Livestock and poultry body temperature monitoring system and method with wearable sensors and infrared cameras

Abstract

The present disclosure relates to a livestock and poultry body temperature monitoring system and method with wearable sensors and infrared cameras. Different breeding area blocks are provided in a stereoscopic space of livestock and poultry houses themselves; each breeding area block is internally provided with livestock and poultry individuals; wearable temperature sensors are randomly worn according to a fixed proportion to form sentinel livestock and poultry individuals; infrared cameras acquire group infrared images on the basis of the breeding area blocks; both the wearable temperature sensors and the infrared cameras are in communication connection with a local server by means of a communication terminal; and the local server is in communication connection with a client by means of a cloud server. The method comprises the steps of data acquisition, data transmission and pre-processing, database construction and model training, state determination, data review, etc. By means of the present disclosure, the advantages of continuous and precise monitoring of wearable temperature sensor individuals and wide-area large-scale flexible monitoring of routing inspection of infrared cameras are integrated, thereby realizing body temperature monitoring and health assessment of groups in livestock and poultry houses at a relatively low cost in an unmanned breeding scenario.

Description

Livestock and poultry body temperature monitoring system and method using wearable sensors and infrared cameras Technical Field

[0001] The present invention relates to the field of livestock and poultry body temperature monitoring, and specifically to multi-source body temperature monitoring based on the combination of individual continuous monitoring by wearable temperature sensor sentinels and wide-area flexible inspections by infrared cameras, as well as a monitoring system and method for evaluating the body temperature health status of livestock and poultry and providing abnormal warnings. Background Art

[0002] Livestock and poultry are warm-blooded animals. Body temperature, as an important indicator of the physiological functions of livestock and poultry, can largely reflect the health status of livestock and poultry. In the actual breeding and production process, the earlier the individual's abnormal condition can be perceived and discovered and timely action can be taken, the more production losses can be reduced.

[0003] Traditional livestock farms often monitor individual body temperatures through random inspections, measuring anal temperatures to represent core body temperature. This is labor-intensive, can easily cause stress reactions in animals, and cannot achieve continuous monitoring. Currently, several temperature monitoring methods based on temperature sensors and infrared cameras have emerged. These methods can effectively detect individual body temperatures, but they all rely on a single threshold for temperature-based monitoring. This is a crude approach that ignores temperature variations due to growth stage and circadian rhythms, and fails to consider the temporal characteristics of temperature fluctuations. This leads to single-valued judgments and poor robustness, hindering the requirements of precision farming. For example, an animal with a high daytime body temperature that maintains its daytime temperature at night is actually abnormal, but a single threshold approach cannot classify it in this dimension. Furthermore, in the context of unmanned large-scale farming, the use of single temperature sensors is subject to data instability, such as detachment and failure. Using infrared cameras for single-use monitoring is costly, and the inspection approach cannot achieve continuous monitoring and obtain good temporal characteristics.

[0004] Summary of the Invention

[0005] In order to solve the problems existing in the background technology, the purpose of the present invention is to provide a livestock and poultry body temperature monitoring system and method that cooperates with wearable temperature sensor monitoring and infrared camera inspection. It integrates the continuous high-precision monitoring data of individual sentinel wearable temperature sensors with the multi-source temperature data of wide-area flexible inspection of infrared cameras, introduces time series features to construct a body temperature change model, and can realize livestock and poultry body temperature monitoring, health status feedback and abnormal warning.

[0006] The technical solution adopted by the present invention to solve its technical problem is:

[0007] 1. A livestock and poultry temperature monitoring system using a wearable sensor and an infrared camera:

[0008] Includes wearable temperature sensor, infrared camera, communication terminal, local server, cloud server and client;

[0009] The livestock and poultry house has different breeding area blocks set up in its own three-dimensional space. Each breeding area block contains livestock and poultry individuals. All livestock and poultry individuals in each breeding area block are randomly equipped with wearable temperature sensors in a fixed ratio to form sentinel livestock and poultry individuals. The infrared camera obtains infrared images of the group based on the breeding area block. The communication terminal is installed in the livestock and poultry house. The wearable temperature sensor and infrared camera are connected to the local server through the communication terminal, and the local server is connected to the client through the cloud server.

