WO2021182695A1 - Système de détection de diarrhée et de prédiction du niveau de risque de diarrhée chez le bétail, et son procédé d'utilisation - Google Patents

Système de détection de diarrhée et de prédiction du niveau de risque de diarrhée chez le bétail, et son procédé d'utilisation Download PDF

Info

Publication number
WO2021182695A1
WO2021182695A1 PCT/KR2020/012334 KR2020012334W WO2021182695A1 WO 2021182695 A1 WO2021182695 A1 WO 2021182695A1 KR 2020012334 W KR2020012334 W KR 2020012334W WO 2021182695 A1 WO2021182695 A1 WO 2021182695A1
Authority
WO
WIPO (PCT)
Prior art keywords
livestock
diarrhea
risk
predicting
data
Prior art date
Application number
PCT/KR2020/012334
Other languages
English (en)
Korean (ko)
Inventor
박지환
천선일
Original Assignee
(주)씽크포비엘
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from KR1020200116045A external-priority patent/KR102624927B1/ko
Application filed by (주)씽크포비엘 filed Critical (주)씽크포비엘
Publication of WO2021182695A1 publication Critical patent/WO2021182695A1/fr

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
    • A01K11/00—Marking of animals
    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
    • A01K29/00—Other apparatus for animal husbandry
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
    • Y02A40/70—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in livestock or poultry

