WO2021044421A1 - System and method for remotely detecting and alerting actual or impending stress in animals in corrals and during transportation - Google Patents

System and method for remotely detecting and alerting actual or impending stress in animals in corrals and during transportation Download PDF

Info

Publication number
WO2021044421A1
WO2021044421A1 PCT/IL2020/050961 IL2020050961W WO2021044421A1 WO 2021044421 A1 WO2021044421 A1 WO 2021044421A1 IL 2020050961 W IL2020050961 W IL 2020050961W WO 2021044421 A1 WO2021044421 A1 WO 2021044421A1
Authority
WO
WIPO (PCT)
Prior art keywords
temperature
pixels
herd
lsi
calculating
Prior art date
Application number
PCT/IL2020/050961
Other languages
French (fr)
Inventor
Dov Berger
Tomer BERGER
Original Assignee
Dov Berger
Berger Tomer
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
Application filed by Dov Berger, Berger Tomer filed Critical Dov Berger
Publication of WO2021044421A1 publication Critical patent/WO2021044421A1/en

Links

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
    • A01K29/00—Other apparatus for animal husbandry
    • A01K29/005—Monitoring or measuring activity, e.g. detecting heat or mating
    • 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
    • A01K1/00—Housing animals; Equipment therefor
    • A01K1/0047—Air-conditioning, e.g. ventilation, of animal housings