[0010] The infrared camera performs inspections along a preset infrared camera inspection route between breeding area blocks in the livestock and poultry house.

[0011] The livestock and poultry houses are divided into a specific number of breeding area blocks according to the three-dimensional spatial structure and numbered. Individuals are randomly selected as sentinels in a specific proportion within the breeding area blocks, and wearable temperature sensors are used to monitor the body temperature and health status of the group in the area.

[0012] The wearable temperature sensor has a battery voltage acquisition circuit and a wireless communication module for battery replacement prompts. The collected data is transmitted to the communication terminal through a wireless data transmission protocol.

[0013] 2. A method for monitoring livestock and poultry body temperature using a wearable sensor and an infrared camera, the method comprising the following steps:

[0014] S1: Data Acquisition

[0015] Wearable temperature sensors are used to obtain continuous body temperature data from a suitable number of sentinel livestock and poultry individuals in each breeding area. Infrared cameras are used to collect infrared thermal imaging images of all livestock and poultry individuals in each breeding area and the location of the breeding area blocks.

[0016] S2: Data transmission and preprocessing

[0017] The communication terminal transmits the continuous body temperature data and infrared thermal imaging data collected in step S1 to the local server respectively. The local server performs pre-processing of the data by screening and image segmentation to obtain body temperature values. The pre-processed body temperature values ​​are used to obtain a body temperature monitoring curve of each livestock and poultry individual that changes with time.

[0018] S3: Database construction and model training

[0019] Under different varieties, different growth stages, and different monitoring methods, the temperature monitoring curves obtained in step S2 are used to construct a growth stage-temperature database, and a normal temperature variation band (temperature time series variation model) is obtained by processing the growth stage-temperature database.

[0020] S4: Status determination and data review

[0021] The real-time collected temperature values ​​are combined with the normal body temperature change band to determine whether the body temperature status is abnormal by using time series matching and outlier discrimination methods. The breeding area where the livestock and poultry with abnormal body temperature status are located is identified as the abnormal area, and the infrared camera is moved to the abnormal area for re-inspection to achieve complete monitoring.

[0022] The step S2 is specifically as follows:

[0023] The continuous temperature data collected by the wearable temperature sensor is compared with the fluctuation range threshold to determine the abnormal value, and the individual abnormal value is eliminated but the continuous abnormal value is retained, and each temperature value obtained is retained as the body temperature value of the livestock and poultry individual;

[0024] The infrared thermal imaging images captured by the infrared camera are segmented using a deep learning method to identify each livestock and poultry individual in each breeding area. Each livestock and poultry individual in the breeding area is renumbered, and the key pixels and temperature information of each livestock and poultry individual in the image are extracted as the body temperature value of the livestock and poultry individual.

[0025] The body temperature value T directly monitored by the wearable temperature sensor and infrared camera s and T c The core body temperature value T is obtained according to the following formula sc 、T cc , the specific formula is as follows: T sc =a s T s +b s T cc =a c T c +b c

[0026] Among them, a s 、b s are the weight and correction constant of the wearable temperature sensor, a c 、b c are the weight and correction constant of the infrared camera respectively.

[0027] The step S3 specifically includes: obtaining body temperature values ​​by using a wearable temperature sensor and an infrared camera under different varieties, different growth stages, and different monitoring methods, and establishing normal body temperature change zones at different growth stages under the same variety and various monitoring methods.

[0028] During monitoring, the corresponding body temperatures at corresponding time series are established simultaneously using machine learning methods, which is different from the setting method of a single threshold to construct a normal body temperature change zone.

[0029] The monitoring method described refers to the location where the wearable temperature sensor is worn.