Definitions

  • the present disclosure relates to a system for detecting diarrhea in livestock and predicting the risk of diarrhea by analyzing image information and sensor information, and a method of using the same.
  • the death of livestock is one of the important factors that greatly affect the productivity of livestock breeding farms such as Korean cattle and dairy cows.
  • Korean beef industry calf deaths resulted in a loss of about KRW 605.7 billion as of 2018.
  • digestive diseases diarrhea
  • ICT information and communication technology
  • livestock industry is changing as ICT technology is applied in the direction of reducing the cost of livestock
  • the adoption of smart livestock technology is still low in the field of disease management of livestock.
  • a manager In order to manage the health status and disease symptoms of livestock, a manager usually walks around and observes them directly, records and manages the weight and meal amount of the livestock, or uses a wearable sensor to contact the livestock movement data, etc.
  • the current level of technology is to analyze and manage the disease or use a microphone to analyze and detect disease signs of livestock, such as coughing sounds, with artificial intelligence.
  • Diarrhea in livestock is mostly caused by viruses, and especially young livestock such as calves can die from dehydration if not taken within 24 hours. There is a need to quickly recognize young livestock and take action with careful observation.
  • a method for detecting diarrhea and predicting the risk of diarrhea in livestock based on sensor data and image data performed on a computer system.
  • the method includes receiving sensor data and an identifier of the livestock, analyzing the sensor data to identify the livestock, classifying the identified activity of the livestock, and calculating the location of the livestock; and receiving image data, analyzing the image data, and classifying the activity of at least one livestock included in the image.
  • the method may further include mapping the activity of the livestock classified as a result of sensor data analysis and the activity of the animal classified as a result of image data analysis, and confirming whether the activity is recognized as the same activity.
  • the step of determining whether the same activity is recognized includes determining whether the class analyzed as a result of analyzing the image data in the same time zone as the class classified as a result of analyzing the sensor data is the same can do.
  • the method may further include predicting the posture of the livestock by time based on the sensor data.
  • the posture prediction step may be performed based on an LSTM time series-based prediction method.
  • the method further comprises calculating the livestock location and analyzing the moving line of the livestock, wherein the analyzing the moving line is frame-by-frame based on a Simple Online and Realtime Tracking technique It may be a step of analyzing the number and time of moving to a predetermined location by tracking the recognized livestock.
  • the method further comprises the step of predicting the risk of diarrhea of the livestock, wherein the predicting of the risk of diarrhea is based on the analysis value of the movement and posture of the livestock, the number of times the livestock approaches the bucket, the livestock lying down It can be calculated according to the number of times and time.
  • the method may further include transmitting an alarm when the predicted risk of diarrhea is greater than or equal to a predetermined value.
  • the step of predicting the risk of diarrhea of the livestock may be calculated by adding a predetermined weight to the number of times the livestock approaches the bucket, the number of times and the time the livestock is lying on the basis of the analysis value of the movement and posture of the livestock. have.
  • a computer-readable medium containing one or more computer-readable instructions executable by a computer, wherein the one or more computer-readable instructions, when executed by the computer, cause the computer to:
  • a computer-readable recording medium for performing any one of the above-described methods is provided.
  • the behavior of the livestock can be monitored without omission for 24 hours, and a prescription necessary for the livestock can be applied in a timely manner.
  • FIG. 1 is a diagram schematically illustrating the overall configuration of a system 100 for detecting and predicting signs of diarrhea in livestock according to an embodiment of the present disclosure.
  • FIG. 2 is a functional block diagram illustrating an exemplary functional configuration of the diarrhea symptom detection and risk prediction server of the livestock of FIG. 1 .
  • FIG. 3 is a functional block diagram illustrating an exemplary functional configuration of the disease management server of FIG. 1 .
  • FIG. 4 is a screen on which a heat map according to a dwell time of a detection object is displayed according to an embodiment of the present disclosure.
  • FIG. 5 is a screen for displaying a result of tracking the movement of a detection object according to an embodiment of the present disclosure.
  • a 'block' or 'unit' means a functional part that performs at least one function or operation, and may be implemented as hardware or software, or a combination of hardware and software.
  • the plurality of 'blocks' or 'units' may be integrated into at least one software module and implemented with at least one processor, except for 'blocks' or 'units' that need to be implemented with specific hardware. .
  • the diarrhea symptom detection and risk prediction system 100 of livestock includes a total sensor 110, a camera 120, a data receiving device 130, a diarrhea symptom detection and risk prediction server 140 of livestock, It may include a communication network (not shown), a beacon receiver 150 and a disease management server 160 .
  • the total sensor 110 may be a fixed sensor attached to individual livestock.
  • the total sensor 110 may include a motion sensor.
  • the total sensor 110 may be a motion sensor capable of detecting movement, such as motion, posture, etc. of livestock, for example, an acceleration sensor, a gyro sensor, or a magnetic sensor.
  • the total sensor 110 may sense the activity of the livestock based on the data of the 3-axis to 9-axis motion sensor according to the movement of the livestock.
  • the total sensor 110 may be attached to the ears, joints, neck circumference, etc. that can detect the movement of livestock. In one embodiment, the total sensor 110 may be a fixed sensor attached to an individual livestock. In one embodiment, the total sensor 110 may be implemented in the form of a band detachable to a specific part, may be implemented in the form of a polyhedron attachable to a specific part, and may be implemented in a fixed form to the face (ear) of livestock. However, the present invention is not limited thereto.
