KR20220039373A - Smart pigsty system and pigsty monitoring method using the same - Google Patents

Abstract

The present invention relates to a smart barn system for providing intelligent monitoring as to livestock raised in a barn. The system includes: imaging devices provided in the barn and generating a captured image; and a monitoring server performing image recognition as to the captured image to detect whether a predetermined event has occurred with respect to livestock in the barn, generating event data as to an event that has occurred, and generating statistical information with respect to the event data. According to the present invention, an abnormal animal behavior event is detected and a change in body weight is detected based on learning-based image analysis. Accordingly, an abnormal animal behavior in a barn can be monitored more accurately and intelligently.

Description

Smart livestock system and livestock monitoring method using the same {SMART PIGSTY SYSTEM AND PIGSTY MONITORING METHOD USING THE SAME}

The present invention relates to a smart livestock system and a livestock monitoring method using the same.

With the development of IT technology and image recognition technology, automation systems are being applied in various environments. As a part of it, development of the monitoring field for the livestock industry is being made.

Looking at the trend of conventional livestock monitoring technology for livestock, a system that manages information on individual livestock and production history using RFID (Radio Frequency Identification), and a temperature sensor provided in the livestock are used to monitor the temperature of livestock. There is a system for detecting and judging the presence or absence of disease in livestock.

However, since these conventional techniques are systems based on deriving a specific situation set in advance, there is a problem in that it is difficult to monitor various situations of the livestock.

Therefore, there is a need for a smart livestock system capable of intelligent monitoring based on the overall analysis of the livestock house.

Korean Patent Publication No. 2010-0001011

One technical aspect of the present invention is to solve the problems of the prior art, by detecting an abnormal behavior event of an animal based on a learning-based image analysis and detecting a change in weight, thereby preventing abnormal behavior of animals in a barn. It is to provide a smart livestock barn system that can monitor more accurately and intelligently and a livestock barn monitoring method using the same.

In addition, a technical aspect of the present invention is a smart livestock system that can accurately monitor animals in a livestock barn by creating a learning database for animal objects and event data and analyzing it based on statistical information, and a livestock barn using the same To provide a monitoring method.

In addition, one technical aspect of the present invention is a smart livestock system that can more accurately estimate the weight change of an animal by acquiring a flat image and a side image of an animal and more accurately estimating the volume of the animal based on it, and It is to provide a livestock monitoring method used.

The above objects and various advantages of the present invention will become more apparent from preferred embodiments of the present invention by those skilled in the art.

One technical aspect of the present invention proposes a smart livestock barn system. The smart livestock system is a smart livestock system that provides intelligent monitoring for livestock raised in a livestock barn, and performs image recognition on a plurality of imaging devices provided in the livestock bar to generate a captured image and the captured image, It may include a monitoring server that detects whether a predetermined event for livestock existing in the livestock has occurred, generates event data for the generated event, and generates statistical information on the event data.

In an embodiment, the monitoring server may self-learning based on the generated statistical information to reset the occurrence criteria of the event.

In one embodiment, the monitoring server performs image recognition on the captured image, detects the occurrence of an event with respect to the livestock existing in the livestock, and an event detection unit that generates the event data when the event occurs; It may include a statistical information management unit that generates statistical information on the event data, and resets the occurrence criteria of the event by self-learning based on the generated statistical information.

In one embodiment, the event detection unit, when the amount of action of the livestock increases or decreases, a behavior change event, if there is no action of the livestock, a no-action event, when the livestock repeats a specific action, a behavior repeat event, the livestock is standing Postural event when a specific posture is taken including posture, supine posture, sitting posture and knee posture A disease infection event can be generated when a disease infection for a livestock individual is estimated based on the event.

In one embodiment, the statistical information management unit, as abnormal behavior statistics, each individual activity amount, average behavior amount, inaction time, specific behavior repetition number and time, standing posture, lying posture, sitting posture, and specific including knee posture Statistical information on the number of times per posture, duration for a specific posture, and total posture maintenance time can be generated.

In one embodiment, the event detection unit, based on the external information data of the livestock, the image recognition module for detecting the livestock area in the captured image, the action or inaction of the livestock based on the change in the livestock area in the continuous captured image It may include a behavior analysis module for generating a behavior-related event for the livestock based on the detected behavioral detection module and the detected behavior or non-action of the livestock.