[0030] In step S3, abnormality determination mainly includes two steps:

[0031] Step 1: Compare the real-time collected temperature value with the normal body temperature variation range to determine whether the temperature value falls within the normal body temperature variation range:

[0032] If it does not fall into the range, the body temperature of the livestock and poultry corresponding to the temperature value is abnormal, and step 2 is performed;

[0033] If it falls, the body temperature of the livestock and poultry corresponding to the temperature value is normal, and step three is performed;

[0034] Step 2: Compare the temperature value with the range [μ-3σ, μ+3σ] determined by the following formula:

[0035] Where μ is the average temperature of the group, σ is the standard deviation of the group temperature, T cci is the body temperature value of the group monitored by wearable temperature sensors and infrared cameras, and n is the number of groups;

[0036] The groups are divided into two situations: all livestock and poultry individuals in a single breeding area block and all livestock and poultry individuals in all breeding area blocks. Comparison and judgment are made between the temperature values ​​of individual livestock and poultry and the group consisting of all livestock and poultry individuals in a single breeding area block, and between the temperature values ​​of individual livestock and poultry and the group consisting of all livestock and poultry individuals in all breeding area blocks:

[0037] If the temperature value is within the range [μ-3σ, μ+3σ], the body temperature state of the livestock and poultry corresponding to the temperature value is not abnormal;

[0038] If the temperature value is not within the range [μ-3σ, μ+3σ], the body temperature state of the livestock and poultry corresponding to the temperature value is abnormal;

[0039] Step 3: Select livestock and poultry with abnormal body temperature, move the infrared camera to the breeding area where the livestock and poultry with abnormal body temperature are located, re-inspect the livestock and poultry, and further monitor the abnormal situation.

[0040] Compared with the existing invention, the present invention has the following beneficial effects:

[0041] 1. This method and system uses two methods to monitor and evaluate the temperature conditions of individual and group livestock and poultry houses. It pre-processes the temperature data collected from multiple sources and can stably characterize and monitor their core temperature.

[0042] 2. This method optimizes the methods of body temperature monitoring and abnormality determination, introduces time series features, and constructs a body temperature time series change model based on breed, growth stage, and monitoring method. This method distinguishes itself from a single threshold determination method and more accurately identifies abnormal individuals.

[0043] 3. This method optimizes the methods of body temperature monitoring and abnormality determination, and proposes a big data-based outlier abnormality determination method that can effectively identify possible abnormal individuals;

[0044] 4. This method and system uses a farming area block and sentinel individual solution to assess individual and group status by monitoring sentinel status. The division of farming area blocks facilitates data analysis and rapid positioning.

[0045] 5. This method and system, along with the multi-source data collection of wearable sensors and infrared cameras, greatly reduces the possibility of system misjudgment and enables the acquisition of more stable and accurate body temperature data.

[0046] 6. Real-time body temperature monitoring can timely understand abnormalities of livestock and poultry, and take early prevention measures to avoid large-scale losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] FIG1 is a diagram showing steps of a method according to an embodiment of the present invention.

[0048] FIG2 is a schematic diagram of the system structure of an embodiment of the present invention.

[0049] In the figure: 1-livestock house, 2-infrared camera inspection route, 3-infrared camera, 4-breeding area block, 5-individual livestock and poultry, 6-wearable temperature sensor, 7-communication terminal, 8-local server, 9-cloud server, 10-client.

[0050] FIG3 is a schematic diagram of a comprehensive body temperature assessment workflow according to an embodiment of the present invention.

[0051] FIG4 is a comparison diagram of an embodiment of the present invention and a traditional body temperature monitoring method. DETAILED DESCRIPTION

[0052] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0053] As shown in Figure 2 , the system includes a wearable temperature sensor 6, an infrared camera 3, a communication terminal 7, a local server 8, a cloud server 9, and a client 10;

[0054] The livestock and poultry house 1 sets up different breeding area blocks 4 in its own three-dimensional space. There are livestock and poultry individuals 5 in each breeding area block 4. All livestock and poultry individuals 5 in each breeding area block 4 are randomly equipped with wearable temperature sensors 6 in a fixed ratio to form sentinel livestock and poultry individuals. The infrared camera 3 obtains group infrared images based on the breeding area block. The communication terminal 7 is installed in the livestock and poultry house 1. The wearable temperature sensor 6 and the infrared camera 3 are both connected to the local server 8 through the communication terminal 7, and the local server 8 is connected to the client 10 through the cloud server 9.

