KR102375362B1 - Method and apparatus for inspecting barn environment based on ai - Google Patents

Abstract

An AI-based livestock barn environment investigation method and device are provided, and the AI-based livestock barn environment investigation method and device are a camera for photographing a livestock room, which is a partitioned place for raising livestock in the livestock bar, and a visible light image of the livestock barn room photographed through the camera It may include a control device for identifying the location of the livestock in the livestock room based on the and measuring the body temperature of the livestock based on a thermal image that is an image obtained by thermal imaging of the identified livestock. .

Description

AI-based livestock barn environment investigation method and device {METHOD AND APPARATUS FOR INSPECTING BARN ENVIRONMENT BASED ON AI}

Embodiments disclosed in the present specification relate to an AI-based livestock environment research method and apparatus, and more specifically, automatically move the livestock, photograph the livestock, and use the artificial intelligence in the livestock barn based on the captured image. It relates to a livestock environment survey method and apparatus for remotely measuring the body temperature of livestock to identify livestock with abnormal symptoms.

The important economic factors of the livestock industry include the fertility rate, mortality rate, and feed consumption of livestock.

One of the causes of death of livestock is death due to disease. Animals affected by the disease show abnormal symptoms, such as anorexia, reduced activity, inability to stand, vomiting, and spots.

Early detection of livestock disease is important in order to prevent the death of livestock due to disease. In general, since changes in the body temperature of livestock occur before abnormal symptoms of livestock due to disease appear, the disease of livestock can be detected early by measuring the temperature of the livestock.

To measure the body temperature of livestock, the manager directly inserts a sensor for measuring body temperature into the body of the livestock.

However, the above-described method for measuring body temperature has a problem in that it requires a lot of time and manpower to measure the body temperature of all livestock raised in the barn.

In addition, since most diseases of livestock are infectious diseases by contact, there is a problem that contact temperature measurement for livestock has a high risk of transmission.

In relation to this, Korea Patent Publication No. 10-1942895, a prior art document, discloses a structure for a livestock dedicated to poultry that is easy to dry the bottom soil by allowing water to drain smoothly to prevent infectious diseases, but livestock without direct contact does not solve the problem of measuring the body temperature of

Therefore, there is a need for a technique for solving the above-mentioned problems.

On the other hand, the above-mentioned background art is technical information that the inventor possessed for the purpose of derivation of the present invention or acquired during the derivation process of the present invention, and it cannot be said that it is necessarily known technology disclosed to the general public before the filing of the present invention. .

Embodiments disclosed in the present specification, it is an object to present an AI-based livestock barn environment research method and apparatus.

Embodiments disclosed in the present specification have an object to provide a livestock environment research method and apparatus for autonomously moving along the corridor in the livestock house and measuring the environment of each barn room.

Embodiments disclosed in the present specification have an object to present a method and apparatus for researching a livestock environment for generating a map of the barn while moving along the corridor in the barn.

Embodiments disclosed in the present specification, it is an object to present a livestock environment investigation method and apparatus for indirectly measuring the body temperature of livestock in the barn using a camera.

Embodiments disclosed in the present specification, it is an object to present a livestock environment investigation method and apparatus for measuring the body temperature of livestock located inside the livestock room using a camera mounted on a variable length arm.

Embodiments disclosed herein have an object to present a livestock environment investigation method and apparatus for tracking and managing the body temperature of each livestock by identifying the livestock photographed through a camera.

Embodiments disclosed herein have an object to propose a livestock environment survey method and apparatus for autonomously moving the livestock house and measuring the environment of each location in the livestock house using a sensor.

As a technical means for achieving the above-described technical problem, according to an embodiment, in the apparatus for examining the environment of the livestock, through the camera and the camera for photographing the livestock room, which is a partitioned place for breeding livestock in the barn Identifies the position of the livestock in the livestock based on the photographed visible light image of the livestock, and measures the body temperature of the livestock based on a thermal image that is an image obtained by thermal imaging for the identified livestock It may include a control device.

According to another embodiment, in the method for the livestock environment investigation apparatus to investigate the environment of the livestock house, the step of photographing the livestock room, which is a partitioned place for raising livestock in the livestock house, based on the photographed visible light image of the livestock house It may include the steps of identifying the location of the livestock in the livestock room, and measuring the body temperature of the livestock based on a thermal image that is an image obtained by thermal imaging of the identified livestock.

According to another embodiment, as a computer readable recording medium on which a program for performing a livestock environment survey method is recorded, the livestock environment survey method includes the steps of: photographing a livestock room, which is a partitioned place for breeding livestock in the livestock barn , identifying the position of the livestock in the livestock room based on the photographed visible light image of the livestock room, and the body temperature of the livestock based on the thermal image image, which is an image obtained by thermal imaging for the identified livestock It may include the step of measuring.

According to another embodiment, as a computer program stored in a recording medium to perform a livestock environment investigation method and carried out by a livestock environment surveying device, the livestock environment investigation method is a livestock house that is a partitioned place for raising livestock in the livestock house Photographing the room, identifying the position of the livestock in the livestock room based on the photographed visible light image of the livestock room, and based on a thermal image image that is an image obtained by thermal imaging for the identified livestock It may include measuring the body temperature of the livestock.

According to any one of the above-mentioned problem solving means, it is possible to present an AI-based livestock barn environment research method and apparatus.

According to any one of the above-mentioned problem solving means, it is possible to propose a livestock environment investigation method and apparatus capable of autonomously moving along the corridor in the livestock house and measuring the environment of each barn room to investigate the environment of the livestock house unattended.