Another technical aspect of the present invention proposes a livestock monitoring method. The livestock monitoring method is a livestock monitoring method performed in a monitoring server that provides intelligent monitoring for livestock raised in the livestock by interworking with a plurality of imaging devices provided in the livestock, and by performing image recognition on the captured image, Detecting whether a predetermined event has occurred for livestock existing in the barn, generating event data for the generated event and generating statistical information for the event data, and self-learning based on the generated statistical information It may include the step of resetting the occurrence criteria of the event.

In one embodiment, the step of detecting whether the event has occurred, generating a behavior change event when the behavior amount of the livestock increases or decreases, generating a non-action event when there is no behavior of the livestock, the livestock Generating an action repetition event when a specific action is repeated, generating a posture event when the livestock takes a specific posture including a standing posture, a lying posture, a sitting posture and a knee posture, the weight of the livestock increases or decreases When a disease infection to a livestock individual is estimated based on the abnormal behavior event and weight change event generated for the livestock, generating a disease infection event is performed at least one of the steps of: can

In one embodiment, the step of detecting whether the event has occurred may include detecting a livestock area in a captured image based on the external information data of the livestock, a behavior of livestock based on a change in the livestock area in a continuous captured image, or A method for monitoring a livestock house comprising the steps of detecting non-action and generating a behavior-related event for the livestock based on the detected behavior or non-action of the livestock.

In an embodiment, the generating statistical information for the event data includes, as abnormal behavior statistics, activity amount for each individual, average behavior amount, inaction time, specific behavior repetition number and time, standing posture, lying posture, sitting posture and generating statistical information on the number of times for each specific posture including the knee posture, the duration for the specific posture, and the total posture maintenance time.

The means for solving the above-described problems do not enumerate all the features of the present invention. Various means for solving the problems of the present invention may be understood in more detail with reference to specific embodiments in the following detailed description.

According to an embodiment of the present invention, there is an effect of more accurately and intelligently monitoring the abnormal behavior of the animal in the barn by detecting the abnormal behavior event of the animal based on the learning-based image analysis and detecting the change in weight. there is.

In addition, according to an embodiment of the present invention, by creating a learning database for animal object and event data and analyzing it based on statistical information, there is an effect that accurate monitoring of animals in the barn can be performed.

In addition, according to an embodiment of the present invention, there is an effect of more accurately estimating a change in the weight of an animal by acquiring a plane image and a side image of the animal and estimating the volume of the animal more accurately based on the obtained plane image and side image.

1 is a view for explaining an application example of a smart livestock barn system according to an embodiment of the present invention.
2 is a diagram illustrating an exemplary computing operating environment of a monitoring server according to an embodiment of the present invention.
3 is a block diagram illustrating a monitoring server according to an embodiment of the present invention.
FIG. 4 is a block diagram illustrating an embodiment of the event detection unit shown in FIG. 3 .
5 to 6 are diagrams for explaining the operation of the body area analysis module shown in FIG.
FIG. 7 is a block diagram illustrating another example of the event detection unit shown in FIG. 3 .
8 to 9 are diagrams illustrating examples of a monitoring screen provided by a smart livestock barn system according to an embodiment of the present invention.
10 is a flowchart illustrating a method for monitoring a livestock house using a smart livestock barn system according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings.

However, the embodiment of the present invention may be modified in various other forms, and the scope of the present invention is not limited to the embodiments described below. In addition, the embodiments of the present invention are provided in order to more completely explain the present invention to those of ordinary skill in the art.

That is, the above-described objects, features and advantages will be described later in detail with reference to the accompanying drawings, and accordingly, a person of ordinary skill in the art to which the present invention pertains will be able to easily implement the technical idea of the present invention. In describing the present invention, if it is determined that a detailed description of a known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description will be omitted. Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings. In the drawings, the same reference numerals are used to indicate the same or similar components.

Also, as used herein, the singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as “consisting of” or “comprising” should not be construed as necessarily including all of the various components or various steps described in the specification, some of which components or some steps are It should be construed that it may not include, or may further include additional components or steps.

In addition, various components and sub-components thereof are described below in order to describe the system according to the present invention. These components and sub-components thereof may be implemented in various forms, such as hardware, software, or a combination thereof. For example, each element may be implemented as an electronic configuration for performing a corresponding function, or may be software itself operable in an electronic system or implemented as a functional element of such software. Alternatively, it may be implemented with an electronic configuration and corresponding driving software.

