KR102210019B1 - Method of monitoring aquafarm using water surface drone - Google Patents

Abstract

According to the present invention, provided is a farm monitoring method using a water drone comprising: a first step of acquiring an image while navigating around the farm; a second step of temporarily storing the acquired image data; a third step of comparing a reference image with a current frame image to calculate an amount of change; a fourth step of determining an abnormal state when the amount of change is greater than that of a threshold value, and sending an alarm to a terminal; and a fifth step of permanently storing the image data from a predetermined frame before the frame in which the abnormality is detected. The water drone of the present invention can maintain a stable posture in a marine environment, and can be automatically restored even if overturned.

Description

Aquafarm monitoring method using a water drone{METHOD OF MONITORING AQUAFARM USING WATER SURFACE DRONE}

The present invention relates to a farm monitoring method using a floating drone, and more specifically, a farm using a floating drone having a function of autonomously monitoring the surroundings of a farm by replacing manpower, and storing an image and sending a notification when an abnormal condition is detected. It's about how to watch.

Initially, drones began to be developed mainly in the form of wireless aircraft for military purposes to reduce the sacrifice of allies, but now drones that can be operated on land, water, and water are being developed, and the scope of use is also in agriculture, logistics, surveying, disaster monitoring, and human life. It is expanding to various fields, even to structure.

Recently, the demand for water drones capable of operating in marine environments is also gradually increasing. Conventionally, people went out to the sea to monitor the ocean, collect marine samples, and perform surveying activities, but working for a long time in a harsh environment caused by wind and waves consumes a lot of human resources and carries a high risk. The demand for unmanned surface drones that can replace activities is gradually increasing.

Since a surface drone must be able to perform activities such as monitoring and information collection in a rugged marine environment, it must be able to maintain its posture stably even by winds and waves that change from time to time, and to be automatically restored even if it is overturned.

The technical problem to be achieved by the present invention is to provide a floating drone that can stably maintain its posture in a marine environment where wind and waves change from time to time, and can be automatically restored even if it is overturned.

The technical problem to be achieved by the present invention is to provide a floating drone capable of solving inconveniences in transportation and storage caused by an increase in volume and weight due to mounting of various electronic devices.

The technical problem to be achieved by the present invention is to provide a floating drone capable of monitoring damage, loss, and theft of a farm on behalf of manpower and transmitting a notification signal when abnormal conditions are detected.

In order to achieve the above technical problem, according to an embodiment of the present invention, a farm monitoring method using a water drone includes a first step of acquiring an image while navigating around a farm, and a second step of temporarily storing the acquired image data. Step, a third step of comparing the reference image and the current frame image to calculate the amount of change, and a fourth step of determining an abnormal state and sending an alarm to the terminal when the amount of change is greater than a threshold value, and an abnormality is detected. And a fifth step of permanently storing image data from before a certain frame of the frame.

According to an embodiment of the present invention, it is possible to improve the posture stability and resilience of a water drone by using a battery that supplies power as a weight without adding an additional weight structure.

According to an embodiment of the present invention, by allowing a multifunctional part including some devices such as batteries and sensors to be attached and detached to the hull, it is possible to facilitate transportation and storage by distributing the total volume and weight of the water drone.

According to an embodiment of the present invention, it is possible to increase the operational efficiency of a surface drone depending on the purpose by providing multi-function units each having different sensors and selecting it according to a purpose and mounting it on the hull.

According to an embodiment of the present invention, an alarm is sent to the terminal by determining damage, loss, and theft of the farm based on the amount of change in the image image of the farm taken while autonomously navigating around the farm, so that the farm is efficiently monitored by replacing manpower. You can do your job.

According to an embodiment of the present invention, since the data of the section in which the abnormality is detected by processing the photographed image data is selectively stored, a limited storage space can be efficiently used even for long-term farm monitoring activities.

The effects of the present invention are not limited to the above effects, and should be understood to include all effects that can be inferred from the configuration of the invention described in the detailed description or claims of the present invention.

1 is a view showing a water drone according to an embodiment of the present invention.
Figure 2 is a block diagram showing the configuration of a multi-function unit of the water drone according to an embodiment of the present invention.
3 is a view showing a water drone with improved resilience by the multifunctional unit of FIG. 2.
4 is a view for showing a detachable function of a water drone according to an embodiment of the present invention.
5 is a view for explaining a method of measuring a water temperature of a target depth of the water drone according to an embodiment of the present invention.
6 is a diagram illustrating an example of an artificial intelligence neural network that has been learned to determine a water temperature of a target depth using a plurality of parameters.
7 is a diagram schematically showing that a water drone according to an embodiment of the present invention autonomously performs aquaculture monitoring.
Figure 8 is a flow chart showing a method for monitoring aquaculture farm by a water drone according to the present invention.
9 is a diagram illustrating examples of image data to aid in the description of FIG. 8.