According to any one of the above-mentioned problem solving means, it is possible to present a method and apparatus for investigating the livestock environment that can be operated immediately even in a livestock house without prior information by moving along the corridor in the livestock house and generating a livestock house map.

According to any one of the above-mentioned problem solving means, a livestock environment survey method that can indirectly measure the body temperature of livestock in the barn using a camera to prevent contact infection due to body temperature measurement and quickly measure the body temperature of livestock; device can be presented.

According to any one of the above-mentioned problem solving means, by measuring the body temperature of livestock located inside the livestock room using a camera mounted on an arm with a variable length, it is possible to measure the body temperature of all livestock in the livestock barn environment The investigation method and apparatus can be suggested.

According to any one of the above-mentioned problem solving means, it is possible to present a livestock environment investigation method and device that can indirectly track changes in body temperature by livestock by identifying livestock photographed through a camera and tracking and managing the body temperature of each livestock. can

According to any one of the above-mentioned problem solving means, it is possible to autonomously move the livestock house and measure the environment of each location in the livestock house using a sensor, and present a livestock environment survey method and device that can monitor the environment of the livestock house unattended for 24 hours. can do.

Effects obtainable in the disclosed embodiments are not limited to the above-mentioned effects, and other effects not mentioned are clear to those of ordinary skill in the art to which the embodiments disclosed from the description below belong. can be understood clearly.

1 is a block diagram showing a network including a livestock environment research apparatus according to an embodiment.
2 is a configuration diagram showing each configuration of a livestock house environment irradiation apparatus according to an embodiment.
3 is a block diagram showing the configuration of a livestock house environment irradiation apparatus according to an embodiment.
4 to 5 are flowcharts for explaining a method for surveying a livestock shed environment according to an embodiment.
6 to 7 are exemplary views for explaining a method for surveying a livestock house environment according to an embodiment.

Hereinafter, various embodiments will be described in detail with reference to the accompanying drawings. The embodiments described below may be modified and implemented in various different forms. In order to more clearly describe the characteristics of the embodiments, detailed descriptions of matters widely known to those of ordinary skill in the art to which the following embodiments belong are omitted. And in the drawings, parts irrelevant to the description of the embodiments are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a component is said to be "connected" with another component, it includes not only the case where it is 'directly connected', but also the case where it is 'connected with another component in between'. In addition, when a component "includes" a component, it means that other components may be further included, rather than excluding other components, unless otherwise stated.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings.

However, before explaining this, the meaning of the terms used below is first defined.

A 'thermal image' is an image expressed in a color corresponding to the temperature of the shooting area using a thermal imaging camera.

A “visible light image” is an image obtained by capturing visible light by an image sensor.

‘Environmental information’ is information that quantifies the environment in the livestock house using sensors, and may include, for example, humidity, temperature, amount of light, dust level, oxygen level, carbon dioxide level, ammonia level, hydrogen sulfide level, etc.

'Shooting angle' is a viewing angle that can be taken using a camera, and the larger the shooting angle, the wider the range can be taken at once, while a zoom-out effect occurs when the shooting object moves away. is reduced and the object to be photographed becomes closer, and distortion of the shape of the object to be photographed may occur.

'Artificial neural network' is an information processing technology that performs complex control by correlating input and output in detail by engineering the advanced information processing mechanism of the biological nervous system. It is a network in which three types of neuron (neuron) models are connected in plurality, consisting of a hidden layer that prioritizes inputs and outputs and adjusts the interrelationship, and an output layer that calculates and outputs the required amount of control based on this.

Terms that require explanation other than those defined above will be separately explained below.

1 is a configuration diagram showing a network including a livestock environment research apparatus 10 according to an embodiment.

The livestock environment survey device 10 can measure the body temperature of livestock in a non-contact manner in each of at least one livestock room in the barn while automatically moving along the corridor of the barn, and for this purpose, the livestock environment survey device 10 can learn the actual measured body temperature information and thermal image of livestock input into the artificial neural network as learning data, and measure the body temperature of livestock based on the thermal image of the livestock taken through the camera using the learned artificial neural network can do.

For example, comparison learning may be performed using a thermal image obtained through thermal imaging of livestock and information on actual body temperature of livestock as learning data. In addition, the livestock environment surveying device 10 may measure the body temperature of the livestock by using a thermal image obtained by photographing the livestock through learning.

And the livestock environment survey device 10 can determine whether the measured body temperature of the livestock is within the normal range, and if there is a livestock with an abnormal body temperature among the livestock, the location and the location of the livestock with the manager terminal 30 Appearance characteristics may be provided.

At this time, the livestock environment surveying device 10 may separately add external features to the livestock to clearly identify the livestock, for example, by discharging paint bullets, paints, or a liquid mixed with paint to the livestock. You can add external features to .

The livestock environment research apparatus 10 may include an artificial neural network or be connected to an artificial neural network implemented in a physically spaced third server 20 according to an embodiment. Hereinafter, it is assumed that the artificial neural network is implemented in the control device 120 .

In addition, the livestock environment survey device 10 may acquire environmental information for each location of the livestock while moving along the corridor of the livestock house.

For example, the livestock environment survey device 10 can measure the temperature, humidity, carbon dioxide level, etc. at each location of the livestock while moving along the corridor of the livestock, and provide the measured environmental information to the manager terminal 30 . there is.

2 is a block diagram showing each configuration of the livestock house environment irradiation device 10. As shown in FIG.

Referring to FIG. 2 , the livestock environment irradiation apparatus 10 may include a camera 11 , a sensor 12 , a body 13 , a pillar 14 , an arm 15 , and a driving device 16 . And the livestock environment irradiation device 10 may additionally include a marking device (not shown).