The various techniques described herein may be implemented with hardware or software, or a combination of both, where appropriate. As used herein, terms such as "Unit", "Server" and "System" likewise refer to computer-related entities, i.e. hardware, a combination of hardware and software, software or It can be treated as equivalent to software at the time of execution. In addition, each function executed in the system of the present invention may be configured in units of modules, and may be recorded in one physical memory, or may be recorded while being dispersed between two or more memories and recording media.

Although various flowcharts are disclosed to describe the embodiments of the present invention, this is for convenience of description of each step, and each step is not necessarily performed according to the order of the flowchart. That is, each step in the flowchart may be performed simultaneously with each other, performed in an order according to the flowchart, or may be performed in an order opposite to the order in the flowchart.

Hereinafter, a smart livestock system and a livestock livestock monitoring method using the same according to some embodiments of the present invention will be described.

1 is a view for explaining an application example of a smart livestock barn system according to an embodiment of the present invention.

Referring to FIG. 1 , the smart livestock house system is based on a plurality of imaging devices 100 provided in the barn 1 and image recognition for the captured image provided from the imaging device 100, It may include a monitoring server 300 that provides intelligent monitoring for the livestock 10 .

The monitoring server 300 is connected to the plurality of imaging devices 100 through the network 2 . Here, the network 2 is not particularly limited, and according to an embodiment, the network 2 may be implemented as an intranet interconnected only internally, or the network 2 may be implemented using the Internet connectable to the outside. may be implemented.

The monitoring server 300 may detect whether a predetermined event has occurred with respect to the livestock 10 existing in the livestock 1 by performing image recognition on the captured image provided from the imaging device 100 . When an event occurs, the monitoring server 300 may generate event data for it.

For example, the monitoring server 300 may detect a change in the amount of behavior of the livestock 10 or detect a change in weight. Alternatively, the monitoring server 300 may determine whether the livestock 10 is ill based on the change in the behavior and weight of the livestock 10 .

Here, when a separate modifier is not applied, the captured image collectively means the captured image for image analysis. Accordingly, the captured image does not mean one image itself, but may include moving pictures continuously provided by the image capturing device. In addition, it is possible to collectively represent the captured images respectively provided by the plurality of imaging devices.

The monitoring server 300 may manage the above-described event data as a database and generate statistical information therefor. The monitoring server 300 may detect an event for the livestock 10 by using the generated statistical information again for monitoring.

1 illustrates a pig as an example of the livestock 10, but is not limited thereto, and the present system is applicable to a barn of various livestock 10 such as cattle, ducks, and chickens.

Hereinafter, various embodiments of the monitoring server 300 will be described in more detail with reference to FIGS. 2 to 9 .

2 is a diagram illustrating an exemplary computing operating environment for implementing the monitoring server 300 according to an embodiment of the present invention.

2 is intended to provide a general and simplified description of a suitable computing environment in which embodiments of a monitoring server may be implemented. Referring to FIG. 2 , as an example of a monitoring server 300 , a computing device, which is a block diagram of an exemplary computing operating environment for smart monitoring, is shown.

The computing device may be any computing device executing an application for providing pre-built monitoring for a logical scenario in a database program according to embodiments, and may include at least a processing unit 203 and a system memory 201 . there is.

A computing device may include a plurality of processing units that cooperate in executing a program. Depending on the exact configuration and type of computing device, system memory 201 may be volatile (eg, RAM), non-volatile (eg, ROM, flash memory, etc.), or a combination thereof. The system memory 201 includes a suitable operating system 202 for controlling the operation of the platform, such as the WINDOWS operating system from Microsoft Corporation. System memory 201 may include one or more software applications, such as program modules, applications, and the like.

The computing device may have additional features or functionality. For example, the computing device may include additional data storage devices 204 such as magnetic disks, optical disks, or tape. Such additional storage may be removable storage and/or fixed storage. Computer readable storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for stored information such as computer readable instructions, data structures, program modules, or other data. The system memory 201 and the storage 204 are only examples of computer-readable storage media. A computer readable storage medium may include RAM (RAM), ROM (ROM), EEPROM, flash memory or other memory technology, CD-ROM, DVD or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage device, or any desired It may include, but is not limited to, any other medium that stores information and that can be accessed by computing device 200 .

input devices 205 of computing devices, such as keyboards, mice, pens, voice input devices, touch input devices, and comparable input devices. Output devices 206 may include, for example, displays, speakers, printers, and other types of output devices. Since these devices are widely known in the art, detailed descriptions thereof will be omitted.