  • the total sensor 110 may be a motion sensor capable of detecting movement, such as motion, posture, etc. of livestock, for example, an acceleration sensor, a speed sensor, or a gyro sensor, but is not limited thereto. As shown in this figure, the total sensor 110 is shown attached to the ears of livestock, but the present disclosure is not limited thereto. In one embodiment, the total sensor 110 may be attached to the ears, joints, neck circumference, etc. that can detect the movement of livestock.
  • the total sensor 110 is located in the spine of the livestock to detect the movement of the body where the forelimbs of the livestock are located, or is located in the region where the sacrum and the coccyx of the livestock are connected, the tail It is possible to sense the movement, the movement of the hind legs, the movement of the hind leg side pelvis, etc., or located in at least a part of the leg portion of the livestock, it is possible to sense the movement of the leg of the livestock, or located in at least a part of the face of the livestock, The movement of the face and/or the movement of the ears of livestock may be sensed.
  • the total sensor 110 may transmit identifier information for identifying individual livestock.
  • the total sensor 110 may include an RFID tag.
  • the total sensor 110 may transmit sensor data sensed together with livestock identifier information.
  • the total sensor 110 may transmit a beacon.
  • the beacon information transmitted from the total sensor 110 may be used to estimate the location of the livestock.
  • the total sensor 110 may operate using a battery. In an embodiment, the total sensor 110 may perform wireless communication. In an embodiment, the total sensor 110 may adjust a communication mode in order to efficiently use energy, and may transmit collected data according to a data transmission policy. In an embodiment, the data transmission policy may include transmitting data in a long period in case of a daily pattern and transmitting data in a short period when a pattern of interest appears.
  • the camera 120 is for photographing the appearance of livestock managed by the livestock farm, and any electronic device such as an image photographing camera, a video recording camera, and a CCTV camera equipped with a wired or wireless communication function.
  • any electronic device such as an image photographing camera, a video recording camera, and a CCTV camera equipped with a wired or wireless communication function.
  • the camera 120 is an image of the livestock itself, a gait image of the livestock, a sleep image, a motion image, an amount of feed ingested, a shoulder posture image, an excretion image, a vomit image, and a cleaning of a barn. Status, etc. can be photographed.
  • the camera 120 stores the recorded image data in a network video recorder (NVR), and transmits it to the diarrhea symptom detection and risk prediction server 140 of livestock through a communication network.
  • NVR network video recorder
  • the diarrhea symptom detection and risk prediction system 100 of livestock is illustrated as having one camera 120 , but the present disclosure is not limited thereto.
  • the data receiving device 130 may receive and collect wired/wireless data. In an embodiment, the data receiving device 130 may receive and collect RFID and motion sensor data. In an embodiment, the data receiving device 130 may collect beacon reception data. In an embodiment, the data receiving device 130 may transmit the received data to the server. In an embodiment, the data receiving device 130 may transmit the received data to the diarrhea symptom detection and risk prediction server 140 of livestock. In an embodiment, the data receiving device 130 may be a sensor data collection gateway.
  • the server 140 for detecting signs of diarrhea and predicting the risk of livestock may analyze the activity of livestock based on the received sensor data.
  • the detection and risk prediction server 140 for diarrhea signs of livestock may analyze the activity pattern of the livestock based on the received sensor data.
  • the diarrhea symptom detection and risk prediction server 140 of livestock may receive image data.
  • the server 140 for detecting signs of diarrhea and predicting the risk of livestock may analyze the activity of the livestock based on the received image data.
  • the diarrhea symptom detection and risk prediction server 140 of livestock may map the activity of individual livestock based on the collected sensor data and image data.
  • the diarrhea symptom detection and risk prediction server 140 of livestock may set the transmission period of the total sensor 110 .
  • the diarrhea symptom detection and risk prediction server 140 of livestock transmits data in a long cycle in case of a daily pattern so as to efficiently use energy from the total sensor 110, and transmits data in a short cycle when a pattern of interest appears. You can instruct the sensor to send data according to the policy.
  • the diarrhea symptom detection and risk prediction server 140 of livestock may be an edge computer.
  • the diarrhea symptom detection and risk prediction server 140 of livestock may analyze sensor data and image data to transmit an identifier of a livestock that has performed a predetermined activity to the disease management server 160 .
  • the communication network may include any wired or wireless communication network, for example, a TCP/IP communication network.
  • the communication network may include, for example, a Wi-Fi network, a LAN network, a WAN network, an Internet network, and the like, but the present invention is not limited thereto.
  • the communication network for example, Ethernet, GSM, EDGE (Enhanced Data GSM Environment), CDMA, TDMA, OFDM, Bluetooth, VoIP, Wi-MAX, Wibro and any other various wired or wireless communication protocols It can be implemented using
  • the beacon receiver 150 may receive a beacon from the total sensor 110 attached to the calf. In an embodiment, the beacon receiver 150 may transmit the received beacon information to the data receiving apparatus 130 . In one embodiment, at least four beacon receivers 150 may be provided in the barn.
  • the disease management server 160 may receive image information from the diarrhea symptom detection and risk prediction server 140 of livestock through a communication network. According to an embodiment of the present disclosure, the disease management server 160 may transmit/receive necessary information to and from the diarrhea symptom detection and risk prediction server 140 of livestock through a communication network.