First, the camera 11 may be provided with a rotation module so as to be rotatable as an input device for acquiring visually recognizable information by photographing livestock raised in the livestock room of the livestock, and one region of the arm 15 to be described later. can be coupled to

Such a camera 11 may take visible light for the vision for autonomous driving of the livestock environment survey device 10, generation or acquisition of a livestock map, and recognition of livestock in the livestock room. In addition, the camera 11 may take a thermal image to measure the body temperature of the livestock.

For example, the camera 11 may use a CMOS image sensor that acquires visible light to photograph livestock raised in a livestock room of a livestock shed, or an object within a livestock shed. Alternatively, the camera 11 may take a thermal image of the livestock using a thermal imaging (LWIR) sensor.

In this case, the camera 11 can adjust the shooting angle according to the shooting, and when the shooting angle is narrow, it can track a specific object and perform high-speed shooting.

For example, the camera 11 can take a picture with a wide shooting angle to track livestock in the livestock room or identify obstacles in the livestock house, and when measuring the body temperature of the livestock in the livestock room, the camera 11 narrows the shooting angle to reach the shooting range. Thermal imaging can be performed by allowing only one livestock to enter. In addition, the camera 11 may perform high-speed imaging so as to quickly take thermal images for each of the livestock in the livestock house.

According to an embodiment, the camera 11 may be implemented as one camera or as two or more physically separated cameras. Hereinafter, it is assumed that it is implemented with one camera and will be described.

In addition, the sensor 12 is provided in the livestock house environment survey device 10 to measure the environment of the point where the livestock house environment survey device 10 is located. For example, the sensor 12 may measure the environment of the livestock house through a temperature sensor, a humidity sensor, a carbon dioxide measurement sensor, and the like.

The main body 13 may be formed in a polyhedral shape, and a device necessary for driving or controlling the livestock environment irradiation device 10 may be mounted. For example, the main body 13 may be equipped with a battery (not shown) for driving the driving device 16 to be described later, and a computing device for controlling the livestock environment irradiation device 10 , etc. may be mounted thereon.

In addition, a pillar 14 , an arm 15 , and a driving device 16 , which will be described later, may be coupled to the body 13 to the outside of the body 13 .

For example, the body 13 may have a rectangular parallelepiped shape, the pillar 14 and the arm 15 may be provided on the upper surface, and the driving device 16 may be provided on the lower surface.

The pillar 14 may be formed in a bar shape having a certain length, and one end may be coupled to an area of the upper surface of the body 13 .

For example, the pillar 14 is disposed in a vertical direction with the ground, and one end of the pillar 14 is coupled to the upper surface of the main body 13, and is coupled to be rotatable 180 degrees to 270 degrees left and right in the longitudinal direction. can

In addition, the column 14 may have a variable length, so that the height of the arm 15 to be described later coupled to the other end of the column 14 may be changed.

For example, the pillar 14 may be implemented in the form of a telescopic rail, and by changing the length, the height from the ground to the arm 15 coupled to the other end of the pillar 14 may be changed.

The arm 15 is formed in a rod shape having a certain length and is disposed parallel to the ground so that one end of the arm 15 can be coupled to the post 14 , and the camera 11 is coupled to the other end of the arm 15 . can be

For example, the arm 15 is implemented in the form of a telescopic rail so that the length can be changed, and accordingly, the separation distance between the camera 11 and the pillar 14 provided at the other end of the arm 15 can be increased or decreased. there is.

In addition, the driving device 16 is provided at the lower end of the main body 13 to move the livestock environment irradiation device 10 .

For example, the driving device 16 may include an electric motor providing driving force and a driving unit receiving driving force from the electric motor and moving the livestock environment irradiation device 10 through rotational motion, and the driving unit is a wheel or infinite It may be implemented in the form of any one of the orbits. At this time, the driving device 16 may transmit a driving force to each wheel differently in a 4-axis independent driving method.

And the marking device (not shown) is provided at one position of the arm 15 to which the camera 11 is coupled, and is a device capable of applying a physical external force to the livestock to add external features to the livestock, for example, paint. It may be a launcher that fires bullets or a sprayer that can spray a liquid mixed with paint or paint.

3 is a block diagram showing the configuration of the livestock environment irradiation apparatus 10 according to an embodiment. Referring to FIG. 3 , the livestock house environment research apparatus 10 according to an embodiment may include an input/output device 110 , a control device 120 , a communication device 130 , and a memory 140 .

First, the input/output device 110 may include an input device for obtaining information about the livestock house, and an output device for displaying information such as a result of a job or the state of the livestock house environment research device 10 . For example, the input/output device 110 may include a camera 11 for photographing a livestock house, a sensor 12 for measuring an environment of a livestock house, and a display panel for displaying a screen.

Specifically, the input device is a device capable of acquiring the manager's input, such as a keyboard, a physical button, a touch screen, etc., a device capable of acquiring information about livestock in the livestock, such as a camera 11 or a microphone, or a temperature sensor, humidity It may include sensors 12 capable of measuring the environment of the livestock house in various forms, such as a sensor and a carbon dioxide measuring sensor. In addition, the output device may include a display panel or a speaker for outputting the state of the livestock environment irradiation device (10). However, the present invention is not limited thereto, and the input/output device 110 may include a configuration supporting various input/output.

Among these input/output devices 110, the camera 11 may photograph the livestock room, which is a partitioned place for raising livestock in the livestock barn.