Definitions

  • the present invention relates to the field of livestock and animal protection. More particularly, the present invention relates to a system and method for remotely detecting and alerting actual or impending stress, such as heat stress, in animals (e.g., livestock) in corrals (e.g., cowsheds) and during transportation.
  • actual or impending stress such as heat stress
  • animals e.g., livestock
  • corrals e.g., cowsheds
  • Heat stress problem causes cows to die worldwide.
  • the main cause of the heat stress and heat stroke in animals and especially in cows, is the weather and the inability of cows to cool themselves.
  • Animals of various kinds may suffer from weather conditions, especially at higher temperature and high humidity, since they find it difficult to cool themselves due to the fact that they do not sweat in a level which is sufficient for effective cooling. Under these conditions, they may enter a state of heat stress and consequently, a state of heat stroke. As a result, their metabolic activity decreases, causing a reduction in their milk output (the amount of milk the cow is able to produce significantly decreases). In addition, the heat stress causes a decrease in the fertility of the cows. Under extreme conditions, a situation of heat stroke can cause even to death. Also, depending on the type of animals, by preventing stress conditions it is possible to improve the Feed Conversion Ratio (FCR) and increase the yield of meat in fattened livestock or poultry.
  • FCR Feed Conversion Ratio
  • a heat stress also causes unnecessary waste of water, electricity and other resources and energy to cool the cows when an impending heat stress is not identified on time, and consequently, causes fluid build-up in cowshed's ground, dirt and mud. This problem is common throughout the world, and in Israel there is a relatively high awareness of the problem.
  • the existing cooling systems are partially manual, and the cows have to be physically moved to cooler areas.
  • Some cowsheds include automated cooling systems.
  • Another solution designed to detect a state of heat stress in livestock is by using a collar that measures the breathing rate of the animal and particularly cows.
  • a collar that measures the breathing rate of the animal and particularly cows.
  • the cow breathes at a rapid rate above a certain threshold, it means that the cow is in higher risk to pass into a state of heat stress, a situation in which the subsequent care will be much less effective. Therefore, the situation of heat stress should be detected at much earlier stages and in advance, where the cow can still be cooled and preventing the cow from entering heat state.
  • Detection of heat stress situation is also important when transporting livestock, since trucks, ships and other transport vehicles have a high density, which increases the chance of cows to enter a heat stress situation.
  • a method for detecting and alerting actual or impending heat stress in livestock comprising the steps of: a) placing at least one thermal imager (IR camera) having a predetermined FOV for capturing a location of a herd of livestock; b) installing a temperature calibration sensor at a predetermined distance from the camera; c) averaging the pixels value in the vicinity of the calibration sensor and the temperature reading is assigned to the average value; d) upon detecting movement of livestock in the FOV, continuously calibrating all pixels in FOV to the average value, according to the temperature reading of the calibration sensor; e) filtering out all pixels that belong to stationary objects and areas on the animals that are irrelevant to the calculation of an indication regarding the animal's core temperature; f) calculating the NITM representing the average thermal energy of the herd of livestock detected in the camera's FOV; g) calculating LSI value as a function of NITM values and Ta, while for NITM values that exceed a predetermined threshold, calculating LSI value as a function Temperature Humidity
  • the method may comprise the steps of: a) placing an array of sensors, which consists at least an Infra-Red thermal camera sufficiently high above ground of a cowshed; b) placing an external temperature sensor at a predetermined distance away from the thermal camera lens inside the camera's field of view, wherein the sensor itself hanging in the air in front of the camera lens; c) capturing an image of herd of cows in the cowshed; d) performing calibration using the pixels from the sensor's area, in which the temperature is equal to the temperature of the environment; e) calculating the temperature, i.e. the thermal energy level, for all pixels in the image, according to the performed calibration; f) selecting only the interesting areas in the image, i.e.
  • the relevant pixels such as gutters and eyes that indicate the cow's core temperature inside the cow; g) filtering all other uninteresting pixels that are considered to be noise and do not give valuable information; h) building temperature histograms for the herd of cows using image processing; i) choosing from the histograms only the pixels that have a good correlation with the core temperature of the cow by the dedicated software; j) for the high temperatures in the histogram above the threshold, calculating the average of the upper part for each column in the histogram, by a predetermined percentage, which indicates the core temperature of a cow in real time; and k) calculating the average of all these averages, which is the core temperature of the herd in the image.
  • the method further comprises the steps of: a) placing a humidity sensor that measures the environmental humidity, for calculating the environmental heat load; b) using algorithms, calculating the ability of the cow's heat dissipation to the environment by the dedicated software, by calculating the temperature gradient between the surface of the cow and the ambient heat load; c) estimating the thermal state of the herd according to the temperature gradient calculation as a number ranging between a lower limit that means that the herd is very comfortable and an upper limit that means that the herd is in a heat stroke/stress situation; d) continuously measuring temperature, ambient heat load and calibration, and at a constant rate, for monitoring the energy that the cow produces and obtaining indication regarding the herd's core temperature on the one hand, and from the other hand, at the same time monitoring the herd's ability to cool itself by releasing heat energy to the environment; and e) calculating the LSI while considering the ambient temperature, humidity, ambient heat load and the physiological measurements from the cows, at a predetermined range of the thermal state
  • the livestock may be selected from the group of:
  • Alert may be sent when the LSI is above a predetermined threshold and automatic cooling systems are being operated.
  • data from sensors such as microphones, gas sensors, voice and breathing sensors is added to the calculation of the LSI.
  • a system for detecting and alerting actual or impending heat stress in livestock, and especially in cows which comprises: a) array of thermal sensors placed sufficiently high above ground of a cowshed, which consists of at least Infra-Red thermal cameras; b) external temperature sensor hanging in the air, placed at a predetermined distance away from the thermal camera lens inside the camera's field of view; c) humidity sensor that measures the environmental humidity; d) a dedicated software module configured to preform image processing algorithms in order to calculate the temperature representing the thermal energy level, for all pixels in the image, and consequently performing calibration for all the pixels in the image; and e) a dedicated software module configured to perform continuously measurements of temperature, ambient heat load and physiological measurements from the cows, continuously and at a constant rate, which enable to monitor the energy that the cow produces, and at the same time monitor the herd's ability to cool itself by releasing heat energy to the environment, by calculating an LSI.
  • a method for detecting and alerting fever in a group of people comprising the steps of: a) placing at least one thermal imager (IR camera) having a predetermined FOV for capturing a location of the group; b) installing a temperature calibration sensor at a predetermined distance from the camera; c) averaging the pixels value in the vicinity of the calibration sensor and the temperature reading is assigned to the average value; d) upon detecting movement of people in the FOV, continuously calibrating all pixels in FOV to the average value, according to the temperature reading of the calibration sensor; e) filtering out all pixels that belong to stationary objects and areas on the people that are irrelevant to the calculation of the people temperature; f) calculating the NITM representing the average thermal energy of the group that is detected in the cameras' FOV; g) calculating NITM values with respect to Ta, while for NITM values that exceed a predetermined threshold, optionally considering the Temperature Humidity Index (THI); h) storing the calculated results; and i) repeating the preceding steps after
  • the system can differentiate between faces of persons in the FOV and indicate a person with deviation.
  • the system may further comprise: a) a plurality of positioning tags that are attached to each individual animal; b) a deployed array of receivers that are located in fixed locations in the transportation vehicle, for receiving data from each tag in different timing and calculating the actual 3-D position of each animal in real-time in the transportation platform; and c) a processor and dedicated software for performing environmental and physiological data fusion of the data collected from the remote sensing platforms and the locating tags, to provide information about the actual status of each individual animal's welfare and/or suspicious disease and/or stress condition.