  • the disease management server 160 may receive at least one of sensor data of livestock, image data of livestock, and biometric characteristic information of livestock from the diarrhea symptom detection and risk prediction server 140 of livestock. can According to an embodiment of the present disclosure, the disease management server 160 may predict whether the corresponding livestock is healthy based on the received classification data, activity recognition data, sensor data, image data, and biometric characteristic information. In an embodiment, the management server 160 may predict the diarrhea risk of the corresponding livestock based on the received classification data, activity recognition data, and sensor data, image data, and biometric characteristic information.
  • the disease management server 160 detects signs of diarrhea in livestock and predicts the risk of livestock image data, biometric feature data, and genetic information about the livestock received from the server 140, and the abnormal symptom determination model. Through this, it is possible to determine whether a disease has occurred in the relevant livestock.
  • the disease management server 160 may determine whether there are abnormal symptoms in the livestock by, for example, analyzing image information of the livestock.
  • the disease management server 160 may analyze the livestock image information to recognize the posture of the livestock.
  • the disease management server 160 analyzes the image information of the calf according to the class classified by the diarrhea symptom detection and risk prediction server 140 of livestock, for example, in the case of a calf, a sitting calf, a lying calf, It is classified into standing calves, overlapping calves, partially visible calves, and unrecognized calves, and when a calf with diarrhea is found, it can be recognized as an abnormal symptom.
  • the disease management server 160 may analyze the received image information to recognize whether vomit of livestock is present or the form of excrement of livestock is included in a normal range, and the like.
  • a person skilled in the art can apply a cloud-based machine learning algorithm by using the image data set for recognition of livestock images, for example, in the case of the sow's sitting posture, and in particular, the existing YOLO v3 and various class classification machine learning algorithms and Since it is well known that it can be implemented by applying the transformation, a detailed description of the livestock image information analysis will be omitted below.
  • the disease management server 160 may be a cloud server.
  • FIG. 2 is a functional block diagram illustrating an exemplary functional configuration of the diarrhea symptom detection and risk prediction server 140 of FIG. 1 .
  • the diarrhea symptom detection and risk prediction server 140 of livestock includes an image data collection module 210, an image data-based diarrhea analysis module 220, a sensor data collection module 230, and a sensor data-based posture analysis. It may include a module 240 , a sensor diarrhea and image diarrhea mapping module 250 , a livestock location calculation module 260 , a data transmission period setting module 270 , a memory module 280 , and a communication module 290 . .
  • the image data collection module 210 may collect image data according to an image data collection policy.
  • the image data collection module 210 may collect 720p or more color video images to the server at a cycle of 1 minute as the image data collection basic policy.
  • the collection period may be shortened to collect more frequently.
  • the image data collection module 210 may collect data by lengthening the collection period, for example, sleep time, if it is not a time period for livestock to be active as a second exception policy.
  • the image data collection module 210 may adjust the data transmission amount and period according to the network transmission environment as the third exception policy. For example, when the network transmission environment deteriorates, the data collection queue can be adjusted to collect data at once when the transmission speed exceeds a certain value.
  • the image data collection module 210 may perform pre-processing on the collected data. In an embodiment, the image data collection module 210 may perform pre-processing on the original image data, such as black-and-white images of the collected image data, or acquire an edge image.
  • the image data-based diarrhea analysis module 220 analyzes the activity state of the object to be monitored in the image by processing the image data using an artificial intelligence technique such as a machine learning technique and an image classification technique.
  • an artificial intelligence technique such as a machine learning technique and an image classification technique.
  • the image data-based diarrhea analysis module 220 may generate at least one abnormal symptom classification model through a learning process such as data labeling by processing image data in advance.
  • the image data-based diarrhea analysis module 220 may analyze the activity of the object (calf) in the image using the classifier with the best recall ability among the classifiers learned by using each classification algorithm.
  • the label (class) recognizable by the livestock anomaly classifier may include feces (Dung), urine (Piddling), and diarrhea (Diarrhea).
  • the sensor data collection module 230 may collect sensor data collected by the total sensor 110 through a communication network.
  • the sensor data may be collected via the beacon receiver 150 or may be collected directly.
  • the sensor data may include beacon, RFID, and motion sensor data.
  • the sensor data-based posture analysis module 240 may analyze data collected from sensors attached to individual livestock to analyze the posture of the corresponding livestock. According to an embodiment, the sensor data-based posture analysis module 240 may detect the posture of the livestock by time based on the collected 3-axis to 9-axis motion sensor data.
  • the sensor data-based posture analysis module 240 may analyze the collected sensor data as a posture pattern using a machine learning technique of a long short term memory (LSTM) time series-based prediction method such as RNN.
  • LSTM long short term memory
  • the sensor data is a list of constant numerical values, it is possible to classify the data by classifying the data at regular intervals and recognizing a pattern of the corresponding data.
  • the posture pattern is Standing, Sitting, Lying, Walking, Running, Dung, Urine. (Piddling), may include diarrhea (Diarrhea).