For example, the camera 11 is provided at one end of the arm 15 so that it can penetrate into the livestock room according to the length extension of the arm 15 , and a direction perpendicular to the ground is used to photograph the livestock in the livestock room. It can be rotated 180 degrees to 270 degrees left and right on the axis.

In addition, the camera 11 may take a visible light image for recognizing the location or object of the livestock using a visible light image sensor or may take a thermal image of the livestock using a thermal imaging (LWIR) sensor.

In addition, the sensor 12 of the input/output device 110 may sense and quantify the environment of the livestock house. For example, the sensor 12 may be composed of a plurality of sensors, and each sensor may measure humidity, temperature, carbon dioxide level, and the like, of a livestock house, respectively.

Meanwhile, the control device 120 may be implemented as a computer capable of accessing a remote server through a network or connecting to other terminals and servers. Here, the computer includes, for example, a laptop, a desktop, and a laptop equipped with a web browser (WEB Browser). Alternatively, the control device 120 may be implemented in a form in which physically separated servers are connected through a network and logically connected to a cloud forming one system through a network to utilize the resources of the cloud.

The control device 120 controls the overall operation of the livestock house environment irradiation device 10, and may include a processor such as a CPU. The control device 120 may control other components included in the livestock house environment survey device 10 to conduct an environmental survey of the livestock house based on the information received through the input/output device 110 .

For example, the control device 120 may execute a program stored in the memory 140 , read a file stored in the memory 140 , or store a new file in the memory 140 .

First, the control device 120 may acquire a livestock house map.

According to one embodiment, the control device 120 may obtain a livestock house map from the manager.

For example, the control device 120 may provide a map production interface capable of producing or editing a livestock map by the manager's terminal, and the size of the livestock house, the size of the livestock room, the arrangement of the livestock room, or the height of the fence of the livestock room from the manager etc. may be sequentially acquired, and a floor plan of the livestock house may be generated based on the acquired information.

According to another embodiment, the control device 120 may generate a livestock map based on information about an object acquired in real time through the camera 11 while moving.

For example, the control device 120 can identify the fence, corridor, livestock, etc. of the livestock room, which are objects on the visible light image taken through the camera 11, and move along the corridor among the identified objects, and the livestock environment irradiation device (10) It is possible to create a livestock map in real time by identifying the fence of the livestock room, the size of the livestock room, and the like.

In addition, the control device 120 may generate a visit order for sequentially visiting the livestock rooms arranged on the livestock house map.

For example, the control device 120 rotates the barn room located within a certain preset radius (extendable length of the arm 15 of the barn environment irradiation device 10) at one location based on the barn entrance on the livestock house map in one direction. can determine the order of visits, and when the order of visits to the livestock room is determined at one location, the visit order of the livestock room can be determined in the same way at the next point.

Alternatively, for example, the control device 120 may generate a tree structure having the stall room as a node based on the location (or coordinates) of the stall room on the livestock house map, and according to a method of traversing the created tree structure, You can decide the order of your visits.

In addition, the control device 120 may use the camera 11 to identify objects in the livestock house and control the operation of the livestock house environment research device 10 that moves according to the visit order of the livestock house.

For example, the control device 120 may identify an obstacle located on the corridor of the livestock house using the visible light image acquired through the camera 11 , and may set a movement route by avoiding the identified obstacle.

Or, for example, the control device 120 can identify the height of the fence in the livestock room, and control the arm 15 not to collide with the fence in the livestock room by adjusting the length of the column 14 based on the identified height. can

Thereafter, the control device 120 may photograph the livestock room visited by the livestock house environment survey device 10 according to the visit order of the livestock house, and may identify the livestock in the livestock house.

For example, the control device 120 may extend the length of the arm 15 to penetrate the camera 11 into the livestock room, and may photograph livestock in the livestock room with the penetrating camera 11 . In addition, the control device 120 may individually identify the livestock based on the external characteristics of the livestock included in the photographed visible light image of the livestock room, such as the size of the body, the location of the spots, the shape of the tail, and the like.

To this end, the control device 120 may perform learning of the artificial neural network to identify the livestock from the visible light image. For example, the control device 120 may learn the appearance of livestock by inputting learning data about the appearance of the livestock to the artificial neural network, and may identify the livestock among objects included in the visible light image using the learning result. .

At this time, when the shooting angle of the camera 11 fails to capture the entire perimeter, the control device 120 rotates the camera 11 to change the shooting direction and sequentially shoots the axial direction, and visible light for each shooting direction. It is possible to identify whether the livestock included in the image is the same.

For example, the control device 120 rotates the camera 11 at a certain angle and can photograph livestock in all directions, rotates at a constant angle and captures the external characteristics of livestock in each of a plurality of visible light images photographed in all directions. On the basis of which livestock can be individually identified.

In this case, the control device 120 may identify whether it is the same livestock by tracking the moving livestock during the interval in which the camera 11 is rotated at a certain angle and photographing the livestock in the livestock area.

For example, the control device 120 searches for livestock having the same external characteristics among the livestock on the visible light image photographed in the second direction based on the external characteristics of the livestock on the visible light image photographed in the first direction, and performs the first By tracking the movement of the livestock on the visible light image of the direction, the same livestock can be identified in the visible light image of the second direction.

Meanwhile, according to an embodiment, the control device 120 may additionally add external features to the identified livestock.

For example, the control device 120 may use a marking device (not shown) to mark additional external features on the external appearance of the livestock by firing a paint bullet or spraying a liquid mixed with the paint to the livestock.

In addition, the control device 120 may measure the body temperature of the livestock based on a thermal image obtained through thermal imaging for each individually identified livestock in the livestock room.