Hereinafter, the present invention will be described with reference to the accompanying drawings. However, the present invention may be implemented in various different forms, and therefore is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are assigned to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected (connected, contacted, bonded)" with another part, it is not only "directly connected", but also "indirectly connected" with another member in the middle. "Including the case. In addition, when a part "includes" a certain component, it means that other components may be further provided, rather than excluding other components unless specifically stated to the contrary.

The terms used in the present specification are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or a combination thereof described in the specification, but one or more other features. It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof, does not preclude in advance.

Hereinafter, a water drone according to the present invention will be described in detail with reference to the drawings.

1 is a view showing a water drone according to an embodiment of the present invention.

As shown in Figure 1, the water drone 100 according to the present invention is the hull 110, the multi-function unit 120, the first sensor unit 130, the image collection unit 140, the antenna 150 and the first It includes two sensor unit 160.

The hull 110 of the water drone 100 has buoyancy so that it can float on the water surface, and therein, an image processing device (not shown) that processes an image captured by the image collection unit 140, data measured through a sensor, or A storage device (not shown) for storing photographed image data and a control terminal or a communication device (not shown) for processing data transmitted and received between the control center and the water drone 100 may be provided.

The multifunctional unit 120 is coupled to the bottom of the ship of the surface drone 100, that is, the lower part of the hull 110, and supplies power necessary for the operation of the surface drone 100 and the operation of various electronic devices, or provides underwater environment data. It is collected and transmitted to the communication device of the hull 110. Detailed configuration and operation of the multifunctional unit 120 will be described later with reference to FIG. 2.

The first sensor unit 130 is coupled to the multi-function unit 120 to collect underwater environment data. The underwater environment data includes water temperature, salinity, water depth, pH, and flow rate. The first sensor unit 130 may be detachably attached to the multi-function unit 120 and includes at least one of a temperature sensor, a depth sensor, a salinity sensor, a pH sensor, and a flow rate sensor.

The image collection unit 140 includes a camera 142, a gimbal 144, and a protection unit 146.

The camera 142 is rotatable and captures an external image within a set angle.

As shown, two rotatable cameras 142 may be operated to capture 360-degree surrounding images. In FIG. 1, two cameras 142 are shown to be operated, but an external image may be captured by rotating one camera 360 degrees.

The captured image is processed by an image processing device provided in the underwater drone 100, and only valid image data is selectively stored among the processed image data. For example, it is possible to selectively and permanently store only the image data of the section in which an abnormality is detected among the image data photographed for farm monitoring, and through this, a limited storage space can be efficiently used. The video data stored in this way may be streamed at the request of a control terminal or a control center.

The gimbal 144 is a device that maintains the posture of the camera 142 horizontally for stable image capture even in a shaking hull.

The protection unit 146 is a protective case installed to prevent the camera 142 from being damaged by flying foreign objects, strong wind, or strong waves. The protection unit 146 may be made of a transparent glass or transparent plastic material to protect the camera 142 but not to obstruct the view of the camera 142 when taking an image.

The antenna 150 transmits data or captured images measured through the first sensor unit 130 and the second sensor unit 160 to a pilot terminal or a control center, and a drone control signal transmitted from the pilot terminal or the control center. Receive. That is, data is transmitted and received between the control terminal or the control center and the floating drone 100. The control terminal may be a smartphone with a control app installed, or may be a dedicated remote controller.

The surface drone 100 may transmit/receive data to and from a terminal or a control center using the LTE (Long Term Evolution) method. However, when a sufficient number of Access Points are installed on surrounding islands, farms, and marine buoys, data may be transmitted and received using WiFi (Wireless Fidelity).

Although the LTE method and the WiFi method have been mentioned as examples of the communication method of the surface drone 100, the present invention is not limited thereto, and various wireless communication methods may be applied.

The second sensor unit 160 is a sensor that is exposed above sea level and installed on the hull 110 to collect atmospheric environment data, and may include at least one of a temperature sensor, an air volume sensor, an illuminance sensor, and a humidity sensor. .