  • the sensor-based diarrhea and image-based diarrhea mapping module 250 may check whether the same detection result is shown in other analysis results when the sensor data analysis result and the image data analysis result diarrhea pattern are analyzed. . In one embodiment, the sensor-based diarrhea and image-based diarrhea mapping module 250 checks whether the same diarrhea pattern is recognized in the result of analyzing the image data when an activity of interest, such as a diarrhea pattern, appears as a result of analyzing the sensor data. can The sensor-based diarrhea and image-based diarrhea mapping module 250 may determine that the livestock has diarrhea with a high probability when diarrhea appears at the same timing in the sensor data analysis result and the image data analysis result. The sensor-based diarrhea and image-based diarrhea mapping module 250 may store the analysis value and request confirmation from the user when only one of the sensor data analysis results and image data analysis results is analyzed as having an activity of interest (diarrhea). .
  • the sensor-based diarrhea and image-based diarrhea mapping module 250 maps the sensor data analysis result and the image data analysis result and confirms whether it is recognized as the same activity, which livestock only as the image data analysis result It can solve the problem that it is difficult to identify whether the activity of interest has been accurately performed. That is, the sensor-based diarrhea and image-based diarrhea mapping module 250 may compare the sensor data (RFID and motion sensor value) with the image data analysis result to specify the livestock. If the same activity of interest appears across several livestock (calf), the sensor-based diarrhea and image-based diarrhea mapping module 250 does not need to individually identify and map the livestock (calf) of each image.
  • the sensor-based diarrhea and image-based diarrhea mapping module 250 is the image data analysis result, if the number of livestock of the activity of interest recognized in the same time period and the number of livestock of the activity of interest recognized on the sensor are the same, the corresponding livestock ID It is possible to transmit interest activity detection information together with the users.
  • the activity-of-interest detection information may include a detection time, an activity-of-interest class, an image, and the like.
  • the sensor-based diarrhea and image-based diarrhea mapping module 250 can maintain accuracy while reducing the computational load through this method.
  • the sensor-based diarrhea and image-based diarrhea mapping module 250 when the sensor-based diarrhea and image-based diarrhea mapping module 250 is different from the number of livestock of the activity of interest recognized as a result of image data analysis and the number of livestock of the activity of interest recognized as a result of sensor data analysis, after mapping as follows , and other information so that the user can check it.
  • the distance between each sensor and the sensor data collection gateway can be calculated as follows.
  • free space path loss can be calculated as follows.
  • distance (KM) can be obtained as follows.
  • each sensor knows the distance to the gateway and that each camera also knows the distance to the gateway
  • the distance between the object (calf) having the symptom of interest recognized within the camera and the gateway can be known. Therefore, the sensor attached to the calf has already been input into the system, so it is possible to know which camera the calf is shooting with.
  • the recognition result of a specific livestock and a sensor can be mapped by comparing the distance from the camera to the gateway of a specific livestock and the distance from the sensor to the gateway.
  • the livestock position calculation module 260 may calculate the position of the livestock based on information received from the beacon receiver 150 .
  • the livestock position calculation module 260 may calculate the position of the livestock by trilateration using the reception time of the beacon transmitter received by each beacon receiver.
  • the livestock position calculation module 260 may calculate the latitude and longitude values of the livestock based on the GPS position of the beacon receiver, as a result of trilateration, and calculate the position error using four or more beacon receivers. can be reduced Since those skilled in the art are well aware of various methods and modifications for calculating the position of an object, a detailed description of the method for calculating the position of the livestock will be omitted below.
  • the livestock position calculation module 260 may calculate the position of the livestock at a predetermined period.
  • the data transmission period setting module 270 may determine a data transmission policy of the sensor and instruct the sensor to transmit sensor data according to the transmission policy.
  • the data transmission policy may instruct the sensor to transmit data at a longer period if the sensor data analysis result is a daily pattern, and may instruct the sensor to transmit the sensor data at a shorter period when a pattern of interest appears.
  • the data transmission period setting module 270 may set a transmission policy to transmit data once every 5 minutes when a pattern of interest appears and transmit data once every 1 to 24 hours in case of a daily pattern.
  • the memory module 280 may be any storage medium in which various programs and related data that can be executed on the server 140 for detecting signs of diarrhea and predicting the risk of livestock are stored. According to an embodiment of the present disclosure, the memory module 280 may store sensor data, image data, and data related to the execution of the analysis module. According to an embodiment of the present disclosure, the memory module 280 may be configured to include various types of volatile or non-volatile memory such as DRAM, SRAM, DDR, RAM, ROM, magnetic disk, optical disk, flash memory, and the like.
  • the communication module 290 may support the diarrhea symptom detection and risk prediction server 140 of livestock to communicate with the outside through a communication network. According to an embodiment of the present disclosure, the communication module 290 may receive data from a communication network according to a predetermined protocol, and the data may be transmitted from the server 140 for detecting diarrhea signs of livestock and predicting the risk through the communication network. You can perform the necessary procedures to be transmitted.
  • FIG. 3 is a functional block diagram illustrating an exemplary functional configuration of the disease management server 160 of FIG. 1 .