[0055] The infrared camera 3 performs inspections along a preset infrared camera inspection route 2 between the breeding area blocks 4 in the livestock and poultry house 1 .

[0056] The data collected by the wearable temperature sensor 6 and the infrared camera 3 are uploaded to the local server 8. The local server 8 or the cloud server 9 pre-processes the data and inputs the normal body temperature change band to determine the status of the livestock and poultry body temperature, quickly locate the breeding area blocks with abnormal livestock and poultry body temperature, and then the infrared camera 3 takes pictures of the breeding area blocks with abnormal livestock and poultry body temperature for review to complete the monitoring.

[0057] After review, the temperature data can be used to comprehensively evaluate the temperature health status of individuals and groups, and the results and warning information can be transmitted to the user through the client 10.

[0058] The livestock and poultry houses are divided into a specific number of breeding area blocks according to the three-dimensional spatial structure. Each breeding area block corresponds to a specific number. A specific number of livestock and poultry individuals in each breeding area block are defined as sentinel livestock and poultry individuals. Sentinel livestock and poultry individuals wear wearable temperature sensors to continuously monitor individual body temperature changes, directly and indirectly reflect the status of the group, and play the role of body temperature monitoring and early warning in the area.

[0059] The infrared inspection camera moves in the livestock and poultry house along the preset slide rails or tracks in the livestock and poultry house, taking one or more thermal images of each breeding area to collect the body temperature data of livestock and poultry. The image information also includes the positioning data and timing information of the breeding area block.

[0060] The wearable temperature sensor 5 has a battery voltage acquisition circuit and a wireless communication module for battery replacement prompts, and the collected data is transmitted to the communication terminal 7 via a wireless data transmission protocol.

[0061] The wearable temperature sensor 5 is coin-shaped and adopts a modular design. It can be stably worn on livestock and poultry with customized accessories such as silicone straps and silicone earrings, which is convenient to wear and can stably represent the location of the individual's body temperature, including but not limited to the underside of chicken wings and pig ears.

[0062] The wearable temperature sensor 5 continuously collects data, and the sampling frequency can be set according to actual needs. The collected information includes timing characteristics and location information. The data collected by the infrared camera 3 includes area information and corresponds to the timing characteristics of the data collected by the wearable temperature sensor 5.

[0063] Wearable temperature sensors monitor continuously 24 hours a day at a certain sampling frequency. The sampled data also includes time series characteristics and location information. Wearable temperature sensors are equipped with accessories and worn at locations on livestock and poultry that can stably represent the body temperature of the individual, including but not limited to the underwings of chickens and the ears of pigs.

[0064] Preset tracks for inspection infrared cameras in livestock and poultry houses, set inspection procedures for inspection infrared cameras according to the areas divided in advance, stay in the corresponding areas during inspections, and take at least one infrared thermal image that meets the requirements in the area, with the shooting angle minimizing obstructions;

[0065] Wearable temperature sensors and infrared cameras transmit the collected data to the communication terminal through a wireless data transmission protocol. The data contains timing characteristics and location information. The communication terminal uploads the data to the server at a certain time frequency. The collected data can be processed by a locally deployed server or directly uploaded to a cloud server for processing. It can be flexibly arranged according to actual conditions.

[0066] In actual deployment, the system can flexibly arrange local servers and cloud servers to facilitate local processing and offline processing, flexibly selecting solutions to improve computing efficiency and reduce costs. If the local server 8 has sufficient computing power, the collected data can be processed directly offline. Otherwise, the data can also be processed directly on the cloud server 9.

[0067] In actual application, the system uses temperature data from temperature sensors, infrared cameras, and multiple sources. After pre-processing, it tracks abnormal individuals based on two abnormality determination methods, verifies the data using infrared camera data, and integrates an expert system to further diagnose abnormal objects and provide feedback to users.

[0068] During actual application, the system can continuously optimize the body temperature model based on the collected data to improve the stability of system use.