  • the output signal may be wirelessly transmitted by a local controlling gateway and cellular transmission module to a dedicated mobile/permanent console in the team cabin, for allowing the team to take care of the livestock in the in the most beneficial way.
  • the system may further comprise autonomous control of cooling/heating device like ventilators, water sprinkles or heating systems, for a closed loop autonomous operation.
  • the collected data may be uploaded in real-time to a database for remotely controlling of the monitored fleet and for performing big-data analysis.
  • the system may further comprise a local monitoring console, which receives the data collected from all sensing platforms and processes the data to obtain indications regarding impending distress of each individual animal and provide local alerts.
  • a local monitoring console which receives the data collected from all sensing platforms and processes the data to obtain indications regarding impending distress of each individual animal and provide local alerts.
  • the data collected from all sensing platforms may be transmitted to a remote data analysis service for further analysis and providing analysis results to a command and control center, for generating and pushing alerts, presenting data at real-time and generating reports.
  • Fig. 1 illustrates a side view of the system proposed by the present invention
  • Fig. 2 illustrates the field of view of the IR camera which includes the temperature sensor for real-time calibration
  • Fig. 3 is a flowchart of the steps for LSI calculation process, according to an embodiment of the invention
  • Fig. 4 is a flow chart of the process of calculating LSI values for various conditions defined by different combinations of Ta, NITM and THI;
  • Fig. 5 is an illustration of livestock transportation in a truck, according to another embodiment of the present invention.
  • Fig. 6 is an illustration of the system architecture
  • Fig. 7 is an illustration of livestock transportation in truck in a time of during unloading and during the transportation (during a ride).
  • the present invention proposes a system and method for detecting and alerting actual or impending heat stress in livestock in cowsheds and during transportation., and especially in cows.
  • the system performs accurate temperature measurement (with a deviation of approximately ⁇ 0.25 °C).
  • Fig. 1 illustrates a cowshed with the system proposed by the present invention.
  • the system includes an array of sensors (such as temperature sensors, IR sensors, microphones and humidity sensors) placed sufficiently high above ground (e.g. on the roof or on posts) of a cowshed, which consists Infra-Red thermal cameras with real-time temperature calibration software that capture an image of herd of cows and continuously measure the surface temperature of preterminal limbs of the cows' bodies that provide accurate indications regarding the core temperature of the cow.
  • the temperature measurement is based on image processing and the pixel analysis of the image to determine the temperature of each pixel.
  • the system uses an external temperature sensor that is positioned at a predetermined distance (for example, about 30 to 40 cm) away from the thermal camera lens inside the camera's field of view (FOV), where the sensor itself may be hanged in the air and the camera staring at it, as illustrated in Fig. 2.
  • This temperature sensor is used as a reference point to continuously calibrate all pixels in the image, since its temperature is equal to the ambient temperature.
  • a dedicated software examines the pixels near the temperature sensor in terms of their thermal energy level. Then, using the average temperature of these pixels from the sensor's area, calibration is performed and the temperature (thermal energy level) is calculated for all pixels in the image. Then, the system measures and calculates the average thermal energy of a herd of cows that were detected in the cameras' field of view, which is defined as a Non- Invasive Temperature Measurement (NITM). While calibrating pixels with accurate temperature data, the system selects only the interesting areas in the image, i.e. the relevant pixels such as gutters and eyes that indicate the cow's core temperature (the core temperature is the temperature inside the cow, which is an emulation of an invasive temperature measurement such as using anal measurement by a thermometer.
  • NITM Non- Invasive Temperature Measurement
  • the core temperature indicates the entire state of the cow and how it feels). All other uninteresting pixels are considered to be noise (do not give valuable information), and they are been filtered out, for example: Iron railings in the cowshed that emit heat, wet hair and wet soil, areas in the cow with a minority of blood vessels such as a cow's back, pixels that had no thermal changes over time, etc. Then, by using image processing algorithms, the dedicated software chooses only the pixels that have a good correlation with the core temperature of the cow. These correlative pixels provide information about the thermal state of the entire cow.
  • the system builds a temperature histogram for the herd of cows and takes only the pixels above a certain predetermined temperature threshold.
  • the pixels above the threshold are considered relevant and the rest of the pixels are defined as noise.
  • the system calculates the average temperature derived from the upper part (that corresponds to higher temperatures) for each column in the histogram, by a predetermined percentage, and the rest of them are been filtered out. These average values indicate the core temperature of a cow in real time and the average value of all these averages is the indication of the core temperature of the herd in the image.
  • the system also includes additional sensors: a humidity sensor that measures the environmental humidity (for calculating the environmental heat load), and when it comes to other livestock, such as chicken and pigs (and possibly, other animals) , microphones are also placed to hear the sounds of the animals, from which one can learn about the state of the animals and how they feel.
  • the dedicated software calculates the ability of the cow to dissipate heat to the environment by calculating the temperature gradient between the surface of the cow and the ambient heat load. If the gradient is large, that means the cow's heat dissipation ability is good. If the gradient is small, it is difficult for the cow to release heat (energy) into the environment and then it begins to warm up and feel uncomfortable. Since a cow naturally does not sweat in a level which is sufficient for effective cooling, so it has difficulty releasing energy to the environment.
  • the system estimates the thermal state of the herd.
  • the estimate is made as a score ranging, for example, from 1 to 10, where 1 means that the herd is very comfortable and 10 means that the herd is in a heat stroke/stress situation.
  • the score may range between different limits, which are defined by the dedicated software, in order to provide rates indications regarding extreme states of the herd.
  • Measurements of temperature, ambient heat load and calibration are repeated continuously at a constant rate. From the one hand, the energy that the cow produces is monitored and the indication regarding the herd's core temperature is obtained, and from the other hand, the herd's ability to cool itself (by releasing heat energy to the environment) is measured. Natural or artificial air movements in the vicinity of the animals is also considered in the measurements made (such that their contribution to the cooling of the animals is reflected).
  • the physiological state of the cows also affects their ability to cool themselves. This data might also be considered by the dedicated software, along with the ambient temperature, humidity, ambient heat load and physiological measurements from the cows.
  • the system then creates a new index called LSI (Livestock Stress Index) which gives an indication from 1 to 10 (status table) of the thermal state of the herd. It is actually the new output provided by the system and may be used by the coward to learn about the thermal status of the herd of cows.
  • LSI Livestock Stress Index
  • the coward decides in which means and cooling systems to use in order to cool the cows.
  • Tables 1-3 illustrate the calculation of the LSI for several values of NITM with respect to the ambient temperature Ta:
  • Table 1 illustrates the LSI calculated values as a function of several measured NITMs for a state for which NITM ⁇ 37°C and NITM -Ta > 4°C.
  • NITM ⁇ 37°C
  • NITM -Ta a relatively larger difference between the measured NITM and the ambient temperature (i.e., there is a larger temperature gradient) and therefore, the ability of the herd to dissipate heat to the ambient increases.
  • the herd will not be in distress and the chance to get into a state of heat stress will be low. This can be seen from the LSI values of Table 1, where the calculated LSI values for NITM values ranging between 33-37 °C are between 1-5.
  • Table 2 illustrates the LSI calculated values as a function of several measured NITMs for a state for which NITM ⁇ 37°C and NITM -Ta ⁇ 4°C.
  • Table 3 illustrates the LSI calculated values as a function of several measured NITMs for a state for which NITM ⁇ 37°C and NITM -Ta ⁇ 2°C.
  • Tables 4a and 4b illustrate the LSI calculated values as a function of several measured NITMs for a state for which NITM > 37°C, while considering both NITM and Temperature Humidity Index (THI -a combination of temperature and humidity that is a measure of the degree of discomfort experienced by an individual in warm weather. Most people are quite comfortable when the index is below 70 and very uncomfortable when the index is above 80 to 85) values.
  • TTI Temperature Humidity Index
  • the ability of the herd to dissipate heat to the ambient is strongly dependent of the THI value, which is indicative of the level of heat load.
  • THI value which is indicative of the level of heat load.
  • Table 4b shows the calculated LSI values for NITM values ranging between 38-40 °C are between 6-10, respectively.