A computing device may include a communication device 207 that allows the device to communicate with other devices via networks 20, such as wired and wireless networks, satellite links, cellular links, local area networks, and comparable mechanisms, such as in a distributed computing environment, for example. may include Communication device 207 is one example of a communication medium, which may include computer readable instructions, data structures, program modules, or other data therein. Illustratively, communication media includes, but is not limited to, wired media such as a wired network or direct connection connection, and wireless media such as acoustic, RF, infrared, and other wireless media.

3 is a block diagram illustrating a monitoring server according to an embodiment of the present invention.

Referring to FIG. 3 , the monitoring server 300 may include an event detection unit 310 , a statistical information management unit 320 , a database 330 , and a monitoring management unit 340 .

The event detection unit 310 may perform image recognition on the captured image provided from the image capturing device 100 to detect whether an event has occurred with respect to the livestock 10 existing in the livestock house 1 .

In an embodiment, the event detection unit 310 may analyze the behavior of the livestock 10 in the captured image and detect an abnormal behavior of the livestock 10 .

For example, the event detecting unit 310 may generate a behavioral change event when the behavioral amount of the livestock 10 is increased or decreased.

As another example, the event detection unit 310 may generate a non-action event when there is no action of the livestock 10 . Alternatively, when the livestock 10 repeats a specific action (a specific posture), a repetitive action event may be generated.

As another example, the event sensor 310 may generate a posture event when the livestock 10 takes a specific posture (standing posture, lying posture, sitting posture, knee posture, etc.).

In an embodiment, the event detection unit 310 may estimate the volume of the livestock 10 using the captured image, and calculate the weight of the livestock 10 using the analyzed volume. The event sensing unit 310 may generate a weight change event for the increase or decrease in the weight of the livestock.

In an embodiment, the event detection unit 310 may generate a disease infection event when a disease infection of a livestock individual is estimated based on an abnormal behavior event and a weight change event generated for the livestock.

In one embodiment, in order to individually identify a livestock entity, each livestock may be provided with a visual identification tag. For example, a visual code for identifying the livestock may be provided on the upper right forefoot of each livestock, and the event detection unit 310 may identify each individual of the livestock by identifying the visual code.

The event detection unit 310 provides data on the behavior or weight of the livestock 10 as event data to the statistical information management unit 320 , and the statistical information management unit 320 manages these event data as the database 330 . can

The statistical information management unit 320 may generate statistical information for event data stored in the database 330 .

For example, the statistical information management unit 320 is abnormal behavior statistics for the livestock 10, each individual activity amount, average behavior amount, time without movement (action), the number and time of repetition of a specific action, a specific posture (standing posture) , lying posture, sitting posture, knee posture, etc.) can generate statistical information for each number, duration for a specific posture, and total posture maintenance time.

As another example, the statistical information management unit 320 may generate statistical information on weight or weight change for each individual livestock 10, or generate statistical information on the possibility of disease infection based on abnormal behavior and weight change. can

The event occurrence criteria may be reset by using the statistical information generated by the statistical information management unit 320 . For example, the event detection unit 310 may detect an abnormal behavior for a specific livestock entity based on the number of repetitions of the specific behavior determined to have occurred and the specific posture and time of the specific posture. The statistical information management unit 320 may reset the number of repetitions of the specific action, the specific posture, and the time of the specific posture based on the statistical information. The statistical information management unit 320 may set a critical value that can be determined as a statistically abnormal state for each event, and reset the number of repetitions of a specific action, a specific posture, and the time of a specific posture according to the critical value. there is.

For example, the statistical information management unit 320 may configure statistical information (eg, an average of 0.2 times per minute) for a specific action (eg, hitting something with the head), and based on this statistical information A threshold value (eg, the top 3% of the normal distribution by standard deviation) may be set, and a case exceeding the threshold value (eg, 20 times per minute) may be set as the event occurrence criterion.