  • the disease management server 160 includes a movement line analysis module 310 , a posture log analysis module 320 , a diarrhea risk prediction module 330 , a risk notification module 340 , a memory module 350 , and communication A module 360 may be included.
  • the movement line analysis module 310 may analyze the movement line of the livestock based on the location information of the livestock. In one embodiment, the movement analysis module 310 may receive the location information of the livestock and analyze the movement of the livestock based on the received information. In an embodiment, the movement analysis module 310 may receive a main location, for example, a water container location, a feed container location, and the like. In an embodiment, the movement line analysis module 310 may track the object recognized for each frame using a Simple Online and Realtime Tracking (SORT) algorithm. In one embodiment, the movement line analysis module 310 may analyze the time spent in each ID of the livestock and the movement line by using the ID mapping result of the total sensor 110 based on the image data. In one embodiment, the movement analysis module 310 may analyze how many times (number of times) the livestock moved to the main location and how long (time) it stayed.
  • SORT Simple Online and Realtime Tracking
  • FIG. 4 is a screen on which a heat map according to a dwell time of a detection object is displayed according to an embodiment of the present disclosure.
  • the movement line analysis module 310 may identify the object ID in the image data and display the object ID in the screen.
  • FIG. 5 is a screen for displaying a result of tracking the movement of a detection object according to an embodiment of the present disclosure.
  • the moving line analysis module 310 may display the tracked moving line for each object ID on the screen.
  • the posture log analysis module 320 may analyze the posture of the livestock based on the posture information (log data) of the livestock. In an embodiment, the posture log analysis module 320 may receive the posture data of the livestock and analyze the posture of the livestock based on the received information. In one embodiment, the posture log analysis module 320 may analyze how many times (number of times) the livestock took a certain posture during a predetermined unit time, and how many times (time) the livestock was taking one posture at one time. .
  • the diarrhea risk prediction module 330 may predict the risk that the livestock will have diarrhea based on the information on the livestock.
  • the information on the livestock may include the movement of the livestock and the posture of the livestock.
  • the diarrhea risk prediction module 330 may quantify the observed activity pattern and predict the diarrhea risk of livestock by using the movement line and posture analysis value.
  • the diarrhea risk prediction module 330 may calculate the diarrhea risk using three variable values.
  • Waterbox Trend The slope of the increase/decrease in the number of times a livestock approaches the water trough
  • Lying Count Trend The slope of the increase/decrease in the number of lying counts of livestock
  • the severity of each of the three variables may be defined as follows:
  • High Waterbox Trend In the last 12 hours, if the slope of the graph of the number of accesses to the Waterbox is greater than a predetermined value, such as 0.5, severe (meaning an increasing trend)
  • Lying Duration Trend In the last 12 hours, if the slope of the Lying Duration graph is greater than a predetermined value, such as 0.5, severe (meaning an increasing trend)
  • the diarrhea risk prediction module 330 may set a weight for each variable.
  • the weight of the Waterbox Trend may be set to 20%
  • the Lying Count Trend weight may be 40%
  • the Lying Duration Trend weight may be set to 40%.
  • the diarrhea risk prediction module 330 may calculate the final severity value as follows.
  • the diarrhea risk prediction module 330 may classify the severity type as follows according to the severity calculation result:
  • the danger notification module 340 may generate and transmit an alarm when the risk of diarrhea in livestock is greater than or equal to a predetermined value.
  • the risk notification module 340 may transmit the calf ID and the risk calculated value to the farm manager as a mobile push message, SMS, or the like, when the diarrhea risk of livestock is calculated above a certain level (eg, Warning).
  • the memory module 350 may be any storage medium in which various programs executable on the disease management server 160 and related data are stored. According to an embodiment of the present disclosure, the memory module 350 may store sensor data, image data, and data related to the execution of the analysis module. According to an embodiment of the present disclosure, the memory module 350 may be configured to include various types of volatile or nonvolatile memory such as DRAM, SRAM, DDR, RAM, ROM, magnetic disk, optical disk, flash memory, and the like.
  • volatile or nonvolatile memory such as DRAM, SRAM, DDR, RAM, ROM, magnetic disk, optical disk, flash memory, and the like.
  • the communication module 360 may support the disease management server 160 to communicate with the outside through a communication network. According to an embodiment of the present disclosure, the communication module 360 may receive data from a communication network according to a predetermined protocol and perform a necessary procedure to transmit data from the disease management server 160 to the outside through the communication network. can do.
  • the present disclosure is not limited to the examples described herein, and various modifications, reconstructions, and substitutions may be made without departing from the scope of the present disclosure.
  • the various techniques described herein may be implemented by hardware or software, or a combination of hardware and software.
  • certain aspects or portions of the analysis machine for software safety analysis according to the present disclosure may be implemented as one or more computer programs executable by a general purpose or dedicated microprocessor, micro-controller, or the like.
  • a computer program includes a storage medium readable by a computer processor or the like, for example, non-volatile memory such as EPROM, EEPROM, flash memory device, magnetic disk such as built-in hard disk and removable disk, magneto-optical disk, and It may be implemented in a form stored in various types of storage media including a CDROM disk and the like.
  • the program code(s) may be implemented in assembly language or machine language, and may be implemented in a form transmitted through electric wiring, cabling, optical fiber, or any other type of transmission medium.