On the other hand, although not shown in the drawing, the floating drone 100 includes a GPS device that can determine the location in real time during remote control or autonomous driving, a propulsion device for moving the floating drone 100 such as a screw, and the hull 110 Also included is a rudder installed on the center line to turn the drone 100 left and right.

The water drone 100 configured as described above may perform a function of collecting underwater and atmospheric environment data using the first sensor unit 130 and the second sensor unit 160 and transmitting the data to a terminal or a control center. The collection unit 140 may be used to monitor damage, loss, and theft of a farm.

The multifunctional unit 120 is located at the bottom of the water drone 100 and functions to supply power to the water drone 100 and measure underwater environment data. In addition, by using the weight of the multi-function unit 120 to move the center of gravity of the water drone 100 downward, it also performs a function of improving the posture stability and resilience of the water drone 100.

Hereinafter, the configuration of the multifunctional unit 120 will be described in detail with reference to the drawings.

As shown in Figure 2, the multi-function unit 120 includes a battery 122, a power control unit 123, a power connection terminal 124, a sensor mounting unit 125, a data interface terminal 128, and a first sensor unit ( 130).

The battery 122 is disposed at the lowest end of the multifunctional unit 120, that is, the lowest end of the surface drone.

The battery 122 is a rechargeable secondary battery, and a lithium polymer battery may be applied.

The surface drone 100 requires a large-capacity battery because it collects marine and atmospheric environment data or monitors a farm for a long time while operating at sea for a long time, and it is also equipped with a plurality of large-capacity batteries to supply sufficient power.

In the present invention, the battery 122 used to supply power to the floating drone 100 is also used as a weight of the floating drone 100. When the battery 122 is disposed at the bottom of the surface drone 100, the center of gravity of the surface drone 100 can be moved downward, thereby improving the postural stability and resilience of the surface drone 100.

If the center of gravity cannot be sufficiently moved with only the weight of the battery 122, some or all of the image processing devices, image storage devices, and communication devices provided in the hull 110 are moved and arranged to the multifunctional unit 120 Thus, it is possible to increase the weight of the multi-functional unit 120.

Meanwhile, the power control unit 123 converts the current and voltage of the battery 122 into various sizes and supplies them to each electronic device of the floating drone 100.

Since the image processing devices, storage devices, communication devices, and various sensors installed inside the ship may have different allowed rated voltages and rated currents, the power control unit 123 reduces the power of the battery 122 within the allowable range of each electronic device. Convert and supply.

In addition, the power control unit 123 is a function to cut off the power supply to prevent damage to electronic devices due to a short circuit when water flows into the hull 110 or the multi-function unit 120 due to the damage of the floating drone 100 You can also have additional.

The power connection terminals 124 are terminals for transmitting the power of the battery 122 to the hull 110, and are installed to be exposed to the outer surface of the multifunctional unit 120. A power connection terminal 124 is also provided on the lower surface of the hull 110 facing the power connection terminal 124 and is in close contact with each other to be electrically connected.

Although two power connection terminals 124 are shown in FIG. 2, when the power control unit 123 generates voltages and currents of various sizes according to the rated voltage and rated current of each electronic device, more power connection terminals 124 May be provided.

The sensor mounting unit 125 is a module to which the first sensor unit 130 measuring underwater environment data is coupled.

The data interface terminal 128 is a terminal for transmitting the data measured by the first sensor unit 130 to the hull 110. Like the power connection terminal 124, a data interface terminal is provided on the lower surface of the hull 110 facing the data interface terminal 128 and is in close contact with each other to be electrically connected.

The first sensor unit 130 may be detachable from the sensor mounting unit 125 and includes at least one of a temperature sensor, a depth sensor, a salinity sensor, a pH sensor, and a flow rate sensor.

On the other hand, even if the hull 110 operates one, the multi-function unit 120 can operate a plurality. For example, when a plurality of multi-function units 120 are operated, the multi-function unit 120, which operates normally even if some of the multi-function units 120 are broken or discharged, can be mounted and used directly on the hull 110, so that operation efficiency Can increase. In addition, sensors provided in the first sensor unit 130 of each multi-function unit 120 may be installed in various combinations so that a multi-function unit 120 suitable for use may be mounted on the hull 110 and used.

As such, the battery 122 in the present invention is used for two purposes. That is, the battery 122 not only supplies power to the surface drone 100, but also contributes to improving the postural stability and resilience of the hull.

The principle of improving the resilience of the surface drone 100 by using the battery 122 will be described with reference to FIG. 3.

3 is a view showing a water drone with improved resilience by the multifunctional unit of FIG. 2.