In this way, the statistical information management unit 320 resets the event occurrence criteria using statistical data, thereby increasing the accuracy of event detection and a smart method based on self-learning without additional intervention by the user. This can have the effect of increasing the accuracy of event detection.

The monitoring management unit 340 may perform comprehensive monitoring of the livestock house 1 based on the event data provided from the event detection unit 310 and the statistical information provided from the statistical information management unit 320 .

The monitoring management unit 340 may provide monitoring data to a user terminal (not shown) connected to the monitoring server 300 .

Here, the user terminal (not shown) is a computing device that provides livestock monitoring to the user by accessing the user terminal 100 through a network to the monitoring server 300, and includes a Personal Communication System (PCS), a Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W- Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminals, smartphones, smartpads, tablet PCs, etc. all kinds of handheld-based wireless communication devices and stationary PCs , a device including a computing device such as a notebook computer may be used.

When an event or statistics set as an abnormal situation occurs during monitoring, the monitoring management unit 340 may provide an alarm about the abnormal situation to the user terminal.

The monitoring management unit 340 may provide the statistical information generated by the statistical information management unit 320 to the user terminal.

8 to 9 are diagrams showing examples of monitoring screens provided by the smart livestock barn system according to an embodiment of the present invention. As shown in the example shown in FIG. 8, the monitoring management unit 340 is statistical information can be provided to the user. Alternatively, as shown in FIG. 9 , statistics on posture and number of posture changes may be provided to the user.

FIG. 4 is a block diagram illustrating an embodiment of the event detection unit shown in FIG. 3 .

Referring to FIG. 4 , the event detection unit 310 includes an image recognition module 311 , a behavior detection module 312 , a behavior analysis module 313 , a body area analysis module 314 , and a weight change detection module 315 . may include

The image recognition module 311 may detect the livestock region from the captured image based on the external information data of the livestock. To this end, the image recognition module 311 may be provided with external information data about the livestock photographed at each angle in advance.

The behavior detection module 312 may detect the behavior or non-action of the livestock based on the change in the livestock area in the continuous captured images.

The behavior analysis module 313 may generate a behavior-related event for the livestock based on the behavior or non-action of the livestock detected by the behavior detection module 312 .

For example, the behavior analysis module 313 may generate a behavior change event when the behavior amount of the livestock increases or decreases, a non-action event when the behavior of the livestock is absent, a behavior repeat event when the livestock repeats a specific behavior, and a standing animal Posture events can be generated when certain postures are taken, including postures, supine postures, sitting postures, and knee postures.

The body area analysis module 314 may analyze the body area of individual livestock.

5 to 6 are diagrams for explaining the operation of the body area analysis module shown in FIG. 4 . Hereinafter, the body area analysis module 314 will be described with further reference to FIGS. 5 to 6 .

Also, in the following description, an imaging device is configured to acquire a side image and a planar image with respect to a livestock object, and the body area of the livestock object is analyzed using the side image and the planar image. However, this is an example, and if images taken from different angles orthogonal to each other are used, the body area may be calculated according to a method to be described later.

The body area analysis module 314 may calculate the pixel area of the livestock area in the side image and the planar image.

5 and 6, Figure (a) shows a captured image of the side of the pig, Figure (b) shows a captured image of the plane of the pig, and in each captured image, the image recognition module 311 can identify the pig area, which corresponds to the blacked out area.

The body area analysis module 314 may sum the number of pixels corresponding to the pig region in the planar image for each column (S610), and may also add the number of pixels corresponding to the pig region in the side image for each column (S620) .

Thereafter, the animal volume may be calculated using Equation 1 below ( S630 ).

[Equation 1]

는 단면적-체적 상수로서, 가축의 종류마다 다르게 설정될 수 있다.Here, a _i is the number of pixels corresponding to the pig area in column i in the planar image, and b _i is the number of pixels corresponding to the pig area in column i in the side image.

is a cross-sectional area-volume constant, and may be set differently for each kind of livestock.

In the case of calculation as in Equation 1, the sum of the cross-sectional areas in each row may be summed, and the cross-sectional area-volume constant may be reflected thereto to calculate the volume of the livestock.

According to this calculation, it is possible to accurately calculate the volume of the livestock from the image.