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Environmental Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Pathology (AREA)
  • Theoretical Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Veterinary Medicine (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Animal Husbandry (AREA)
  • Zoology (AREA)
  • Physiology (AREA)
  • Multimedia (AREA)
  • Birds (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

L'invention concerne un procédé de détection de diarrhée et de prédiction du niveau de risque de diarrhée, le procédé étant fondé sur des données de capteur et des données d'image et mis en œuvre sur un système informatique. Le procédé peut comprendre les étapes consistant : à recevoir des données de capteur et des identifiants de bétail, et à analyser les données de capteur pour identifier le bétail, à classifier des activités du bétail identifié, et à calculer les emplacements du bétail ; et à recevoir des données d'image et à analyser les données d'image pour classifier l'activité d'au moins un animal d'élevage compris dans une image.
PCT/KR2020/012334 2020-03-12 2020-09-11 Système de détection de diarrhée et de prédiction du niveau de risque de diarrhée chez le bétail, et son procédé d'utilisation WO2021182695A1 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
KR20200030611 2020-03-12
KR10-2020-0030611 2020-03-12
KR1020200116045A KR102624927B1 (ko) 2020-03-12 2020-09-10 가축의 설사 탐지 및 설사 위험도 예측 시스템 및 그 이용 방법
KR10-2020-0116045 2020-09-10