[0069] The implementation process of the present invention is as follows:

[0070] S1: Data Acquisition

[0071] Wearable temperature sensors 6 are used to obtain continuous high-precision body temperature data of a suitable number of sentinel livestock and poultry individuals in the breeding area block 4. Infrared cameras 3 are used to collect infrared thermal imaging images of all livestock and poultry individuals in each breeding area block 4 and the location of the breeding area block 4, thereby covering infrared thermal imaging data and positioning data of more livestock and poultry animals.

[0072] S2: Data transmission and preprocessing

[0073] The communication terminal 7 transmits the continuous body temperature data and infrared thermal imaging data collected in step S1 to the local server 8. The local server 8 filters the data and performs image segmentation preprocessing to obtain body temperature values. Specifically, the image segmentation is to segment the head of the livestock and poultry. The preprocessed body temperature values ​​are processed to obtain a body temperature monitoring curve of each livestock and poultry individual that changes over time.

[0074] S3: Database construction and model training

[0075] Under different varieties, different growth stages, and different monitoring methods, the temperature monitoring curves obtained in step S2 are used to construct a growth stage-temperature database, and a normal temperature variation zone is obtained by processing the growth stage-temperature database;

[0076] S4: Status determination and data review

[0077] The real-time collected temperature values ​​are combined with the normal body temperature change band to determine whether the body temperature status is abnormal by using time series matching and outlier discrimination. The breeding area block 4 where the livestock and poultry with abnormal body temperature status are located is determined as the abnormal area, and the infrared camera 3 is moved to the abnormal area for re-inspection to achieve complete monitoring.

[0078] Finally, the temperature data can be integrated to provide evaluation and feedback on the body temperature health status of the group in each breeding area of ​​the livestock and poultry house.

[0079] Step S2 is specifically as follows: comparing the continuous temperature data collected by the wearable temperature sensor with the fluctuation range threshold to determine abnormal values, eliminating individual abnormal values ​​but retaining continuously occurring abnormal values, and retaining each obtained temperature value as the body temperature value of the livestock and poultry individual; retaining continuously occurring abnormal values ​​means that the abnormal values ​​appear for 5 consecutive times or for more than 15 minutes.

[0080] The infrared thermal imaging images captured by the infrared camera are segmented using a deep learning method to identify each livestock and poultry individual in each breeding area. Each livestock and poultry individual in the breeding area is renumbered, and the key pixels and temperature information of each livestock and poultry individual in the image are extracted as the body temperature value of the livestock and poultry individual.

[0081] The body temperature value T directly monitored by the wearable temperature sensor and infrared cameras and T c The core body temperature value T is obtained according to the following formula sc 、T cc , the specific formula is as follows: T sc =a s T s +b s T cc =a c T c +b c

[0082] Among them, a s 、b s are the weight and correction constant of the wearable temperature sensor, a c 、b c are the weight and correction constant of the infrared camera respectively. The values ​​of a and b are pre-set according to the monitored object and monitoring method.

[0083] Step S3 is specifically as follows: under different varieties, different growth stages, and different monitoring methods, the body temperature values ​​are collected by the wearable temperature sensor 6 and the infrared camera 3, and the normal body temperature change band of the same variety and different growth stages under various monitoring methods is established through statistical processing. The normal body temperature change band includes an upper curve and a lower curve as a body temperature time series change model.

[0084] Specifically:

[0085] Step 1: Compare the real-time collected temperature value with the normal body temperature variation range to determine whether the temperature value falls within the normal body temperature variation range:

[0086] If it does not fall into the range, the body temperature of the livestock and poultry corresponding to the temperature value is abnormal, and step 2 is performed;

[0087] If it falls, the body temperature of the livestock and poultry corresponding to the temperature value is normal, and step three is performed;

[0088] Step 2: Compare the temperature value with the range [μ-3σ, μ+3σ] determined by the following formula to determine the outlier:

[0089] Where μ is the average temperature of the group, σ is the standard deviation of the group temperature, T cci is the body temperature value of the group monitored by wearable temperature sensors and infrared cameras, and n is the number of groups;