The weight change detection module 315 may receive the volume of the livestock from the body area analysis module 314 and calculate the weight of the livestock by reflecting the volume-weight weight thereon. The volume-weight weight is set so that the weight increases as the volume increases. In addition, the volume-weight weight may be set differently for each kind of livestock.

The weight change detection module 315 may generate an event related to the weight of the livestock by using the calculated weight of the livestock. For example, when the weight of the livestock increases or decreases, the weight change detection module 315 may generate a weight change event for the corresponding livestock.

FIG. 7 is a block diagram illustrating another example of the event detection unit illustrated in FIG. 3 .

Referring to FIG. 7 , the event detection unit 311 includes an image recognition module 311 , a behavior detection module 312 , a behavior analysis module 313 , a body area analysis module 314 , a weight change detection module 315 and It may include a disease determination module 316 .

Since the image recognition module 311 to the weight change detection module 315 can be easily understood from the description described above with reference to FIG. 4 , the description thereof will not be repeated and will be omitted herein.

The disease determination module 316 may determine whether the livestock is diseased by interworking with the behavior detection module 312 and the behavior analysis module 313 . In this embodiment, the disease determination module 316 may include at least one function of the behavior analysis module 313 or the weight change detection module 315 .

Alternatively, the disease determination module 316 may determine whether the livestock is diseased, based on the behavior-related event generated by the behavior analysis module 313 and the weight-related event generated by the weight change detection module 315 .

As an example, the disease determination module 316 determines that the amount of activity of a livestock individual is less than a threshold, a specific posture is maintained for a critical time or more, and when it is determined that the weight of the livestock individual is reduced by more than a critical weight within a standard time, the corresponding livestock is A disease state may be determined and a disease infection event may be generated.

Alternatively, the determination criterion of the disease determination module 316 may be changed according to a disease. For example, the disease determination module 316 may determine that a disease including mental pathology has occurred in the livestock and generate a disease infection event when the livestock continuously repeats a specific action for a threshold number or more for a unit time. .

In the above, various embodiments of the smart livestock system have been described with reference to FIGS. 1 to 9 .

Hereinafter, a method for monitoring a livestock house using a smart livestock barn system according to an embodiment of the present invention will be described with reference to FIG. 10 .

Since the method for monitoring a livestock house using the smart livestock system to be described below is performed based on the smart livestock system described above with reference to FIGS. 1 to 9, it can be more easily understood with reference to the above description.

10 is a flowchart illustrating a method for monitoring a livestock house using a smart livestock barn system according to an embodiment of the present invention.

Referring to FIG. 10 , the monitoring server 300 may perform image recognition on the captured image to detect whether a predetermined event for livestock existing in the livestock has occurred ( S1010 ).

The monitoring server 300 may generate event data for the generated event and generate statistical information about the event data (S1020).

The monitoring server 300 may self-learning based on the generated statistical information to reset the event occurrence criteria (S1030).

In one embodiment for step S1010, the monitoring server 300, when the amount of action of the livestock increases or decreases, generating a behavior change event, if there is no action of the livestock, generating a non-action event, the livestock is a specific action repeating to generate a repeating event; generating a postural event when the livestock assumes specific postures including standing, supine, sitting and kneeling postures; generating a postural event when an animal gains or loses weight At least one of the steps of generating a weight change event for the livestock and generating a disease infection event when the disease infection of the livestock individual is estimated based on the abnormal behavior event and the weight change event generated for the livestock may be performed.

In an embodiment for step S1010, the monitoring server 300 may detect the livestock area from the captured image, based on the external information data of the livestock. The monitoring server 300 detects the behavior or non-action of the livestock based on the change in the livestock area in the continuous captured image, and generates a behavior-related event for the livestock based on the detected behavior or non-action of the livestock. can

In one embodiment for step S1020, the monitoring server 300, as abnormal behavior statistics, each individual activity amount, average behavior amount, inaction time, specific behavior repetition number and time, standing posture, lying posture, sitting posture and knee Statistical information on the number of times for each specific posture including the posture, the duration for the specific posture, and the total posture maintenance time may be generated.

The present invention described above is not limited by the above-described embodiments and the accompanying drawings, but is limited by the claims described below, and the configuration of the present invention may vary within the scope without departing from the technical spirit of the present invention. Those of ordinary skill in the art to which the present invention pertains can easily recognize that it can be easily changed and modified.