To this end, the controller 120 may learn a relationship between a thermal image obtained by photographing the livestock with a thermal imaging camera and the actual body temperature of the livestock.

For example, the control device 120 can learn the relationship between the color of the thermal image and the actual body temperature of the livestock by inputting the thermal image of the livestock and the actual body temperature at the time of taking the thermal image of the livestock into the artificial neural network as learning data. there is.

Also, according to an embodiment, the controller 120 may perform learning to compare the color of each part and the measured temperature for each part of the livestock in the thermal image image of a livestock having a normal body temperature.

For example, the control device 120 may learn the temperature of each part of the animal having a normal body temperature by learning the temperature relationship measured from each color of the head and legs of the livestock and the head and legs of the livestock from the thermal image. .

In addition, the control device 120 may measure the body temperature of the livestock based on a thermal image obtained by taking a thermal image of the livestock.

At this time, according to the embodiment, the control device 120 may set the shooting angle of the camera 11 to be narrow so as to take a thermal image centering on a specific livestock tracking a location, and perform thermal imaging at high speed for a specific livestock. can do.

For example, the control device 120 may track a moving livestock based on a visible light image and perform thermal imaging of the livestock, and use a pre-learned artificial neural network to determine the color based on the color of the thermal image. It is possible to measure the body temperature of the livestock by estimating the body temperature of the corresponding livestock.

In this case, the controller 120 may further determine whether the body temperature of the livestock is normal based on the thermal image image of a portion of the livestock.

For example, the controller 120 may determine whether the body temperature of the livestock is normal based on the temperature difference by comparing the head temperature of the livestock having a normal body temperature based on the thermal image of the head of the livestock.

Meanwhile, the control device 120 may acquire environmental information at each location in the livestock house while visiting the livestock room according to the livestock house map.

For example, the control device 120 divides the livestock house into predetermined sizes and uses the sensor 12 provided in the livestock house environment irradiation device 10 at at least one point for each divided section to determine temperature, humidity, carbon monoxide concentration, It can measure carbon dioxide concentration and fine dust concentration.

The communication device 130 may perform wired/wireless communication with other devices or networks. To this end, the communication device 130 may include a communication module supporting at least one of various wired and wireless communication methods. For example, the communication module may be implemented in the form of a chipset.

Wireless communication supported by the communication device 130 is, for example, Wi-Fi (Wireless Fidelity), Wi-Fi Direct, Bluetooth (Bluetooth), UWB (Ultra Wide Band) or NFC (Near Field Communication), 2G to 5G It may include communication technology, or more communication technology. In addition, the wired communication supported by the communication device 130 may be, for example, USB, Ethernet, coaxial cable, or optical communication.

Various types of data such as files, applications, and programs may be installed and stored in the memory 140 . The control device 120 may access and use data stored in the memory 140 , or may store new data in the memory 140 . Also, the control device 120 may execute a program installed in the memory 140 . Referring to FIG. 1 , a program for performing a livestock environment survey method may be installed in the memory 140 .

4 and 5 are flowcharts for explaining a method for surveying a livestock house environment according to an embodiment.

The method for irradiating the livestock environment according to the embodiment shown in FIGS. 4 and 5 includes the steps of time-series processing in the barn environment irradiation apparatus 10 shown in FIGS. 1 to 3 . Therefore, even if omitted below, the contents described above with respect to the livestock environment irradiation apparatus 10 shown in FIGS. can

4 is a flowchart illustrating a method for irradiating a livestock environment for measuring the body temperature of livestock in a barn according to an embodiment of the present invention.

First, the livestock environment research apparatus 10 may determine the order of visiting the livestock room in the livestock house based on the livestock house map (S4001).

To this end, the livestock house environment survey device 10 may obtain a livestock house map.

According to one embodiment, the livestock environment research apparatus 10 may move a corridor in the livestock house, identify the location of the livestock house, and generate and obtain a livestock house map in real time.

For example, the livestock environment survey device 10 can identify the corridor in the livestock house through the camera 11, and can identify the number and location of the livestock house based on the fence of the surrounding livestock house while moving along the corridor. , it is possible to create a livestock house map in real time. And when there is no longer a movable corridor, the livestock environment survey device 10 may complete the generation of the livestock house map and return to the initial position.

According to another embodiment, the livestock barn environment research apparatus 10 may obtain a livestock house map from the manager terminal 30 .

For example, the livestock environment research apparatus 10 may provide a map production interface capable of generating or editing a livestock house map to the manager terminal 30, and at least one of a livestock room and a corridor from the manager through the map production interface You can obtain a livestock house map including placement information for

And the livestock environment research device 10 may determine the order of visits to the livestock room based on the acquired livestock house map.

For example, the livestock environment survey device 10 may set visiting points along the corridor at intervals corresponding to the size of the livestock room based on the entrance, which is the initial location of the livestock house map, and the livestock houses located within a preset radius at each visit point. It is possible to determine the order of visits in one direction with respect to the room.

Or, for example, the livestock environment research apparatus 10 may create a tree structure based on the relative positions between the livestock rooms and the livestock room on the livestock map as a node, and visit the livestock room according to the existing method of traversing the tree structure. order can be determined.

6 is an exemplary diagram illustrating the livestock environment research apparatus 10 for determining the visit order of the livestock room and performing the visit.

Referring to FIG. 6 , the livestock environment investigation device 10 is a visiting point ( 602, 603) can be set, and the first axis of rotation 604, 605, which can be photographed at the first visit point 602, is the rotation direction of the arm 15 of the livestock environment irradiation apparatus 10. In addition, a visit order may be set in the order of the second livestock room 605 . In addition, the livestock environment research apparatus 10 may determine the order of visits to the livestock rooms 606 and 607 in the same manner with respect to the second visit point 603 .