(a) is a front view of a surface drone in a balanced position, and (b) is a front view of a surface drone in which a battery is not installed in the multifunctional part and is inclined at a certain angle by external force. In addition, (c) is a front view of a water drone with a battery installed in the multifunctional part and tilted at a certain angle, and (d) is a front view of a surface drone with a battery installed in the multifunctional part and turned 180°.

First, looking at (a), since the gravity acting vertically downward from the center of the surface drone 100 and the buoyancy acting vertically upward act in opposite directions with the same force on the same vertical line, the surface drone 100 is Keeping the balance.

The state shown in (a) is an ideal state, and it is difficult to substantially maintain the state of (a) in a marine environment where waves are constantly generated.

G denotes the center of gravity of the water drone 100, B denotes the buoyancy center (center) of the water drone 100, and K denotes the keel. The keel is a structural member installed in the longitudinal direction on the center line of the lowermost part of the ship, and is a part that forms the basis of the longitudinal structure of the hull from the bow member to the stern member along the center line of the ship. Here, the keel is located on the lowermost surface of the water drone 100.

(b) shows a state in which the water drone 100 in which the battery is not installed in the multi-function unit 120 is inclined at a certain angle by an external force such as wind or waves.

M represents the metacenter, and indicates the point where the line of action of buoyancy force intersects the line of action of buoyancy when the ship is inclined.

Hereinafter, the distance between the keel (K) and the center of gravity (M) will be defined as KM, and the distance between the keel (K) and the center of gravity (G) will be defined as KG. In order to have resilience when the surface drone 100 is inclined by external force, it must satisfy KM>MG. If, as in (b), the buoyancy center (B) moves and becomes KM<KG, the surface drone 100 is likely to overturn due to the rotational force acting in the opposite direction.

Looking at (c), by arranging the battery 122 at the bottom of the multi-function unit 120 of the water drone 100, the center of gravity (G) was moved in the direction of the keel (K) compared to (b). Accordingly, even if the buoyancy center (B) moves because the surface drone 100 is inclined at a certain angle, the KM>KG condition can be satisfied, so that a restoring force acts on the surface drone 100 to return to the state (a). .

Looking at (d), when the surface drone 100 is completely turned 180°, gravity and buoyancy act in a straight line and the resilience is 0, but the tide or wind acts as an initial external force, causing the surface drone 100 to slightly Even if it shakes, the condition is KM>KG and the hull is restored to its original posture. However, in actual sea, minute waves on the surface of the water are constantly generated and can act as an initial external force, and the inertial force while the surface drone 100 is overturned can also act as an initial external force, so that the surface drone 100 of the present invention is substantially tilted. It can be said that it always has a resilience regardless of the angle of loss.

In this way, in order to always have a resilience regardless of the angle at which the water drone 100 according to the present invention is inclined, the battery 122 disposed in the multifunctional unit 120 always satisfies the KM>KG condition regardless of the angle. )'S placement position and weight are adjusted. Of course, it would be desirable to place the battery 122 at the bottom of the multi-function unit 120. In addition, it is possible to increase the weight by disposing a plurality of batteries 122 to satisfy the condition KM>KG.

However, as a result of the simulation, if a sufficient center of gravity (G) movement effect cannot be obtained even if several batteries 122 are placed at the bottom of the multifunction unit 120, an image processing device or a communication device disposed on the hull 110, etc. It may be arranged to move to the multi-function unit 120.

The multifunctional unit 120, which plays an important role in the posture stability of the water drone 100, may be detachably attached to the hull 110, as shown in FIG. 4.

The surface drone 100 is equipped with many electronic devices for collecting and communicating data on aquaculture monitoring missions and atmospheric and underwater environments, and thus has considerable volume and weight. Therefore, it is possible to distribute the volume and weight by the separation of the hull 110 and the multi-function unit 120, it is possible to facilitate transportation and storage. However, when operating at sea, since the hull 110 and the multi-function module 120 operate in a combined state, the coupling portion of the hull 110 and the multi-function module 120 must be tightly contacted so that water does not permeate into the coupling portion. do.

As described above, the water drone 100 collects underwater environment data using the first sensor unit 130 of the multifunctional unit 120. The underwater environment data that the water drone 100 can measure include water temperature, depth, salinity, pH, and flow rate.

Hereinafter, a method for measuring the depth of the water drone 100 according to the present invention will be described with reference to the drawings.