1: Congratulatory remarks 2: Network
100: imaging device 200: computing device
300: monitoring server
201: system memory 202: operating system
203 processing unit 204 storage
205: input device 206: output device
207: communication device
310: event detection unit 320: statistical information management unit
330: database 340: monitoring management unit
311: image recognition module 312: behavior detection module
313: behavior analysis module 314: body area analysis module
315: weight change detection module 316: disease determination module

Claims (10)

As a smart livestock system that provides intelligent monitoring of livestock raised in a livestock barn,
a plurality of imaging devices provided in the barn to generate a captured image; and
A monitoring server that performs image recognition on the captured image, detects whether a predetermined event has occurred for livestock existing in the livestock shed, generates event data for the generated event, and generates statistical information on the event data ;
A smart barn system that includes.
According to claim 1, wherein the monitoring server
A smart livestock house system, characterized in that self-learning based on the generated statistical information and resetting the standard of occurrence of the event.
The method of claim 2, wherein the monitoring server
an event detection unit for performing image recognition on the captured image, detecting the occurrence of an event with respect to the livestock existing in the livestock, and generating the event data when the event occurs; and
a statistical information management unit that generates statistical information for the event data, and resets the occurrence criteria of the event by self-learning based on the generated statistical information;
A smart barn system that includes.
The method of claim 3, wherein the event detection unit
a behavioral change event when the behavioral amount of the livestock increases or decreases;
a non-action event if there is no action of the livestock;
a behavior repeat event when the livestock repeats a specific behavior;
a posture event when the livestock takes a specific posture including a standing posture, a lying posture, a sitting posture, and a knee posture;
a weight change event for the livestock when the animal's weight increases or decreases; and
a disease infection event when the disease infection of the livestock individual is estimated based on the abnormal behavior event and the weight change event generated for the livestock;
Smart livestock system, characterized in that it generates.
The method of claim 3, wherein the statistical information management unit
As anomaly statistics, each individual's activity amount, average amount of behavior, inaction time, the number and time of repetition of a specific behavior, the number of times for each specific posture including standing posture, supine posture, sitting posture and knee posture, the duration of the specific posture, and A smart livestock house system, characterized in that it generates statistical information about the total posture holding time.
The method of claim 3, wherein the event detection unit
an image recognition module for detecting a livestock region from a captured image based on the external information data of the livestock;
a behavior detection module for detecting the behavior or non-action of the livestock based on the change in the livestock area in the continuous captured images; and
a behavior analysis module for generating a behavior-related event for the livestock based on the detected behavior or non-action of the livestock;
A smart barn system that includes.
A livestock monitoring method performed in a monitoring server that provides intelligent monitoring for livestock raised in the livestock by interworking with a plurality of imaging devices provided in the livestock,
performing image recognition on the captured image to detect whether a predetermined event has occurred for livestock existing in the livestock house;
generating event data for the generated event and generating statistical information about the event data; and
self-learning based on the generated statistical information and resetting the occurrence criteria of the event;
A livestock monitoring method comprising:
The method of claim 7, wherein the step of detecting whether the event has occurred,
generating a behavior change event when the behavior amount of the livestock increases or decreases;
generating a non-action event if there is no action of the livestock;
generating an action repetition event when the livestock repeats a specific action;
generating a posture event when the livestock takes a specific posture including a standing posture, a lying posture, a sitting posture, and a knee posture;
generating a weight change event for the livestock when the weight of the livestock increases or decreases; and
generating a disease infection event when the disease infection of the livestock individual is estimated based on the abnormal behavior event and the weight change event generated for the livestock;
A livestock monitoring method comprising at least one of.
The method of claim 7, wherein the step of detecting whether the event has occurred,
detecting a livestock region from the captured image based on the external appearance information data of the livestock;
detecting the behavior or inaction of the livestock based on the change in the livestock area in the continuous captured images; and
generating a behavior-related event for the livestock based on the detected behavior or inaction of the livestock;
A livestock monitoring method comprising:
The method of claim 7, wherein the generating of statistical information for the event data comprises:
As anomaly statistics, each individual's activity amount, average amount of behavior, inaction time, the number and time of repetition of a specific behavior, the number of times for each specific posture including standing posture, supine posture, sitting posture and knee posture, the duration of the specific posture, and generating statistical information on total posture maintenance time;
A livestock monitoring method comprising:

Images