In addition, the livestock environment research apparatus 10 may photograph the visited livestock room according to the visit order determined in step S4001 (S4002).

For example, the livestock environment irradiation apparatus 10 may use the camera 11 to photograph the livestock room with visible light. In this case, if the entire livestock room is not included in the shooting angle of the camera 11 , the livestock environment irradiation apparatus 10 may rotate the camera 11 in units of shooting to photograph livestock in the livestock room.

Referring to FIG. 6 , the livestock environment irradiation apparatus 10 extends the arm 15 of the livestock environment irradiation apparatus 10 into the visited livestock house room 608 to penetrate the camera 11 into the livestock house room 608 to make a livestock house. Livestock in room 608 may be photographed.

Thereafter, the livestock environment irradiation apparatus 10 may individually identify the livestock in the livestock room based on the visible light image (S4003).

For example, the livestock environment irradiation device 10 can photograph livestock in the livestock room with visible light, can identify the external features of the livestock included in the visible light image, and individually examine the livestock in the visible light image based on the external features. can be registered as

At this time, the livestock environment survey device 10 may track the location of the livestock.

For example, when the livestock environment irradiation apparatus 10 rotates the camera 11 according to the shooting angle of the camera 11 to photograph the livestock room, the livestock environment irradiation apparatus 10 identifies in the first visible light image The movement of the same livestock may be tracked by identifying whether livestock having the same external feature in the second visible light image is present based on the external feature of the animal.

7 is an exemplary view illustrating a state of photographing a livestock room using the camera 11 . However, the livestock shown on the visible light images 701 , 702 , 703 , and 704 in FIG. 7 may not correspond one-to-one with the livestock shown in the thermal image 706 as it is briefly shown.

Referring to FIG. 7 , the livestock environment irradiation device 10 rotates the camera 11 to obtain visible light images 701 , 702 , 703 , 704 photographed in the livestock room, and a third visible light image 703 . can identify livestock 705 and track whether the identified livestock 705 is moving within the visible light image.

This allows the same livestock to be identified as different livestock and not managed.

At this time, the livestock environment survey device 10 may mark the external characteristics of the livestock tracking the movement to be distinguished from other livestock.

For example, the livestock environment irradiation device 10 may fire a paint bullet to the livestock identified in any one of a plurality of visible light images photographed in the livestock room to make a distinguishable marking on the skin of the livestock. This makes it easy to identify livestock based on their markings when tracking their movements in the rest of the visible light image.

In addition, the livestock environment investigation apparatus 10 may take a thermal image of the livestock individually identified in step S4003 (S4004), and may identify whether the body temperature of the livestock is normal based on the thermal image (S4005).

For example, the livestock environment investigation apparatus 10 may narrow the shooting angle so that only one livestock of the camera 11 is included within the shooting angle, and may take a thermal image for each livestock identified in step S4003. In addition, the livestock environment irradiation device 10 may measure the body temperature of each livestock based on the captured thermal image.

To this end, the livestock environment surveying apparatus 10 may train an artificial neural network to measure the body temperature of livestock using a thermal image.

For example, the livestock environment research apparatus 10 may perform learning by inputting a relationship between a thermal image of a livestock and an actual body temperature of the livestock into an artificial neural network as learning data. In addition, the livestock environment investigation apparatus 10 may additionally learn a relationship between a thermal image obtained by photographing a portion of the livestock and the actual body temperature of the livestock.

In the livestock environment research apparatus 10, learning of the artificial neural network may be performed before step S4001.

For example, the livestock environment survey device 10 may measure the body temperature of the livestock based on a thermal image obtained by photographing the body of the livestock using the learned artificial neural network, and identify whether the measured body temperature is within the normal body temperature range Thus, it is possible to determine whether the animal is abnormal or not.

And, for example, when a part of livestock is photographed, the livestock environment survey device 10 may measure the temperature of the photographed area based on a thermal image image of a portion of the livestock, and the corresponding portion of the livestock having a normal body temperature It is possible to determine whether the animal's body temperature is normal by comparing it with the temperature to determine whether the animal's body temperature is normal.

Or, for example, the livestock environment investigation apparatus 10 may determine whether the livestock is abnormal by identifying whether the temperature distribution in the thermal image is different from the temperature distribution of the livestock having a normal body temperature.

Referring to FIG. 7 , the livestock environment irradiation apparatus 10 determines the color of the thermal image region 707 corresponding to the livestock 705 in the thermal image 706 taken in the same direction as the third visible light image 703 . As a basis, the body temperature of the livestock 705 may be measured.

And when the body temperature of the livestock measured based on the thermal image is not the normal body temperature, the livestock environment survey device 10 may provide an alarm to the manager terminal 30 that the corresponding livestock is not the normal body temperature (S4006) .

For example, the livestock environment investigation device 10 may provide a text message including information on the external characteristics of the livestock determined to be not normal body temperature and the location of the livestock room in which the livestock is located to the manager terminal 30. .

At this time, according to the embodiment, the livestock environment investigation apparatus 10 may mark the external characteristics so as to externally identify the identified livestock determined as not having a normal body temperature.

For example, the livestock environment irradiation device 10 fires paint bullets or discharges a liquid mixed with paints to livestock identified as not having normal body temperature, marking them with a color different from the color of the animal's outer skin, It can be made to be externally distinguishable from livestock.