Publications (1)

Publication Number Publication Date
WO2021182695A1 true WO2021182695A1 (fr) 2021-09-16

Family

ID=77672419

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2020/012334 WO2021182695A1 (fr) 2020-03-12 2020-09-11 Système de détection de diarrhée et de prédiction du niveau de risque de diarrhée chez le bétail, et son procédé d'utilisation

Country Status (1)

Country Link
WO (1) WO2021182695A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110298619A1 (en) * 2008-12-11 2011-12-08 Faire (Ni) Limited Animal monitoring system and method
JP2017112857A (ja) * 2015-12-21 2017-06-29 良一 春日 畜産管理システム
KR102001798B1 (ko) * 2016-03-11 2019-07-18 퀄컴 인코포레이티드 비디오 이해를 위한 모션-기반 어텐션에 의한 순환 네트워크들
KR102034998B1 (ko) * 2019-07-12 2019-10-22 경상대학교산학협력단 돼지움직임 감지용 광이표
CN110427905A (zh) * 2019-08-08 2019-11-08 北京百度网讯科技有限公司 行人跟踪方法、装置以及终端

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110298619A1 (en) * 2008-12-11 2011-12-08 Faire (Ni) Limited Animal monitoring system and method
JP2017112857A (ja) * 2015-12-21 2017-06-29 良一 春日 畜産管理システム
KR102001798B1 (ko) * 2016-03-11 2019-07-18 퀄컴 인코포레이티드 비디오 이해를 위한 모션-기반 어텐션에 의한 순환 네트워크들
KR102034998B1 (ko) * 2019-07-12 2019-10-22 경상대학교산학협력단 돼지움직임 감지용 광이표
CN110427905A (zh) * 2019-08-08 2019-11-08 北京百度网讯科技有限公司 行人跟踪方法、装置以及终端

Similar Documents

Publication Publication Date Title
WO2021221249A1 (fr) Système de gestion de bétail intelligent et procédé pour cela
JP6203238B2 (ja) 畜産管理システム
KR101712633B1 (ko) 센서와 무인비행체를 이용한 방목 가축 질병 예측 관리시스템 및 관리방법
KR20190033892A (ko) 야생동물 모니터링 시스템 및 그 방법
WO2022145614A1 (fr) Système et procédé d'estimation du poids du bétail utilisant une image d'étable de bétail
KR20150130803A (ko) 전염병 모니터링 방법 및 이를 이용한 시스템, 이를 수행하기 위한 기록매체
Dhaya et al. A wireless collision detection on transmission poles through IoT technology
WO2022158674A1 (fr) Système et procédé pour reconnaître et surveiller automatiquement le comportement du bétail en utilisant un apprentissage profond
WO2019083299A1 (fr) Dispositif et procédé de gestion d'un lieu d'élevage
WO2021194008A1 (fr) Procédé et dispositif de service infonuagique servant à détecter et à gérer tout symptôme anormal chez la truie
CN111310596A (zh) 一种动物患病状态监测***及方法
WO2024117665A1 (fr) Dispositif de détection de comportement de chevauchement de bovins
WO2021182684A1 (fr) Système de détection de symptômes anormaux de bétail individuel et procédé pour l'utiliser
KR102527322B1 (ko) 딥러닝 기반의 객체 인식을 통한 가축 관리 방법
KR20210116183A (ko) 가축의 설사 탐지 및 설사 위험도 예측 시스템 및 그 이용 방법
KR20160094589A (ko) 개체식별장치와 무인비행체를 이용한 방목가축 추적관리 시스템
KR102584357B1 (ko) 반문 이미지를 기반으로 한 축산 동물의 개체 식별 장치 및 영상을 기반으로 한 가축 행동 패턴 분류 시스템 및 가축 행동 패턴 분류 방법
KR20200105558A (ko) 컴퓨터 비전을 이용한 가축 질병 예측 시스템 및 그 방법
WO2021182695A1 (fr) Système de détection de diarrhée et de prédiction du niveau de risque de diarrhée chez le bétail, et son procédé d'utilisation
CN207938184U (zh) 一种车载违章行为抓拍***
CN116883946B (zh) 老人异常行为实时检测方法、装置、设备及存储介质
WO2019098583A1 (fr) Procédé et système d'analyse du comportement d'un chien de compagnie
CN116963595A (zh) 猪饲养辅助装置、猪饲养辅助方法以及猪饲养辅助程序
WO2024034923A1 (fr) Procédé et système de reconnaissance d'objet et d'analyse de modèle de comportement sur la base d'une surveillance vidéo à l'aide d'une intelligence artificielle
CN112489346A (zh) 一种办公区域用智能红外监测报警设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20924866

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20924866

Country of ref document: EP

Kind code of ref document: A1