  • the LSI value is selected to be the highest value from both Table 4a and 4b. For example, if the THI is 72 the LSI value of Table 4a is 6. However, if at the same time the NITM is 39.5 °C, the cellulated LSI value of Table 4b is 9. Then, the final selected LSI value will be 9.
  • Fig. 3 is a flowchart of the steps for LSI calculation process, according to an embodiment of the invention.
  • IR camera thermal imager
  • a temperature calibration sensor is installed at a predetermined distance from the camera.
  • the pixels value in the vicinity of the calibration sensor is averaged and the temperature reading is assigned to the average value.
  • all pixels in FOV are continuously calibrated to the average value, according to the temperature reading of the calibration sensor.
  • NITM representing the average thermal energy of the herd of livestock detected in the camera's FOV
  • LSI value are calculated as a function of NITM values and Ta, while for NITM values that exceed a predetermined threshold, LSI value are calculate as a function Temperature Humidity Index (THI) and choose the highest value of LSI of both calculations.
  • THI Temperature Humidity Index
  • Fig. 4 is a detailed flow chart of the process of calculating LSI values for various conditions defined by different combinations of Ta, NITM and THI, according to another embodiment of the invention.
  • the system checks if the NITM (Non-lnvasive Temperature Measurement) is ⁇ 37. If no, at the next step 122, the system checks if the THI (Temperature Humidity Index) is ⁇ 75. If yes, at the next step 101, the system checks if the NITM- AmbientTemperature3MaximalGradiemt (4°C). If no, at the next step 143, the system checks if the NITM-AmbientTemperature ⁇ MaximalGradient and also if the NITM-
  • the system checks if the NITM ⁇ 37 and also if the NITM>36. If yes, at the next step 120, the LSI is determined as 5. If no, at the step 103, the system checks if the NITM ⁇ 36 and also if the NITM>35. If yes, at the next step 107, the LSI is determined as 4. If no, at the step 104, the system checks if the NITM ⁇ 35 and also if the NITM>34. If yes, at the next step 108, the LSI is determined as 3. If no, at the step 105, the system checks if the NITM ⁇ 34 and also if the NITM>33. If yes, at the next step 106, the LSI is determined as 2.
  • the system checks if the NITM ⁇ 33. If yes, at the next step 110, the LSI is determined as 1.
  • the system checks if the NITM-AmbientTemperature3MaximalGradiemt (4 °C). If no, at the next step 143, the system checks if the NITM-
  • the system checks if the NITM ⁇ 37 and also if the NITM>36. If yes, at the next step 115, the LSI is determined as 6. If no, at the step 112, the system checks if the NITM ⁇ 36 and also if the NITM>35. If yes, at the next step 120, the LSI is determined as 5. If no, at the step 113, the system checks if the NITM ⁇ 35 and also if the NITM>34. If yes, at the next step 107, the LSI is determined as 4.
  • the system checks if the NITM ⁇ 34 and also if the NITM>33. If yes, at the next step 108, the LSI is determined as 3. If no, at the step 109, the system checks if the NITM ⁇ 33. If yes, at the next step 110, the LSI is determined as 1. At step 143, the system checks if the NITM-AmbientTemperature ⁇ MaximalGradient and also if the NITM- AmbientTemperature>MinimalGradient. If no, at the next step 116, the system checks if the NITM-AmbientTemperature ⁇ MinimalGradient.
  • the system checks if the NITM (Non-lnvasive Temperature Measurement) is ⁇ 37. If no, at the next step 122, the system checks if the THI (Temperature Humidity Index) is ⁇ 75. If yes, at the next step 144, the system checks if the NITM- AmbientTemperature ⁇ MinimalGradient. If no, at the next step 146 the THI_LSI variable is assigned with the value of 6. If yes, at the next step 144 the THM.SI variable is assigned with the value of 7.
  • the system checks if the THI (Temperature Humidity Index) is ⁇ 75. If no, at the next step 123 the system checks if the THI>75 and also if the THI ⁇ 78. If yes, at the next step 144 the THI_LSI variable is assigned with the value of 7. If no, at the next step 124 the system checks if the THI>78 and also if the THI ⁇ 80. If yes, at the next step 125 the THI_LSI variable is assigned with the value of 8. If no, at the next step 126 the system checks if the THI>80 and also if the THI ⁇ 82. If yes, at the next step 127 the THM.SI variable is assigned with the value of 9. If no, at the next step 128 the system checks if the THI>82. If yes, at the step 129 the THM.SI variable is assigned with the value of 10.
  • THI Temporal Humidity Index
  • the system checks if the NITM ⁇ 38. If yes, at the next step 129 the NITM_LSI variable is assigned with the value of 6. If no, at the next step 132, the system checks if the NITM>38 and also if NITM ⁇ 38.5. If yes, at the next step 139 the NITM_LSI variable is assigned with the value of 7. If no, at the next step 133, the system checks if the NITM>38.5 and also if NITM ⁇ 39. If yes, at the next step 134 the NITM_LSI variable is assigned with the value of 8. If no, at the next step 135, the system checks if the NITM>39 and also if NITM ⁇ 40.
  • the system checks if the NITM>40. If yes, at the next step 138 the NITM_LSI variable is assigned with the value of 10.
  • the system checks if the THI_LSI3NITM_LSI. If yes, at the next step 141, the LSI is determined asTHI_LSI. If yes, at the next step 142, the LSI is determined as NITM_LSI.
  • LSI herd's thermal state
  • the proposed method and system may be used for remotely sensing, in real time, persons who have fever in order to monitor and control epidemics.
  • the system including IR cameras and associated calibration temperature sensors may be deployed in strategic points such as airports, bus stations and train stations to continuously capture images of crowd in their field of view. For example, a group of passengers coming from the same geographical zone may be analyzed, to detect abnormal average fever among the group members. This may help the official authorities such as the immigration authority to control the movement of persons who may be epidemic carriers, due to their body temperature.
  • a non-invasive remote monitoring system for early detection of potential stress situation of livestock during transportation process is proposed.
  • Fig. 5 is an illustration of a remote monitoring system operated during livestock transportation in a truck.
  • the system includes a cooling/chilling system 12 and a remote sensing platform 11 which is installed in such a way that it can monitor the animals in a certain level/cage positioned in any transportation platform like a truck, a train or a vessel.
  • the sensing platform continuously collects data regarding the physiological parameters of the animals which are positioned in its field of view and also collect data about the environmental conditions in the monitored area.
  • a small locating tags such as Ultra-Wide Band (UWB) Positioning Tags 13, are attached to each induvial animal and a deployed array of receivers 14 (that are located in fixed locations in the transportation vehicle), receives data from each tag 13 in different timing and by using triangulation, calculates the actual 3-D position of each animal in real-time in the transportation platform.
  • UWB Ultra-Wide Band
  • the proposed system performs data fusion of the collected data from the remote sensing platform 11 (environmental and physiological data) and the locating tags 13, in order to provide information about the actual status of each individual animal's welfare and/or suspicious disease and/or stress condition.
  • the output signal is wirelessly transmitted by a local controlling gateway and cellular transmission module 15 to a dedicated mobile/permanent console 16 in the team cabin, thereby allowing the team to take care of their livestock in the in the most beneficial way.
  • the system can autonomously control any cooling device 12 like ventilators, water sprinkles or heating systems, for a closed loop autonomous operation.
  • the data can be uploaded in real-time to any relevant database for remotely controlling of the monitored fleet and for performing big-data analysis.
  • x, y the exact horizontal location of any animal
  • z its height
  • This technology can be used extensively not just during transportation, but also in in cowsheds.
  • the indication of the condition of the animals in the case of transport is done for the entire herd and for each animal separately (in the case of transport there is not a large amount of animals such as in a cowshed, for example, and therefore, the condition and behavior of each animal can be monitored separately).
  • Fig. 6 is an illustration of the system architecture which is adapted to be installed on a transportation platform, such as a truck.
  • the system comprises a local monitoring console 16, which receives the data collected from all sensing platforms 11 and processing the data to obtain indications regarding impending distress of each individual animal and provide local alerts to a supervisor 17.
  • the monitoring console 16 may be controlled by a user interface 18.
  • the data collected from all sensing platforms 11 may be transmitted to a remote data analysis service 19 for further analysis.
  • the analysis results may be forwarded to a command and control center 20, for generating and pushing alerts, presenting data at real-time and generating reports.
  • Fig. 7 is an illustration of livestock monitoring in a truck during loading, after loading and during transportation, by an array of sensing platforms 11 that are located at different observation points along the platform. It should be noted that even though the above examples have been directed to livestock, the system proposed by the present invention may be adapted to detect stress in many other cultivated animals and also in human beings. Also, the system is adapted to detect several kinds of stress that is reflected in temperature changes, such as stress that originates from a disease or panic (e.g., in case of a predator intrusion).

