordingly, the water level analyzer 350 selects a water level display object that can be accurately recognized based on the environment context, and converts the selected water level display object to a water level value by comparing the selected water level display object with the stored water level display object to determine the current water level value.

In an embodiment, the water level analyzer 350 may determine the water level value through an average by synthesizing the water level values according to each of the recognized water level display objects. Here, the water level analysis unit 350 includes a water level value according to the number of scales on the water level table on the upper side of the water surface, a water level value according to the number of water level tables in contact with the water surface, a water level range according to the color of the water level table bonded to the water surface, The current water level value can be determined by synthesizing the water level values according to the pattern shape. The water level analyzer 350 may determine the current water level through an average of water level values of the recognized water level display objects. In an embodiment, the water level analyzer 350 may determine the current water level through the average of the remaining water level values excluding the highest and lowest among the recognized water level values of the water level display objects. The water level analysis unit 350 can accurately measure the current water level even if there is a deviation in the water level value due to contamination in the water level table 110 or an error in the recognition of some of the water level display objects due to external environmental factors. have.

For example, the water level analysis unit 350 indicates that the water level is 2 m when the number of water level table scales exposed on the upper side of the water surface is two, and when the color is yellow, the water level is between 2 m and 3 m, and when the pattern is a dotted line, the water level is 2 m. If the character is 2, the water level is 2m, so the current water level is calculated as 2m.

The water level situation warning unit 370 may determine a dangerous situation based on the current water level value, and if it is an alarm target, may output an external alarm signal through a speaker and notify the user terminal 170 of the dangerous situation. In one embodiment, the water level situation warning unit 370 may classify the water level situation into stages such as flat water level, surrounding, boundary, danger, flooding, etc. according to the current water level value, and predict the water level situation based on the water level change to predict the current water level situation or It generates a step-by-step alarm according to the predicted water level situation so that the water level situation can be easily recognized. The water level alarm unit 370 may generate an alarm according to each alarm, and provides the current water level and water level condition to the user terminal 170 of the manager or user so as to quickly and appropriately respond to a dangerous situation.

The control unit 390 controls the overall operation of the intelligent water level detection device 150, the water level table image acquisition unit 310, the water level display object recognition unit 330, the water level analysis unit 350, and the water level situation alarm unit 370. It can manage the control flow or data flow between them.

4 is an exemplary diagram for explaining a water level table according to an embodiment.

Referring to FIG. 4 , the water level table 110 shows a method of displaying the water level with the number of scales, a method of displaying the water level with numbers, a method of displaying the water level with a specific pattern, a method of displaying the water level with a color, and a combination thereof. It can be implemented in various ways, such as a method of displaying the water level by applying it.

4(A) is an example of a water level table in which black scales are displayed at regular intervals on a bridge column, and a water level value can be determined by analyzing the number of scales.

4(B) is an example of a water level table in which different color scales are displayed at regular intervals on a bridge column, and a water level value can be determined through analysis of the number and/or color of the scales.

FIG. 4(C) is an example of a water level table in which different pattern scales are displayed on a bridge column at regular intervals, and a water level value can be determined by analyzing the number of scales and/or pattern shape.

4(D) is an example of a water level table in which numbers indicating water levels are directly displayed on a bridge column at regular intervals, and a water level value can be determined through numerical analysis.

(E) of FIG. 4 is an example of a water level table displayed in a complex manner. A scale and a number are written together to indicate a water level, and a dangerous situation according to the water level can be displayed in different colors for each step. For example, the danger mark can be marked with different colors: white for flat water levels below 10 m, blue for water levels around 11 m or less, orange for boundary water levels below 12 m, and red for flooding water levels below 14 m.

The intelligent water level sensing device 150 according to an embodiment recognizes a water level display object such as a scale, number, color, pattern, etc. displayed on the water level table 110 from an image taken of the water level table 110 and selects a specific value according to the installation environment. The accuracy of water level measurement can be improved by selecting a water level display object or synthesizing them to determine the current water level value.

5 is a flowchart illustrating an intelligent water level sensing process according to an embodiment of the present invention.