On the other hand, if the body temperature of the livestock is normal in step S4005, the livestock environment investigation device 10 may determine whether the temperature measurement of all livestock in the livestock room has been completed (S4007), and if the temperature measurement of all livestock is not completed, Steps S4004 to S4007 may be repeated until the temperature measurement of all livestock in the livestock room is completed.

And when the body temperature of all the livestock in the livestock room is measured in step S4007, the livestock environment investigation device 10 can determine whether all the livestock rooms in the livestock are visited (S4008), and if all the livestock rooms are not visited, it is determined in step S4001 Steps S4002 to S4008 may be repeated by moving to a livestock room to be visited next according to the order of visiting the livestock room in the livestock house.

In step S4008, when all the livestock rooms in the barn are visited and the body temperature of all livestock in the barn is measured, the barn environment survey device 10 may notify the manager terminal 30 that the temperature measurement of the livestock in the barn has been completed (S4009) ).

For example, the livestock environment investigation apparatus 10 may generate a report including information on the body temperature and temperature measurement date and time of livestock located in each livestock room for each livestock room, and may provide it to the manager terminal 30 .

5 is a flowchart illustrating a method of collecting livestock environment information by the livestock house environment research apparatus 10. Referring to FIG. Hereinafter, for the convenience of description, the description of the same configuration as described with reference to FIG. 4 will be omitted.

Referring to FIG. 5 , the livestock environment research device 10 may determine the visit order of the livestock room in the livestock house (S5001), and may acquire environmental information of each point in the livestock house while moving according to the determined visiting order of the livestock house (S5001). S5002).

For example, the livestock environment survey device 10 measures the temperature, humidity, carbon dioxide concentration, carbon monoxide concentration, wind, etc. of the environment in each livestock room according to the visit order of the livestock room determined in step S5001 using the sensor 12 . can do.

And, the livestock environment investigation apparatus 10 may determine whether all the livestock rooms have been visited (S5003), and if not all the livestock rooms have been visited, steps S5002 to S5003 may be repeated.

When all the livestock rooms are visited in step S5003, the livestock environment research apparatus 10 may provide environmental information of the livestock house to the manager terminal 30 (S5004).

For example, the livestock environment research device 10 provides environmental information at each location of the livestock house to the manager terminal 30 based on the environmental information acquired at the location of the livestock house visited in step S5002, but the environment is displayed on the livestock house map. Information can be displayed and provided.

Alternatively, the livestock house environment survey device 10 may provide information on livestock house management based on environmental information at each location of the livestock house.

For example, the livestock environment research apparatus 10 may open the ceiling of the livestock house for ventilation based on wind and humidity for each location of the livestock house or additionally provide information on the operation of the ventilation facility.

The term '~ unit' used in the above embodiments means software or hardware components such as field programmable gate array (FPGA) or ASIC, and '~ unit' performs certain roles. However, '-part' is not limited to software or hardware. '~' may be configured to reside on an addressable storage medium or may be configured to refresh one or more processors. Accordingly, as an example, '~' indicates components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, and procedures. , subroutines, segments of program patent code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.

The functions provided in the components and '~ units' may be combined into a smaller number of elements and '~ units' or separated from additional components and '~ units'.

In addition, components and '~ units' may be implemented to play one or more CPUs in a device or secure multimedia card.

4 and 5, the livestock environment survey method according to the embodiment may be implemented in the form of a computer-readable medium for storing instructions and data executable by a computer. In this case, the instructions and data may be stored in the form of program codes, and when executed by the processor, a predetermined program module may be generated to perform a predetermined operation. In addition, computer-readable media can be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. In addition, the computer-readable medium may be a computer recording medium, which is a volatile and non-volatile and non-volatile storage medium implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data. It may include both volatile, removable and non-removable media. For example, the computer recording medium may include magnetic storage media such as HDD and SSD, optical recording media such as CD, DVD and Blu-ray disc, or accessible through a network. It may be a memory included in the server.

Also, the method for surveying the livestock environment according to the embodiment described with reference to FIGS. 4 and 5 may be implemented as a computer program (or computer program product) including instructions executable by a computer. The computer program includes programmable machine instructions processed by a processor, and may be implemented in a high-level programming language, an object-oriented programming language, an assembly language, or a machine language. . In addition, the computer program may be recorded in a tangible computer-readable recording medium (eg, a memory, a hard disk, a magnetic/optical medium, or a solid-state drive (SSD), etc.).

Therefore, the method for investigating the livestock environment according to the embodiment described with reference to FIGS. 4 and 5 can be implemented by executing the computer program as described above by the computing device. The computing device may include at least a portion of a processor, a memory, a storage device, a high-speed interface connected to the memory and the high-speed expansion port, and a low-speed interface connected to the low-speed bus and the storage device. Each of these components is connected to each other using various buses, and may be mounted on a common motherboard or in any other suitable manner.

Here, the processor may process a command within the computing device, such as, for example, to display graphic information for providing a graphic user interface (GUI) on an external input or output device, such as a display connected to a high-speed interface. Examples are instructions stored in memory or a storage device. In other embodiments, multiple processors and/or multiple buses may be used with multiple memories and types of memory as appropriate. In addition, the processor may be implemented as a chipset formed by chips including a plurality of independent analog and/or digital processors.

Memory also stores information within the computing device. As an example, the memory may be configured as a volatile memory unit or a set thereof. As another example, the memory may be configured as a non-volatile memory unit or a set thereof. The memory may also be another form of computer readable medium, such as, for example, a magnetic or optical disk.