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Environmental Sciences (AREA)
  • Biophysics (AREA)
  • Animal Husbandry (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

A system for detecting and alerting actual or impending heat stress in livestock, and especially in cows, comprising an array of thermal sensors placed sufficiently high above ground of a cowshed, which consists of at least Infra-Red thermal camera; an external temperature sensor hanging in the air, placed at a predetermined distance away from the thermal camera lens inside the camera's field of view; humidity sensor that measures the environmental humidity; a dedicated software module configured to preform image processing algorithms in order to calculate the temperature representing the thermal energy level for all pixels in the image, and consequently performing calibration for all the pixels in the image; a dedicated software module configured to perform measurements of temperature, ambient heat load and physiological measurements from the cows, continuously and at a constant rate, which enable to monitor the energy that the cow produces, and at the same time monitor the herd's ability to cool itself by releasing heat energy to the environment, by calculating an LSI.

Description

SYSTEM AND METHOD FOR REMOTELY DETECTING AND ALERTING ACTUAL OR
IMPENDING STRESS IN ANIMALS IN CORRALS AND DURING TRANSPORTATION
Field of the Invention
The present invention relates to the field of livestock and animal protection. More particularly, the present invention relates to a system and method for remotely detecting and alerting actual or impending stress, such as heat stress, in animals (e.g., livestock) in corrals (e.g., cowsheds) and during transportation.
Background of the Invention
Heat stress problem causes cows to die worldwide. The main cause of the heat stress and heat stroke in animals and especially in cows, is the weather and the inability of cows to cool themselves.
Animals of various kinds, especially cows in a cowshed, may suffer from weather conditions, especially at higher temperature and high humidity, since they find it difficult to cool themselves due to the fact that they do not sweat in a level which is sufficient for effective cooling. Under these conditions, they may enter a state of heat stress and consequently, a state of heat stroke. As a result, their metabolic activity decreases, causing a reduction in their milk output (the amount of milk the cow is able to produce significantly decreases). In addition, the heat stress causes a decrease in the fertility of the cows. Under extreme conditions, a situation of heat stroke can cause even to death. Also, depending on the type of animals, by preventing stress conditions it is possible to improve the Feed Conversion Ratio (FCR) and increase the yield of meat in fattened livestock or poultry.
A heat stress also causes unnecessary waste of water, electricity and other resources and energy to cool the cows when an impending heat stress is not identified on time, and consequently, causes fluid build-up in cowshed's ground, dirt and mud. This problem is common throughout the world, and in Israel there is a relatively high awareness of the problem.
The existing cooling systems are partially manual, and the cows have to be physically moved to cooler areas. Some cowsheds include automated cooling systems.
Existing temperature measurement systems use thermal cameras, but each camera requires real-time calibration while measuring the temperature, with high accuracy. In order to achieve a high level of accuracy, conventional methods use a black body, which is a very large and thermally stable heat storage (with a relatively constant temperature) since it almost does not emit energy to the environment. The disadvantage of a black body is that it is large, and very expensive.
Another solution designed to detect a state of heat stress in livestock is by using a collar that measures the breathing rate of the animal and particularly cows. When the cow breathes at a rapid rate above a certain threshold, it means that the cow is in higher risk to pass into a state of heat stress, a situation in which the subsequent care will be much less effective. Therefore, the situation of heat stress should be detected at much earlier stages and in advance, where the cow can still be cooled and preventing the cow from entering heat state.
Detection of heat stress situation is also important when transporting livestock, since trucks, ships and other transport vehicles have a high density, which increases the chance of cows to enter a heat stress situation.
It is therefore an object of the present invention to provide a system and method for remotely identifying the thermal state of a herd of cows, in cowsheds and during transportation, in real time at any given moment, and to provide alert regarding cows that are about to enter a state of heatstroke, so that the cowards can perform chilling operations to prevent the cows from entering a state of heatstroke. It is another object of the present invention to provide a system and method for remotely performing a continuous measurement in real time with high accuracy, using advanced and efficient calibration measures.
It is a further object of the present invention to effectively operate cooling systems for cows according to the thermal state measured in cows.
Other objects and advantages of the invention will become apparent as the description proceeds.
Summary of the Invention
A method for detecting and alerting actual or impending heat stress in livestock, comprising the steps of: a) placing at least one thermal imager (IR camera) having a predetermined FOV for capturing a location of a herd of livestock; b) installing a temperature calibration sensor at a predetermined distance from the camera; c) averaging the pixels value in the vicinity of the calibration sensor and the temperature reading is assigned to the average value; d) upon detecting movement of livestock in the FOV, continuously calibrating all pixels in FOV to the average value, according to the temperature reading of the calibration sensor; e) filtering out all pixels that belong to stationary objects and areas on the animals that are irrelevant to the calculation of an indication regarding the animal's core temperature; f) calculating the NITM representing the average thermal energy of the herd of livestock detected in the camera's FOV; g) calculating LSI value as a function of NITM values and Ta, while for NITM values that exceed a predetermined threshold, calculating LSI value as a function Temperature Humidity Index (THI) and choosing the highest value of LSI of both calculations; h) storing the chosen LSI results; and i) repeating the preceding steps after a predetermined time delay.
The method may comprise the steps of: a) placing an array of sensors, which consists at least an Infra-Red thermal camera sufficiently high above ground of a cowshed; b) placing an external temperature sensor at a predetermined distance away from the thermal camera lens inside the camera's field of view, wherein the sensor itself hanging in the air in front of the camera lens; c) capturing an image of herd of cows in the cowshed; d) performing calibration using the pixels from the sensor's area, in which the temperature is equal to the temperature of the environment; e) calculating the temperature, i.e. the thermal energy level, for all pixels in the image, according to the performed calibration; f) selecting only the interesting areas in the image, i.e. the relevant pixels such as gutters and eyes that indicate the cow's core temperature inside the cow; g) filtering all other uninteresting pixels that are considered to be noise and do not give valuable information; h) building temperature histograms for the herd of cows using image processing; i) choosing from the histograms only the pixels that have a good correlation with the core temperature of the cow by the dedicated software; j) for the high temperatures in the histogram above the threshold, calculating the average of the upper part for each column in the histogram, by a predetermined percentage, which indicates the core temperature of a cow in real time; and k) calculating the average of all these averages, which is the core temperature of the herd in the image.
In one aspect, the method, further comprises the steps of: a) placing a humidity sensor that measures the environmental humidity, for calculating the environmental heat load; b) using algorithms, calculating the ability of the cow's heat dissipation to the environment by the dedicated software, by calculating the temperature gradient between the surface of the cow and the ambient heat load; c) estimating the thermal state of the herd according to the temperature gradient calculation as a number ranging between a lower limit that means that the herd is very comfortable and an upper limit that means that the herd is in a heat stroke/stress situation; d) continuously measuring temperature, ambient heat load and calibration, and at a constant rate, for monitoring the energy that the cow produces and obtaining indication regarding the herd's core temperature on the one hand, and from the other hand, at the same time monitoring the herd's ability to cool itself by releasing heat energy to the environment; and e) calculating the LSI while considering the ambient temperature, humidity, ambient heat load and the physiological measurements from the cows, at a predetermined range of the thermal state of the herd, according to which the coward can use to decide in which means and cooling systems to use in order to cool the cows.
The livestock may be selected from the group of:
Cows;
Chicken;
- Pigs; Sheep;
Other livestock animals.
Alert may be sent when the LSI is above a predetermined threshold and automatic cooling systems are being operated.
In one aspect, data from sensors such as microphones, gas sensors, voice and breathing sensors is added to the calculation of the LSI.
A system for detecting and alerting actual or impending heat stress in livestock, and especially in cows, which comprises: a) array of thermal sensors placed sufficiently high above ground of a cowshed, which consists of at least Infra-Red thermal cameras; b) external temperature sensor hanging in the air, placed at a predetermined distance away from the thermal camera lens inside the camera's field of view; c) humidity sensor that measures the environmental humidity; d) a dedicated software module configured to preform image processing algorithms in order to calculate the temperature representing the thermal energy level, for all pixels in the image, and consequently performing calibration for all the pixels in the image; and e) a dedicated software module configured to perform continuously measurements of temperature, ambient heat load and physiological measurements from the cows, continuously and at a constant rate, which enable to monitor the energy that the cow produces, and at the same time monitor the herd's ability to cool itself by releasing heat energy to the environment, by calculating an LSI.
A method for detecting and alerting fever in a group of people, comprising the steps of: a) placing at least one thermal imager (IR camera) having a predetermined FOV for capturing a location of the group; b) installing a temperature calibration sensor at a predetermined distance from the camera; c) averaging the pixels value in the vicinity of the calibration sensor and the temperature reading is assigned to the average value; d) upon detecting movement of people in the FOV, continuously calibrating all pixels in FOV to the average value, according to the temperature reading of the calibration sensor; e) filtering out all pixels that belong to stationary objects and areas on the people that are irrelevant to the calculation of the people temperature; f) calculating the NITM representing the average thermal energy of the group that is detected in the cameras' FOV; g) calculating NITM values with respect to Ta, while for NITM values that exceed a predetermined threshold, optionally considering the Temperature Humidity Index (THI); h) storing the calculated results; and i) repeating the preceding steps after a predetermined time.
In case of exceeding a predetermined threshold, the system can differentiate between faces of persons in the FOV and indicate a person with deviation.