5 is a diagram for explaining a method of measuring the water temperature of a target depth by a water drone according to an embodiment of the present invention, and FIG. 6 is an artificial intelligence neural network that is learned to find out the water temperature of the target depth using a plurality of parameters. It is a diagram showing an example of.

The first sensor unit 130 of the multifunction unit 120 includes a temperature sensor.

As shown in FIG. 5, when there is a depth error between the sensor location depth at which the temperature sensor of the first sensor unit 130 is located and the target depth to measure the water temperature, in general, a mechanical arm, a wire, etc. After lowering the temperature sensor to the target depth, measure the water temperature.

However, in the present invention, a method of indirectly determining the water temperature of a target depth is proposed by fixing the position of the temperature sensor and using other parameters as input values using an artificial intelligence neural network. The input parameters include data measured by the first sensor unit 130 and the second sensor unit 160.

Before mounting the artificial intelligence neural network on the surface drone 100, a learning model that learns various input parameters and a large number of data on the water temperature of the target depth must be constructed. For example, the water temperature of the sensor location depth measured by the first sensor unit 130 and the air temperature, illuminance, humidity, air volume measured by the second sensor unit 160, and the water temperature and measurement time of each target depth The artificial intelligence neural network is trained by measuring at various points on the sea.

Referring to FIG. 6, the water temperature of the sensor location depth measured through the first sensor unit 130 is input to the input layer 182 of the artificial intelligence neural network, and the temperature, illuminance measured through the second sensor unit 160, and When the measurement time is input together with the humidity and air volume, the hidden layer 184 finds out the water temperature of the target depth based on the learned result using these parameters. Then, the water temperature of the target depth is output through the output layer 186.

On the other hand, the water drone 100 according to an embodiment of the present invention may perform a farm monitoring by using the image collection unit 140.

Since farm facilities are constantly exposed to sea water, they may be corroded and damaged by salt or damaged by external forces such as storms and thus lost. In addition, theft of farmed seafood such as sea cucumber and abalone occurs frequently. Therefore, it is important to monitor the farm to ensure timely facility maintenance or private property. However, since the consumption of manpower is too great for humans to directly monitor the farm, much more efficient monitoring is possible when monitoring using the aquatic drone 100.

7 is a diagram schematically showing that a water drone according to an embodiment of the present invention autonomously performs aquaculture monitoring.

As shown, a plurality of way-points (W1 to W4) are set around the farm 200.

The surface drone 100 operates autonomously using satellite communication, and passes through set transit points (W1 to W4). At this time, an external image is captured to monitor for abnormalities.

The surface drone 100 receives location information in real time using a Global Positioning System (GPS) based on a Global Navigation System (GNSS) and operates autonomously in an accurate route.

Figure 8 is a flow chart showing a method for monitoring aquaculture farm by a water drone according to the present invention.

When a farm monitoring start signal comes from the control terminal or the control center, the water drone navigates around the farm and acquires external images with a camera in step S310.

In step S320, the acquired image data is temporarily stored. The storage device provided in the surface drone consists of a temporary storage device and a permanent storage device, and the image data first captured by the surface drone is stored in the temporary storage device. The temporary storage device is a space that is automatically deleted in the order of data stored first when the storage capacity is full, and may be set to be automatically deleted after a certain period of time.

In step S330, the image processing device on the ship simplifies the image data.

The simplification process can go through several processes. For example, pixels at both extremes of the Gaussian distribution, that is, pixels in the low-frequency and high-frequency regions, can be removed with a Gaussian filter, leaving only the pixels in the middle region. In addition, the image may be smoothed by removing a high-frequency component having a large gradation change rate among pixel values using a smooth filter. For example, in the captured image data, since the light reflection area has a large change in grayscale with the surrounding area, removing such a part may smooth the image as a whole. Consequently, the Gaussian filter and the filter is smooth and simplify the data by reducing the amount of image data.

In addition, image data may be simplified by reducing the number of gradations of pixels constituting the image. For example, when the number of grayscales of each pixel is 16, reducing the number of grayscales to 2 greatly reduces the capacity of image data.

The reason for performing the step S330 is to prevent a decrease in image processing speed by reducing the capacity of the image data. However, if the processing speed of the image processing apparatus is fast enough to process a large amount of data, the process of simplifying the image data may be skipped and step S340 may be immediately performed.

In step S340, a change amount is calculated by comparing a reference image and a current (N) frame image. Here, the reference image may be a previously stored image or a previous frame image. N is a natural number. In addition, the amount of change may indicate the number of pixels changed in the current frame image compared to the reference image.