[0090] The groups are divided into two situations: all livestock and poultry individuals in a single breeding area block and all livestock and poultry individuals in all breeding area blocks. The temperature values ​​of individual livestock and poultry and the group composed of all livestock and poultry individuals in a single breeding area block, and the temperature values ​​of individual livestock and poultry and the group composed of all livestock and poultry individuals in all breeding area blocks are compared and judged according to the above range [μ-3σ, μ+3σ]:

[0091] If the temperature value is within the range [μ-3σ, μ+3σ], the body temperature state of the livestock and poultry corresponding to the temperature value is not abnormal;

[0092] If the temperature value is not within the range [μ-3σ, μ+3σ], the body temperature state of the livestock and poultry corresponding to the temperature value is abnormal;

[0093] As shown in the embodiment of FIG4 , compared with the traditional body temperature monitoring method that sets a fixed threshold, this method can identify abnormal individuals at least 10 hours in advance.

[0094] Step 3: Select livestock and poultry with abnormal body temperature, mobilize the infrared camera to move to the breeding area block 4 where the livestock and poultry with abnormal body temperature are located to re-inspect the livestock and poultry, and further monitor the abnormal situation.

[0095] It can be seen that the present invention sets up breeding area blocks and sentinel livestock and poultry individuals, and adopts two methods to monitor and evaluate the body temperature status of individuals and groups in livestock and poultry houses. It can stably characterize and monitor their core temperature, which is helpful to quickly and stably locate and analyze the group status; optimize the method of body temperature monitoring and abnormality judgment, introduce time series characteristics, and construct a growth stage-temperature body temperature time series change model. At the same time, a big data-based outlier abnormality judgment method is proposed, which can effectively lock possible abnormal individuals; multi-source data acquisition and infrared camera review can obtain more stable and accurate body temperature data, greatly reducing the possibility of system misjudgment; real-time body temperature monitoring can timely understand livestock and poultry abnormalities, and take early precautions to avoid large-scale losses.

Claims

1. A livestock and poultry body temperature monitoring system using a wearable sensor and an infrared camera, characterized in that: It includes a wearable temperature sensor (6), an infrared camera (3), a communication terminal (7), a local server (8), a cloud server (9) and a client (10); A livestock and poultry house (1) is provided with different breeding area blocks (4) in its own three-dimensional space. Each breeding area block (4) contains livestock and poultry individuals (5). All livestock and poultry individuals (5) in each breeding area block (4) are randomly equipped with wearable temperature sensors (6) in a fixed ratio to form sentinel livestock and poultry individuals. An infrared camera (3) obtains infrared images of the group based on the breeding area blocks. A communication terminal (7) is installed in the livestock and poultry house (1). The wearable temperature sensor (6) and the infrared camera (3) are both connected to a local server (8) through the communication terminal (7). The local server (8) is connected to a client (10) through a cloud server (9).

2. The livestock and poultry body temperature monitoring system using a wearable sensor and an infrared camera according to claim 1 is characterized in that: The infrared camera (3) performs inspections along a preset infrared camera inspection route (2) between breeding area blocks (4) in the livestock and poultry house (1).

3. The livestock and poultry body temperature monitoring system using a wearable sensor and an infrared camera according to claim 1 is characterized in that: The wearable temperature sensor (6) has a battery voltage collection circuit and a wireless communication module for battery replacement prompts, and the collected data is transmitted to the communication terminal 7 through a wireless data transmission protocol.