The system may further comprise: a) a plurality of positioning tags that are attached to each individual animal; b) a deployed array of receivers that are located in fixed locations in the transportation vehicle, for receiving data from each tag in different timing and calculating the actual 3-D position of each animal in real-time in the transportation platform; and c) a processor and dedicated software for performing environmental and physiological data fusion of the data collected from the remote sensing platforms and the locating tags, to provide information about the actual status of each individual animal's welfare and/or suspicious disease and/or stress condition.
The output signal may be wirelessly transmitted by a local controlling gateway and cellular transmission module to a dedicated mobile/permanent console in the team cabin, for allowing the team to take care of the livestock in the in the most beneficial way.
The system may further comprise autonomous control of cooling/heating device like ventilators, water sprinkles or heating systems, for a closed loop autonomous operation.
The collected data may be uploaded in real-time to a database for remotely controlling of the monitored fleet and for performing big-data analysis.
The system may further comprise a local monitoring console, which receives the data collected from all sensing platforms and processes the data to obtain indications regarding impending distress of each individual animal and provide local alerts.
The data collected from all sensing platforms may be transmitted to a remote data analysis service for further analysis and providing analysis results to a command and control center, for generating and pushing alerts, presenting data at real-time and generating reports.
Brief Description of the Drawings
The above and other characteristics and advantages of the invention will be better understood through the following illustrative and non-limitative detailed description of preferred embodiments thereof, with reference to the appended drawings, wherein:
Fig. 1 illustrates a side view of the system proposed by the present invention;
Fig. 2 illustrates the field of view of the IR camera which includes the temperature sensor for real-time calibration; Fig. 3 is a flowchart of the steps for LSI calculation process, according to an embodiment of the invention;
Fig. 4 is a flow chart of the process of calculating LSI values for various conditions defined by different combinations of Ta, NITM and THI;
Fig. 5 is an illustration of livestock transportation in a truck, according to another embodiment of the present invention;
Fig. 6 is an illustration of the system architecture; and
Fig. 7 is an illustration of livestock transportation in truck in a time of during unloading and during the transportation (during a ride).
Detailed Description of the Present Invention
The present invention proposes a system and method for detecting and alerting actual or impending heat stress in livestock in cowsheds and during transportation., and especially in cows. The system performs accurate temperature measurement (with a deviation of approximately ±0.25 °C).
Fig. 1 illustrates a cowshed with the system proposed by the present invention. The system includes an array of sensors (such as temperature sensors, IR sensors, microphones and humidity sensors) placed sufficiently high above ground (e.g. on the roof or on posts) of a cowshed, which consists Infra-Red thermal cameras with real-time temperature calibration software that capture an image of herd of cows and continuously measure the surface temperature of preterminal limbs of the cows' bodies that provide accurate indications regarding the core temperature of the cow. The temperature measurement is based on image processing and the pixel analysis of the image to determine the temperature of each pixel. The system uses an external temperature sensor that is positioned at a predetermined distance (for example, about 30 to 40 cm) away from the thermal camera lens inside the camera's field of view (FOV), where the sensor itself may be hanged in the air and the camera staring at it, as illustrated in Fig. 2. This temperature sensor is used as a reference point to continuously calibrate all pixels in the image, since its temperature is equal to the ambient temperature.
A dedicated software examines the pixels near the temperature sensor in terms of their thermal energy level. Then, using the average temperature of these pixels from the sensor's area, calibration is performed and the temperature (thermal energy level) is calculated for all pixels in the image. Then, the system measures and calculates the average thermal energy of a herd of cows that were detected in the cameras' field of view, which is defined as a Non- Invasive Temperature Measurement (NITM). While calibrating pixels with accurate temperature data, the system selects only the interesting areas in the image, i.e. the relevant pixels such as gutters and eyes that indicate the cow's core temperature (the core temperature is the temperature inside the cow, which is an emulation of an invasive temperature measurement such as using anal measurement by a thermometer. The core temperature indicates the entire state of the cow and how it feels). All other uninteresting pixels are considered to be noise (do not give valuable information), and they are been filtered out, for example: Iron railings in the cowshed that emit heat, wet hair and wet soil, areas in the cow with a minority of blood vessels such as a cow's back, pixels that had no thermal changes over time, etc. Then, by using image processing algorithms, the dedicated software chooses only the pixels that have a good correlation with the core temperature of the cow. These correlative pixels provide information about the thermal state of the entire cow.
The system builds a temperature histogram for the herd of cows and takes only the pixels above a certain predetermined temperature threshold. The pixels above the threshold are considered relevant and the rest of the pixels are defined as noise. For the high temperatures in the histogram above the threshold, the system calculates the average temperature derived from the upper part (that corresponds to higher temperatures) for each column in the histogram, by a predetermined percentage, and the rest of them are been filtered out. These average values indicate the core temperature of a cow in real time and the average value of all these averages is the indication of the core temperature of the herd in the image.
The system also includes additional sensors: a humidity sensor that measures the environmental humidity (for calculating the environmental heat load), and when it comes to other livestock, such as chicken and pigs (and possibly, other animals) , microphones are also placed to hear the sounds of the animals, from which one can learn about the state of the animals and how they feel. The dedicated software calculates the ability of the cow to dissipate heat to the environment by calculating the temperature gradient between the surface of the cow and the ambient heat load. If the gradient is large, that means the cow's heat dissipation ability is good. If the gradient is small, it is difficult for the cow to release heat (energy) into the environment and then it begins to warm up and feel uncomfortable. Since a cow naturally does not sweat in a level which is sufficient for effective cooling, so it has difficulty releasing energy to the environment.
According to the thermal energy of the herd and the calculation the above gradient, the system estimates the thermal state of the herd. The estimate is made as a score ranging, for example, from 1 to 10, where 1 means that the herd is very comfortable and 10 means that the herd is in a heat stroke/stress situation.
It should be noted that the score may range between different limits, which are defined by the dedicated software, in order to provide rates indications regarding extreme states of the herd.
Measurements of temperature, ambient heat load and calibration are repeated continuously at a constant rate. From the one hand, the energy that the cow produces is monitored and the indication regarding the herd's core temperature is obtained, and from the other hand, the herd's ability to cool itself (by releasing heat energy to the environment) is measured. Natural or artificial air movements in the vicinity of the animals is also considered in the measurements made (such that their contribution to the cooling of the animals is reflected).
The physiological state of the cows (such as age, health status, etc.) also affects their ability to cool themselves. This data might also be considered by the dedicated software, along with the ambient temperature, humidity, ambient heat load and physiological measurements from the cows. The system then creates a new index called LSI (Livestock Stress Index) which gives an indication from 1 to 10 (status table) of the thermal state of the herd. It is actually the new output provided by the system and may be used by the coward to learn about the thermal status of the herd of cows. By using the LSI, the coward decides in which means and cooling systems to use in order to cool the cows.
The proposed algorithm for calculating and outputting an LSI:
Tables 1-3 illustrate the calculation of the LSI for several values of NITM with respect to the ambient temperature Ta:
Figure imgf000014_0001
Table 1
Table 1 illustrates the LSI calculated values as a function of several measured NITMs for a state for which NITM < 37°C and NITM -Ta > 4°C. In this state, there is a relatively larger difference between the measured NITM and the ambient temperature (i.e., there is a larger temperature gradient) and therefore, the ability of the herd to dissipate heat to the ambient increases. In this state, the herd will not be in distress and the chance to get into a state of heat stress will be low. This can be seen from the LSI values of Table 1, where the calculated LSI values for NITM values ranging between 33-37 °C are between 1-5.
Figure imgf000015_0001
Table 2
Table 2 illustrates the LSI calculated values as a function of several measured NITMs for a state for which NITM < 37°C and NITM -Ta < 4°C.
In this state, there is a smaller difference between the measured NITM and the ambient temperature (i.e., there is a smaller temperature gradient) and therefore, the ability of the herd to dissipate heat to the ambient is limited. In this state, the chance to get into a state of heat stress will be slightly higher. This can be seen from the LSI values of Table 2, where the calculated LSI values for NITM values ranging between 33-37 °C are between 1-6, respectively.
Figure imgf000016_0001
Table 3
Table 3 illustrates the LSI calculated values as a function of several measured NITMs for a state for which NITM < 37°C and NITM -Ta < 2°C.
In this state, there is a relatively small difference between the measured NITM and the ambient temperature (i.e., there is a very small temperature gradient) and therefore, the ability of the herd to dissipate heat to the ambient further decreases. In this state (which is more extreme), it is likely that the herd will be in distress when NITM exceeds 35 °C. This can be seen from the LSI values of Table 3, where the calculated LSI values for NITM values ranging between 33-37 °C are between 1-7, respectively.
Figure imgf000016_0003
Figure imgf000016_0002
Table 4a table 4b
Tables 4a and 4b illustrate the LSI calculated values as a function of several measured NITMs for a state for which NITM > 37°C, while considering both NITM and Temperature Humidity Index (THI -a combination of temperature and humidity that is a measure of the degree of discomfort experienced by an individual in warm weather. Most people are quite comfortable when the index is below 70 and very uncomfortable when the index is above 80 to 85) values.
In this state, the ability of the herd to dissipate heat to the ambient is strongly dependent of the THI value, which is indicative of the level of heat load. This can be seen from the LSI values of Table 4a, where the calculated LSI values for THI values ranging between 72 and 82 are between 6-10, respectively. In addition, Table 4b shows the calculated LSI values for NITM values ranging between 38-40 °C are between 6-10, respectively. According to the invention, when the heat level increases such that NITM > 37°C, the LSI value is selected to be the highest value from both Table 4a and 4b. For example, if the THI is 72 the LSI value of Table 4a is 6. However, if at the same time the NITM is 39.5 °C, the cellulated LSI value of Table 4b is 9. Then, the final selected LSI value will be 9.