Referring to FIG. 5 , the intelligent water level detection device 150 recognizes the position of the water surface in the image captured by the camera 130 through the water level mark image acquisition unit 310 and acquires the water level mark image near the recognized water level. Yes (step S510). The water table image acquisition unit 310 converts the image taken through the camera 130 into a three-dimensional space-time image, calculates the average and standard deviation of the image intensity from the converted space-time image, and divides the image into a flowing and non-flowing region. By setting the boundary between the flowing and non-flowing regions as the water surface, it can be recognized as a water surface position. The watermark image acquisition unit 310 may acquire a watermark image near the surface of the water by recognizing the location of the water surface.

In addition, the intelligent water level sensing device 150 may recognize a water level display object including at least one of the number of scales, colors, patterns, and characters of the water level table near the water surface through the water level display object recognition unit 330 (step S530). The water level display object recognition unit 330 extracts the water level mark image object near the water surface through deep learning analysis of the water level mark image, and information such as the number, color, shape, and character of the pattern from the extracted water level mark image object can be extracted. have.

The intelligent water level sensing device 150 may convert the water level display objects recognized through the water level analyzer 350 into a water level value to calculate the current water level value (step S550). The intelligent water level detection device 150 may alert the dangerous situation according to the current water level value calculated through the water level condition alarm unit 370 and notify the user terminal 170 (step S570).

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art can variously modify and change the present invention within the scope without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that it can be done.

100: intelligent water level detection system
110: watermark 130: camera
150: intelligent water level detection device 170: user terminal
210: processor 230: memory
250: user input/output unit 270: network input/output unit
310: water level image acquisition unit 330: water level display object recognition unit
350: water level analysis unit 370: water level situation alarm unit
390: control unit

Claims (9)

a water table image acquisition unit for recognizing a water surface position in an image taken by a camera and acquiring a water level mark image near the recognized water surface;
a water level display object recognition unit for recognizing a water level display object from the obtained water level table image;
a water level analysis unit converting the recognized water level display object into a water level value to calculate a current water level value; and
and a water level warning unit for warning a dangerous situation according to the current water level value,
The water level display object recognition unit
Recognize the water level display objects through deep learning-based image analysis in the water level table image,
When the water level is marked on the water level table, the level of the water level table that appears above the water surface in the water level table image is extracted and the number of the extracted divisions is counted to recognize the number of divisions,
When the water level is displayed in color on the water level table, the color property of the water level table is extracted from the water level table image to recognize the color of the water level table in contact with the water surface,
Recognizing the shape of the pattern in contact with the water surface in the water level table image when the water level is patterned on the water level table,
When the water level is numerically displayed on the water level table, the text area is estimated from the water level table image and the text area and the non-text area are classified to recognize the number in the text area,
The water level analysis unit
The water level value according to the number of scales on the water level table on the upper side of the water level, the water level value according to the number of the water level mark in contact with the water surface, the water level range according to the color of the water level mark in contact with the water surface, and the water level value according to the pattern shape of the water level mark touching the water surface. An intelligent water level sensing device, characterized in that it determines the current water level value through
The method of claim 1, wherein the camera
An intelligent water level detection device, characterized in that a plurality of water level markers are installed at the site to detect the water level, and the water level marker and the water surface are photographed.
According to claim 1, wherein the water level display object
Intelligent water level detection device, characterized in that it includes the number of scales, numbers, colors, and patterns indicating the water level displayed on the water level table.
delete delete delete delete According to claim 1, wherein the water level warning unit
According to the current water level, it classifies the water level situation into levels of level, surrounding, boundary, danger, and flooding, and predicts the water level situation based on the change in water level to generate a step-by-step alarm according to the current or predicted water level situation, and An intelligent water level sensing device, characterized in that it provides the current water level and water level situation to the user terminal.
Recognizing the position of the water surface in the image taken by the camera and acquiring a water level table image near the recognized water surface;
recognizing a water level display object including the number, color, pattern, and number of scales indicating the water level displayed on the water level table through deep learning-based image analysis in the obtained water level table image;
converting each of the recognized water level display objects into a water level value and calculating a current water level value by synthesizing them; and
Including the step of alarming a dangerous situation according to the current water level value,
The step of calculating the current water level value is
The water level value according to the number of scales on the water level table above the water level, the water level value according to the number of the water level table in contact with the water surface, the water level range according to the color of the water level table in contact with the water surface, and the water level value according to the pattern shape of the water level table connected to the water surface. Intelligent water level detection method, characterized in that determining the current water level value through

Images