In addition, the storage device may provide a large-capacity storage space to the computing device. The storage device may be a computer readable medium or a configuration including such a medium, for example, a network storage device such as a storage area network (SAN), NAS, DAS, Cloud Storage, or devices or other devices in the above-described network devices. It may also include a configuration, and may be a floppy disk device, a hard disk device, an optical disk device, or a tape device, a flash memory, or other semiconductor memory device or device array similar thereto.

The above-described embodiments are for illustration, and those of ordinary skill in the art to which the above-described embodiments pertain can easily transform into other specific forms without changing the technical idea or essential features of the above-described embodiments. You will understand. Therefore, it should be understood that the above-described embodiments are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may be implemented in a combined form.

The scope to be protected through this specification is indicated by the claims described below rather than the detailed description, and it should be construed to include all changes or modifications derived from the meaning and scope of the claims and their equivalents. .

10: livestock environment survey device
11: Camera 12: Sensor
13: body 14: pillar
15: arm 16: drive device

Claims (20)

In the device for examining the environment of the livestock,
a camera for photographing a livestock room, which is a partitioned place for raising livestock in the barn; and
The position of the livestock in the livestock room is identified based on the visible light image of the livestock room taken through the camera, and the body temperature of the livestock is determined based on the thermal image obtained by thermal imaging of the identified livestock. including a control device for measuring;
The control device is
A livestock environment investigation apparatus for dividing the livestock room according to a preset shooting angle, and identifying the position of the livestock in the livestock room based on the relationship between the divided visible light images. The method of claim 1,
The control device is
A livestock environment research apparatus for learning the relationship between the actual body temperature of the livestock and the color of a region corresponding to the livestock in the thermal image based on the information on the actual body temperature of the livestock and the thermal image of the livestock. delete The method of claim 1,
The control device is
A livestock environment for identifying external features of livestock included in any one visible light image among the divided-photographed visible light images, and identifying the remaining livestock except for livestock having the identified external characteristics among livestock included in the remaining visible light images investigation device. The method of claim 1,
The control device is
Acquiring a livestock map including information on at least one of the location and corridor of the livestock house, and determining the order of visits to the livestock house based on the livestock map, a livestock environment research device. 6. The method of claim 5,
The control device is
Based on the visible light image obtained through the camera, the livestock house and the corridor are identified, and the livestock house map is generated based on the identified livestock house and the corridor. The method of claim 1,
The livestock environment survey device,
a body formed in a polyhedral shape and provided with the control device;
a pole formed in a bar shape having a certain length, and having one end disposed in a direction perpendicular to the ground at an upper end of the body and coupled thereto; and
Formed in the shape of a rod having a constant length and arranged parallel to the ground, one end coupled to the pole and the other end further comprising an arm provided with the camera. 8. The method of claim 7,
The cancer is
variable length,
The control device is
By varying the length of the arm, a camera provided at one end of the arm is penetrated into the livestock room to photograph the livestock room. 8. The method of claim 7,
The livestock environment survey device,
Further comprising a driving device provided at the lower end of the main body to move the livestock environment irradiation device in the livestock,
The control device is
A livestock house environment survey device for controlling the driving device to move a position of the livestock house environment survey device to obtain environmental information in the livestock house. 8. The method of claim 7,
The livestock environment survey device,
Further comprising a marking device coupled to the arm to apply a physical force to add an external characteristic for identifying the livestock,
The control device is
Controlling the marking device to mark the external features for identifying the livestock through the visible light image, livestock environment irradiation device. In the method for the livestock environment investigation device to investigate the environment of the livestock,
photographing a barn room, which is a partitioned place for raising livestock in the barn;
identifying the position of the livestock in the livestock room based on the photographed visible light image of the livestock room; and
Measuring the body temperature of the livestock based on a thermal image that is an image obtained by thermal imaging of the livestock whose location is identified,
The step of photographing the livestock room,
Comprising the step of dividing the shooting room according to the preset shooting angle,
The step of identifying the location of the livestock in the livestock room,
Including the step of identifying the location of the livestock in the livestock room based on the relationship between the divided visible light images, the livestock environment investigation method. 12. The method of claim 11,
The livestock environment survey method is,
Further comprising the step of learning a relationship between the actual body temperature of the livestock and the color of an area corresponding to the livestock in the thermal image based on the information on the actual body temperature of the livestock and the thermal image of the livestock, further comprising: Investigation method. delete 12. The method of claim 11,
The livestock environment survey method is,
identifying external features of livestock included in any one visible light image among the divided photographed visible light images; and
Further comprising the step of identifying the remaining livestock except for the cattle having the identified external features among the livestock included in the remaining visible light image, livestock environment survey method. 12. The method of claim 11,
The livestock environment survey method is,
obtaining a livestock house map including information on at least one of a livestock room location and a corridor of the livestock house; and
Further comprising the step of determining the visit order of the livestock room based on the livestock house map, livestock environment survey method. 16. The method of claim 15,
The step of obtaining the congratulatory map is,
identifying a livestock room and a corridor of the livestock house based on a visible light image obtained through a camera provided in the livestock barn environment irradiation device; and
Including the step of generating the livestock map based on the identified livestock room and corridor, the livestock environment survey method. 12. The method of claim 11,
The step of photographing the livestock room,
Controlling an arm having a variable length provided in the livestock environment research device, and penetrating a camera provided at one end of the arm into the livestock room to photograph the livestock room. 12. The method of claim 11,
The livestock environment survey method is,
The method further comprising the step of obtaining environmental information in the livestock house by moving the location of the livestock house environment research device. A computer-readable recording medium in which a program for performing the method according to claim 11 is recorded. A computer program stored in a medium to perform the method according to claim 11, which is carried out by the livestock environment survey device.

Images