Fig. 3 is a flowchart of the steps for LSI calculation process, according to an embodiment of the invention. At the first step 301, at least one thermal imager (IR camera) having a predetermined FOV is placed for capturing a location of a herd of livestock. At the next step 302, a temperature calibration sensor is installed at a predetermined distance from the camera. At the next step 303, the pixels value in the vicinity of the calibration sensor is averaged and the temperature reading is assigned to the average value. At the next step 304, upon detecting movement of livestock in the FOV, all pixels in FOV are continuously calibrated to the average value, according to the temperature reading of the calibration sensor. At the next step 305 all pixels that belong to stationary objects and areas on the animals that are irrelevant to the calculation of the animal's core temperature are filtered out. At the next step 306, the NITM representing the average thermal energy of the herd of livestock detected in the camera's FOV is calculated. At the next step 307, LSI value are calculated as a function of NITM values and Ta, while for NITM values that exceed a predetermined threshold, LSI value are calculate as a function Temperature Humidity Index (THI) and choose the highest value of LSI of both calculations. At the next step 308 the chosen LSI results are stored. This process is repeated at step 309, after a predetermined time delay.
Fig. 4 is a detailed flow chart of the process of calculating LSI values for various conditions defined by different combinations of Ta, NITM and THI, according to another embodiment of the invention. At step 100, the system checks if the NITM (Non-lnvasive Temperature Measurement) is < 37. If no, at the next step 122, the system checks if the THI (Temperature Humidity Index) is < 75. If yes, at the next step 101, the system checks if the NITM- AmbientTemperature³MaximalGradiemt (4°C). If no, at the next step 143, the system checks if the NITM-AmbientTemperature<MaximalGradient and also if the NITM-
AmbientTemperature³MinimalGradient (2°C). If yes, at the next step 102, the system checks if the NITM<37 and also if the NITM>36. If yes, at the next step 120, the LSI is determined as 5. If no, at the step 103, the system checks if the NITM<36 and also if the NITM>35. If yes, at the next step 107, the LSI is determined as 4. If no, at the step 104, the system checks if the NITM<35 and also if the NITM>34. If yes, at the next step 108, the LSI is determined as 3. If no, at the step 105, the system checks if the NITM<34 and also if the NITM>33. If yes, at the next step 106, the LSI is determined as 2.
If no, at the step 109, the system checks if the NITM<33. If yes, at the next step 110, the LSI is determined as 1.
At step 101, the system checks if the NITM-AmbientTemperature³MaximalGradiemt (4 °C). If no, at the next step 143, the system checks if the NITM-
AmbientTemperature<MaximalGradient and also if the NITM- AmbientTemperature>MinimalGradient. If yes, atthe next step 111, the system checks if the NITM<37 and also if the NITM>36. If yes, at the next step 115, the LSI is determined as 6. If no, at the step 112, the system checks if the NITM<36 and also if the NITM>35. If yes, at the next step 120, the LSI is determined as 5. If no, at the step 113, the system checks if the NITM<35 and also if the NITM>34. If yes, at the next step 107, the LSI is determined as 4. If no, at the step 114, the system checks if the NITM<34 and also if the NITM>33. If yes, at the next step 108, the LSI is determined as 3. If no, at the step 109, the system checks if the NITM<33. If yes, at the next step 110, the LSI is determined as 1. At step 143, the system checks if the NITM-AmbientTemperature<MaximalGradient and also if the NITM- AmbientTemperature>MinimalGradient. If no, at the next step 116, the system checks if the NITM-AmbientTemperature<MinimalGradient.
At step 100, the system checks if the NITM (Non-lnvasive Temperature Measurement) is <37. If no, at the next step 122, the system checks if the THI (Temperature Humidity Index) is < 75. If yes, at the next step 144, the system checks if the NITM- AmbientTemperature<MinimalGradient. If no, at the next step 146 the THI_LSI variable is assigned with the value of 6. If yes, at the next step 144 the THM.SI variable is assigned with the value of 7.
At the step 122, the system checks if the THI (Temperature Humidity Index) is < 75. If no, at the next step 123 the system checks if the THI>75 and also if the THI<78. If yes, at the next step 144 the THI_LSI variable is assigned with the value of 7. If no, at the next step 124 the system checks if the THI>78 and also if the THI<80. If yes, at the next step 125 the THI_LSI variable is assigned with the value of 8. If no, at the next step 126 the system checks if the THI>80 and also if the THI<82. If yes, at the next step 127 the THM.SI variable is assigned with the value of 9. If no, at the next step 128 the system checks if the THI>82. If yes, at the step 129 the THM.SI variable is assigned with the value of 10.
At the step 130, the system checks if the NITM< 38. If yes, at the next step 129 the NITM_LSI variable is assigned with the value of 6. If no, at the next step 132, the system checks if the NITM>38 and also if NITM<38.5. If yes, at the next step 139 the NITM_LSI variable is assigned with the value of 7. If no, at the next step 133, the system checks if the NITM>38.5 and also if NITM<39. If yes, at the next step 134 the NITM_LSI variable is assigned with the value of 8. If no, at the next step 135, the system checks if the NITM>39 and also if NITM<40. If yes, at the next step 136 the NITM_LSI variable is assigned with the value of 9. If no, at the next step 137 the system checks if the NITM>40. If yes, at the next step 138 the NITM_LSI variable is assigned with the value of 10. At the step 130, the system checks if the THI_LSI³NITM_LSI. If yes, at the next step 141, the LSI is determined asTHI_LSI. If yes, at the next step 142, the LSI is determined as NITM_LSI.
According to another embodiment of the present invention, it is also possible to alert when the herd's thermal state (LSI) exceeds a certain number and if necessary, activate automatic cooling systems for cooling the herd of the cows.
According to another embodiment, the proposed method and system may be used for remotely sensing, in real time, persons who have fever in order to monitor and control epidemics. In this case, the system including IR cameras and associated calibration temperature sensors may be deployed in strategic points such as airports, bus stations and train stations to continuously capture images of crowd in their field of view. For example, a group of passengers coming from the same geographical zone may be analyzed, to detect abnormal average fever among the group members. This may help the official authorities such as the immigration authority to control the movement of persons who may be epidemic carriers, due to their body temperature.
According to another embodiment of the present invention, a non-invasive remote monitoring system for early detection of potential stress situation of livestock during transportation process is proposed.
Fig. 5 is an illustration of a remote monitoring system operated during livestock transportation in a truck. The system includes a cooling/chilling system 12 and a remote sensing platform 11 which is installed in such a way that it can monitor the animals in a certain level/cage positioned in any transportation platform like a truck, a train or a vessel. The sensing platform continuously collects data regarding the physiological parameters of the animals which are positioned in its field of view and also collect data about the environmental conditions in the monitored area.
A small locating tags such as Ultra-Wide Band (UWB) Positioning Tags 13, are attached to each induvial animal and a deployed array of receivers 14 (that are located in fixed locations in the transportation vehicle), receives data from each tag 13 in different timing and by using triangulation, calculates the actual 3-D position of each animal in real-time in the transportation platform.
The proposed system performs data fusion of the collected data from the remote sensing platform 11 (environmental and physiological data) and the locating tags 13, in order to provide information about the actual status of each individual animal's welfare and/or suspicious disease and/or stress condition.
All the collected data is being filtered, analyzed and processed by a local electronic board, using dedicated algorithms, which eventually output the LSI (livestock Stress Index) parameter and information about individuals, which might require extra attention by the team.
The output signal is wirelessly transmitted by a local controlling gateway and cellular transmission module 15 to a dedicated mobile/permanent console 16 in the team cabin, thereby allowing the team to take care of their livestock in the in the most beneficial way.
Also, the system can autonomously control any cooling device 12 like ventilators, water sprinkles or heating systems, for a closed loop autonomous operation.
The data can be uploaded in real-time to any relevant database for remotely controlling of the monitored fleet and for performing big-data analysis. By comparing the data collected simultaneously across all platforms, it is possible to extrapolate and calculate the exact horizontal location of any animal (x, y), and its height (z) to know whether it stands or lies down. Using real-time data collection, one can learn about the condition of the animal at any given moment: how long it has been standing and when, how long it has been lying/resting and when, how long it has been near the food stall, etc. For example, when one sees that a particular animal has not been eating for a long time, it may be under distress and needs to be treated.
This technology can be used extensively not just during transportation, but also in in cowsheds. The indication of the condition of the animals in the case of transport is done for the entire herd and for each animal separately (in the case of transport there is not a large amount of animals such as in a cowshed, for example, and therefore, the condition and behavior of each animal can be monitored separately).
Fig. 6 is an illustration of the system architecture which is adapted to be installed on a transportation platform, such as a truck. The system comprises a local monitoring console 16, which receives the data collected from all sensing platforms 11 and processing the data to obtain indications regarding impending distress of each individual animal and provide local alerts to a supervisor 17. The monitoring console 16 may be controlled by a user interface 18. In addition, the data collected from all sensing platforms 11 may be transmitted to a remote data analysis service 19 for further analysis. The analysis results may be forwarded to a command and control center 20, for generating and pushing alerts, presenting data at real-time and generating reports.
Fig. 7 is an illustration of livestock monitoring in a truck during loading, after loading and during transportation, by an array of sensing platforms 11 that are located at different observation points along the platform. It should be noted that even though the above examples have been directed to livestock, the system proposed by the present invention may be adapted to detect stress in many other cultivated animals and also in human beings. Also, the system is adapted to detect several kinds of stress that is reflected in temperature changes, such as stress that originates from a disease or panic (e.g., in case of a predator intrusion).
The above examples and description have of course been provided only for the purpose of illustrations, and are not intended to limit the invention in any way. As will be appreciated by the skilled person, the invention can be carried out in a great variety of ways, employing more than one technique from those described above, all without exceeding the scope of the invention.