In step S350, when the image change amount calculated in step S340 is greater than a preset threshold, an alarm is transmitted to the terminal. On the other hand, when the amount of image change is less than the threshold, the monitoring activity is maintained. The large change in the current frame image compared to the reference image indicates that the farm facilities were damaged, lost, or a suspicious person invaded.

In step S370, when an abnormality is detected in the current (N) frame image, the N-M frame image data is permanently stored. M is a natural number greater than or equal to 1.

In order to accurately observe the process of loss of farm facilities or the process of intruders entering the farm, it must be stored before a certain frame (M) of the frame where an abnormality is detected.

The step of transmitting an alarm to the terminal (S360) and the step of selectively permanently storing the image data (S370) may be performed simultaneously.

In step S380, when the user who receives the alarm requests the video through the terminal, the floating drone streams the permanently stored video data to the terminal.

9 is a diagram illustrating examples of image data to aid in the description of FIG. 8.

(a) shows the reference image of the farm for comparison with the image image captured by the image collection unit of the water drone.

(b) shows a part of the left side of the first object, which is one of the facilities of the farm, was damaged and lost. When comparing the reference image of (a) and the frame image of (b), it can be seen that only some pixels on the left of the first object have changed.

Since the image processing apparatus of a floating drone according to the present invention has changed only a small number of pixels than a set threshold, it is determined that it is a loss of a degree that does not affect the function of the farm and does not send a notification to the terminal.

(c) shows a state in which the first object OB1 is completely lost. When comparing the reference image of (a) and the frame image of (c), a large number of pixels are changed to exceed the threshold. In this case, the N-M frame image data is permanently stored and an alarm is sent to the terminal.

In (d), the second object (OB2), that is, an intruder invading the farm is shown.

When a person invades the farm, the number of pixels changes according to the area of the person, so the amount of change in the image exceeds the threshold value, and the water drone determines that the farm facility is lost or a person intrudes and sends an alarm to the terminal. do.

As described above, since the water drone according to an embodiment of the present invention adjusts the position and weight of the battery disposed in the multifunctional part coupled to the lower part of the hull to always satisfy KM>KG, regardless of the inclination angle of the water drone You will always have resilience. In other words, the battery provided to supply power to the surface drone is also used as a weight, contributing to the improvement of the attitude stability and resilience of the surface drone.

In addition, the water drone according to an embodiment of the present invention can be easily transported and stored by dispersing the volume and weight of the water drone because the multifunctional part including batteries and sensors can be attached to the hull.

In addition, the water drone according to an embodiment of the present invention compares the image data captured by the camera with reference data, determines whether there is an abnormality in the farm according to the amount of change, and selectively selects only image data including the section in which the abnormality is detected. By permanent storage, limited storage space can be used efficiently.

100: water drone 110: hull
120: multi-function unit 130: first sensor unit
140: image collection unit 142: camera
144: gimbal 146: guard
150: antenna 160: second sensor unit

Claims (6)

As a method of monitoring aquaculture using a water drone,
The steps of acquiring images while navigating around the farm,
Temporarily storing the acquired image data, and
Computing the amount of change by comparing the reference image and the current frame image, and
When the amount of change is greater than a threshold value, determining as an abnormal state and transmitting an alarm to the terminal;
Permanently storing image data from a predetermined frame before the frame in which an abnormality is detected; and
Including the step of estimating the water temperature of the target depth by receiving the water temperature measured by the first sensor unit of the water drone and the atmospheric environment data measured by the second sensor unit,
The first sensor unit is located at the bottom of the surface drone, and the second sensor unit is installed on the hull of the surface drone to be exposed above sea level,
In the estimating of the target depth water temperature, the water temperature of the sensor position depth measured by the first sensor unit, the air temperature, illuminance, humidity, air volume measured by the second sensor unit, and the water temperature and measurement time of each target depth Using artificial intelligence neural networks How to monitor aquaculture using a surface drone. The method of claim 1,
Before the step of comparing the reference image and the current frame image to calculate a change amount,
The method of monitoring a farm using a water drone further comprising the step of reducing and simplifying the data capacity by processing the acquired image data. The method of claim 2,
The image data processing is to filter the image data obtained using a Gaussian filter and a smooth filter. The method of claim 1,
The reference image is a pre-stored image or a previous frame image, a farm monitoring method using a water drone. The method of claim 1,
The amount of change indicates the number of pixels changed between the reference image and the current frame image. The method of claim 1,
A farm monitoring method using a water drone to stream permanently stored image data to the terminal upon request of the terminal.

Images