4. A livestock and poultry body temperature monitoring method using a wearable sensor and an infrared camera in coordination with the livestock and poultry body temperature monitoring system according to any one of claims 1 to 3, characterized in that the method The following steps are involved: S1: Data Acquisition The continuous body temperature data of a suitable number of sentinel livestock and poultry individuals in the breeding area block (4) are obtained through wearable temperature sensors (6), and the infrared thermal imaging images of all livestock and poultry individuals in each breeding area block (4) and the positions of the breeding area blocks (4) are collected through infrared cameras (3); S2: Data transmission and preprocessing The communication terminal (7) transmits the continuous body temperature data and infrared thermal imaging data collected in step S1 to the local server (8), and the local server (8) performs preprocessing of screening and image segmentation on the data to obtain body temperature values, and uses the preprocessed body temperature values ​​to obtain a body temperature monitoring curve of each livestock and poultry individual that changes with time series; S3: Database construction and model training Under different varieties, different growth stages and different monitoring methods, the temperature monitoring curves obtained in step S2 are used to construct a growth stage-temperature database. Get the normal body temperature change zone; S4: Status determination and data review The real-time collected temperature values ​​are combined with the normal temperature variation band to determine whether the temperature status is abnormal by using time series matching and outlier discrimination. The breeding area block (4) where the livestock and poultry with abnormal temperature status are located is determined as the abnormal area, and the infrared camera (3) is moved to the abnormal area for re-inspection to achieve complete monitoring.

5. The livestock and poultry body temperature monitoring method using a wearable sensor and an infrared camera according to claim 4 is characterized in that: The step S2 is specifically as follows: The continuous temperature data collected by the wearable temperature sensor is compared with the fluctuation range threshold to determine the abnormal value, and the individual abnormal values ​​are eliminated but the continuous abnormal values ​​are retained, and each temperature value obtained is retained as the body temperature value of the livestock and poultry individual; The infrared thermal imaging images captured by the infrared camera are segmented by deep learning methods to identify each livestock and poultry individual. Each livestock and poultry individual in the breeding area block is renumbered, and the key pixel points and temperature information of each livestock and poultry individual in the image are extracted as the body temperature value of the livestock and poultry individual. The body temperature value T directly monitored by the wearable temperature sensor and infrared camera s and T c The core body temperature value T is obtained according to the following formulas: sc , T cc , the specific formula is as follows: T sc =a s T s +b s T cc =a c T c +b c Among them, a s , b s are the weight and correction constant of the wearable temperature sensor, a c , b c are the weight and correction constant of the infrared camera respectively.

6. The livestock and poultry body temperature monitoring method using a wearable sensor and an infrared camera according to claim 4 is characterized in that: The step S3 specifically comprises: in the case of different varieties, different growth stages and different monitoring methods, the body temperature values ​​are collected by a wearable temperature sensor (6) and an infrared camera (3), and a normal body temperature variation zone is established for different growth stages of the same variety and various monitoring methods.

7. The livestock and poultry body temperature monitoring method using a wearable sensor and an infrared camera according to claim 4 is characterized in that: In step S4, the abnormality determination mainly includes two steps: Step 1: Compare the real-time collected temperature value with the normal body temperature variation range to determine whether the temperature value falls within the normal body temperature variation range: If it does not fall into the range, the body temperature state of the livestock and poultry corresponding to the temperature value is abnormal, and step 2 is performed; If it falls into, the body temperature state of the livestock and poultry corresponding to the temperature value is normal, and step three is performed; Step 2: Compare the temperature value with the range [μ-3σ, μ+3σ] determined by the following formula: Where μ is the average temperature of the group, σ is the standard deviation of the group temperature, T cci is the body temperature value of the group monitored by wearable temperature sensors and infrared cameras, and n is the number of groups; The groups are divided into two situations: all livestock and poultry individuals in a single breeding area block and all livestock and poultry individuals in all breeding area blocks. Comparison and judgment are made between the temperature values ​​of livestock and poultry individuals and the group composed of all livestock and poultry individuals in a single breeding area block, and between the temperature values ​​of livestock and poultry individuals and the group composed of all livestock and poultry individuals in all breeding area blocks: If the temperature value is within the range [μ-3σ, μ+3σ], the body temperature state of the livestock and poultry corresponding to the temperature value is not abnormal; If the temperature value is not within the range [μ-3σ, μ+3σ], the body temperature state of the livestock and poultry corresponding to the temperature value is abnormal; Step 3: Select livestock and poultry with abnormal body temperature, move the infrared camera to the breeding area block (4) where the livestock and poultry with abnormal body temperature are located, re-inspect the livestock and poultry, and further monitor the abnormal situation.

Images