Claims

1. A method for detecting and alerting actual or impending heat stress in livestock, comprising: a) placing at least one thermal imager (IR camera) having a predetermined FOV for capturing a location of a herd of livestock; b) installing a temperature calibration sensor at a predetermined distance from the camera; c) averaging the pixels value in the vicinity of the calibration sensor and the temperature reading is assigned to the average value; d) upon detecting movement of livestock in the FOV, continuously calibrating all pixels in FOV to said average value, according to the temperature reading of the calibration sensor; e) filtering out all pixels that belong to stationary objects and areas on the animals that are irrelevant to the calculation of an indication regarding the animal's core temperature; f) calculating the NITM representing the average thermal energy of the herd of livestock detected in the camera's FOV; g) calculating LSI value as a function of NITM values and Ta, while for NITM values that exceed a predetermined threshold, calculating LSI value as a function Temperature Humidity Index (THI) and choosing the highest value of LSI of both calculations; h) storing the chosen LSI results; and i) repeating the preceding steps after a predetermined time delay.
2. A method according to claim 1, comprising: a) placing an array of sensors, which consists of at least an Infra-Red thermal camera sufficiently high above ground of a cowshed; b) placing an external temperature sensor at a predetermined distance away from the thermal camera lens inside the camera's field of view, wherein the sensor itself hanging in the air in front of the camera lens; c) capturing an image of herd of cows in the cowshed; d) performing calibration using the pixels from the sensor's area, in which the temperature is equal to the temperature of the environment; e) calculating the temperature, i.e. the thermal energy level, for all pixels in the image, according to the performed calibration; f) selecting only the interesting areas in the image, i.e. the relevant pixels such as gutters and eyes that indicate the cow's core temperature inside the cow; g) filtering all other uninteresting pixels that are considered to be noise and do not give valuable information; h) building temperature histograms for the herd of cows using image processing ; and i) choosing from said histograms only the pixels that have a good correlation with the core temperature of the cow by the dedicated software; j) for the high temperatures in the histogram above said threshold, calculating the average of the upper part for each column in the histogram, by a predetermined percentage, which indicates the core temperature of a cow in real time; and k) calculating the average of all these averages, which is the core temperature of the herd in the image.
3. A method according to claim 2, further comprising: a) placing a humidity sensor that measures the environmental humidity, for calculating the environmental heat load; b) using algorithms, calculating the ability of the cow's heat dissipation to the environment by the dedicated software, by calculating the temperature gradient between the surface of the cow and the ambient heat load; c) estimating the thermal state of the herd according to said temperature gradient calculation as a number ranging between a lower limit that means that the herd is very comfortable and an upper limit that means that the herd is in a heat stroke/stress situation; d) continuously measuring temperature, ambient heat load and calibration, and at a constant rate, for monitoring the energy that the cow produces and obtaining indication regarding the herd's core temperature on the one hand, and from the other hand, at the same time monitoring the herd's ability to cool itself by releasing heat energy to the environment; and e) calculating the LSI while considering the ambient temperature, humidity, ambient heat load and said physiological measurements from the cows, at a predetermined range of the thermal state of the herd, according to which the coward can use to decide in which means and cooling systems to use in order to cool the cows.
4. A method according to claim 1, wherein the livestock is selected from the group of:
Cows;
Chicken;
- Pigs;
Sheep;
Other livestock animals.
5. A method according to claim 2, wherein alert is being sent when the LSI is above a predetermined threshold and automatic cooling systems are being operated.
6. A method according to claim 1, wherein data from voice and breathing sensors is added to the calculation of the LSI.
7. A system for detecting and alerting actual or impending heat stress in livestock, and especially in cows, comprising: a) an array of thermal sensors placed sufficiently high above ground of a cowshed, which consists of at least Infra-Red thermal camera; b) an external temperature sensor hanging in the air, placed at a predetermined distance away from the thermal camera lens inside the camera's field of view; c) A humidity sensor that measures the environmental humidity; d) a dedicated software module configured to preform image processing algorithms in order to calculate the temperature representing the thermal energy level, for all pixels in the image, and consequently performing calibration for all the pixels in the image; and e) a dedicated software module configured to perform continuously measurements of temperature, ambient heat load and physiological measurements from the cows, continuously and at a constant rate, which enable to monitor the energy that the cow produces, and at the same time monitor the herd's ability to cool itself by releasing heat energy to the environment, by calculating an LSI.
8. A method for detecting and alerting fever in a group of people, comprising: a) placing at least one thermal imager (IR camera) having a predetermined FOV for capturing a location of said group. b) installing a temperature calibration sensor at a predetermined distance from the camera; c) averaging the pixels value in the vicinity of the calibration sensor and the temperature reading is assigned to the average value; d) upon detecting movement of people in the FOV, continuously calibrating all pixels in FOV to said average value, according to the temperature reading of the calibration sensor; e) filtering out all pixels that belong to stationary objects and areas on the people that are irrelevant to the calculation of the people temperature; f) calculating the NITM representing the average thermal energy of said group that is detected in the cameras' FOV; g) calculating NITM values with respect to Ta, while for NITM values that exceed a predetermined threshold, optionally considering the Temperature Humidity Index (THI); -innun] h) storing the calculated results; and i) repeating the preceding steps after a predetermined time.
9. A system for detecting and alerting actual or impending heat stress in livestock during transportation on a moving platform, comprising: a) array of thermal sensors placed sufficiently high above the floor of said platform, which consists of a plurality of Infra-Red thermal cameras; b) external temperature sensor hanging in the air, placed at a predetermined distance away from each thermal sensor lens inside the camera's field of view; c) a humidity sensor that measures the environmental humidity; d) a dedicated software module configured to preform image processing algorithms in order to calculate the temperature representing the thermal energy level, for all pixels in the image, and consequently performing calibration for all the pixels in the image; and e) a dedicated software module configured to perform continuously measurements of temperature, ambient heat load and physiological measurements from the cows, continuously and at a constant rate, which enable to monitor the energy that the cow produces, and at the same time monitor the herd's ability to cool itself by releasing heat energy to the environment, by calculating an LSI.
10. A system according to claim 9, further comprising a cooling/chilling subsystem, which is activated after continuously collecting and analyzing data regarding the physiological parameters of the animals which are positioned in its field of view and data about the environmental conditions in the monitored area.
11. A system according to claim 9, further comprising: d) a plurality of positioning tags that are attached to each induvial animal; e) a deployed array of receivers that are located in fixed locations in the transportation vehicle, for receiving data from each tag in different timing and calculating the actual 3-D position of each animal in real-time in the transportation platform; and f) a processor and dedicated software for performing environmental and physiological data fusion of the data collected from the remote sensing platforms and the locating tags, to provide information about the actual status of each individual animal's welfare and/or suspicious disease and/or stress condition.
12. A system according to claim 9, in which output signal is wirelessly transmitted by a local controlling gateway and cellular transmission module to a dedicated mobile/permanent console in the team cabin, for allowing the team to take care of the livestock in the in the most beneficial way.
13. A system according to claim 9, further comprising autonomous control of cooling/heating devices like ventilators, water sprinkles or heating systems, for a closed loop autonomous operation.
14. A system according to claim 9, in which the collected data is uploaded in real-time to a database for remotely controlling of the monitored fleet and for performing big-data analysis.
15. A system according to claim 9, further comprising a local monitoring console, which receives the data collected from all sensing platforms and processes the data to obtain indications regarding impending distress of each individual animal and provide local alerts.
16. A system according to claim 9, in which the data collected from all sensing platforms is transmitted to a remote data analysis service for further analysis and providing analysis results to a command and control center, for generating and pushing alerts, presenting data at real-time and generating reports.
PCT/IL2020/050961 2019-09-03 2020-09-03 System and method for remotely detecting and alerting actual or impending stress in animals in corrals and during transportation WO2021044421A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
IL269105 2019-09-03
IL269105A IL269105A (en) 2019-09-03 2019-09-03 System and method for detecting and alerting actual or impending heat stress in livestock

Publications (1)

Publication Number Publication Date
WO2021044421A1 true WO2021044421A1 (en) 2021-03-11

Family

ID=74852284

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IL2020/050961 WO2021044421A1 (en) 2019-09-03 2020-09-03 System and method for remotely detecting and alerting actual or impending stress in animals in corrals and during transportation

Country Status (2)

Country Link
IL (1) IL269105A (en)
WO (1) WO2021044421A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113785783A (en) * 2021-08-26 2021-12-14 北京市农林科学院智能装备技术研究中心 Livestock grouping system and method
CN114342828A (en) * 2021-12-01 2022-04-15 中国科学院亚热带农业生态研究所 Neck-ring type wearable milk cow respiratory frequency real-time monitoring device
CN115619946A (en) * 2022-12-16 2023-01-17 山东超华环保智能装备有限公司 Risk monitoring method and device for medical waste refrigerator

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110054338A1 (en) * 2008-11-14 2011-03-03 Technion Research & Development Foundation Ltd. Device, system and method for monitoring heat stress of a livestock animal
US20150302241A1 (en) * 2012-12-02 2015-10-22 Agricam Ab Systems and methods for predicting the outcome of a state of a subject

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110054338A1 (en) * 2008-11-14 2011-03-03 Technion Research & Development Foundation Ltd. Device, system and method for monitoring heat stress of a livestock animal
US20150302241A1 (en) * 2012-12-02 2015-10-22 Agricam Ab Systems and methods for predicting the outcome of a state of a subject

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
PRAMOD KUMAR ET AL.: "INTEGRATION BETWEEN THE THERMAL STRESS INDEX (TGWB) AND THE LIVESTOCK STRAIN INDEX (LSI) AS A GUIDELINE FOR DAIRY FARMING IN TROPICAL CLIMATE", 30 April 2019 (2019-04-30) *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113785783A (en) * 2021-08-26 2021-12-14 北京市农林科学院智能装备技术研究中心 Livestock grouping system and method
CN113785783B (en) * 2021-08-26 2023-03-17 北京市农林科学院智能装备技术研究中心 Livestock grouping system and method
CN114342828A (en) * 2021-12-01 2022-04-15 中国科学院亚热带农业生态研究所 Neck-ring type wearable milk cow respiratory frequency real-time monitoring device
CN115619946A (en) * 2022-12-16 2023-01-17 山东超华环保智能装备有限公司 Risk monitoring method and device for medical waste refrigerator
CN115619946B (en) * 2022-12-16 2023-04-18 山东超华环保智能装备有限公司 Risk monitoring method and device for medical waste refrigerator

Also Published As

Publication number Publication date
IL269105A (en) 2021-03-25

Similar Documents

Publication Publication Date Title
WO2021044421A1 (en) System and method for remotely detecting and alerting actual or impending stress in animals in corrals and during transportation
US10195008B2 (en) System, device and method for observing piglet birth
US20200214266A1 (en) Domestic animal information management system, domestic animal barn, domestic animal information management program, and domestic animal information management method
US9894885B2 (en) Mobile animal surveillance and distress monitoring
Poikalainen et al. Infrared temperature patterns of cow's body as an indicator for health control at precision cattle farming.
EP2925121B1 (en) System and method for predicting the health outcome of a subject
CA2746485C (en) An animal monitoring system and method
JP6190750B2 (en) Excrement detection system, excrement detection method, and excrement detection program
EP3468353B1 (en) A garment
CA2850918C (en) Method and apparatus for detecting lameness in livestock
US20090074253A1 (en) Method and Apparatus for the Automatic Grading of Condition of Livestock
KR20160092538A (en) Livestocks management method and system using sensor and drone
US20110054338A1 (en) Device, system and method for monitoring heat stress of a livestock animal
EP3756458A1 (en) Weight determination of an animal based on 3d imaging
EP3503720B1 (en) Method and device to detect lameness of a cow
KR101568979B1 (en) Cattle monitoring system and method using depth information
KR102372107B1 (en) Image-based sow farrowing notification system
JP7410607B1 (en) Feeding management system and feeding management method
CN114926634A (en) Event detection method and device, equipment, system and medium
CN112484880A (en) Adaptive health monitoring device and health monitoring method
CN112261869A (en) Method and control unit for controlling a movable catch-up gate
Bahr et al. The ease of movement: how automatic gait and posture analysis can contribute to early lameness detection in dairy cattle

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: 20861411

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: 20861411

Country of ref document: EP

Kind code of ref document: A1