Infrared thermal imager temperature measurement method, device and equipment based on ambient temperature self-compensation

Abstract

The application relates to an infrared thermal imager temperature measurement method, device and equipment based on environmental temperature self-compensation. The method comprises the following steps: acquiring a target parameter of a target object; wherein the target parameter comprises a current apparent temperature of the target object measured by using an infrared thermal imager and a current environmental parameter of a target region where the target object is located, the current environmental parameter at least comprising a current environmental temperature; determining a temperature difference according to the current environmental temperature and the current apparent temperature, inputting the current environmental temperature, the current apparent temperature and the temperature difference into a temperature compensation model to obtain a current temperature compensation value of the target object; and compensating the current apparent temperature by using the current temperature compensation value to obtain a real temperature of the target object. By using the method, the influence of the environmental temperature can be self-adaptively compensated, and the infrared temperature measurement accuracy of the measured object is improved.

Description

Technical Field

[0001] This application relates to the field of infrared temperature compensation technology, and in particular to an infrared thermal imager temperature measurement method, apparatus and equipment based on ambient temperature self-compensation. Background Technology

[0002] With the maturity of infrared detection and imaging technology, infrared thermal imager technology based on non-contact temperature measurement has become an indispensable monitoring method in many fields due to its core advantages such as fast response and the ability to acquire two-dimensional temperature field distribution. Its temperature measurement accuracy is directly related to the reliability of safety assessment and status judgment of the measured object.

[0003] In traditional infrared thermometry, the temperature of the object is usually calculated by inverting the radiation signal of the object being measured by the infrared thermal imager based on a fixed radiation model and preset environmental parameters.

[0004] However, this method assumes that environmental conditions such as temperature are stable or can be simplified to constant values, without fully considering the actual impact of dynamic changes and uneven spatial distribution in real-world scenarios. This results in an error between the infrared temperature of the measured object and its true temperature, reducing the accuracy of the infrared temperature of the measured object. Summary of the Invention

[0005] Therefore, it is necessary to provide an infrared thermal imager temperature measurement method, device, and equipment based on ambient temperature self-compensation to address the above-mentioned technical problems. This method can adaptively compensate for the influence of ambient temperature and improve the accuracy of infrared temperature measurement of the measured object.

[0006] In a first aspect, this application provides an infrared thermal imager temperature measurement method based on ambient temperature self-compensation, comprising:

[0007] Obtain the target parameters of the target object; wherein, the target parameters include the current apparent temperature of the target object measured by an infrared thermal imager and the current environmental parameters of the target area where the target object is located, and the current environmental parameters include at least the current ambient temperature;

[0008] Based on the current ambient temperature and the current apparent temperature, the temperature difference is determined, and the current ambient temperature, the current apparent temperature, and the temperature difference are input into the temperature compensation model to obtain the current temperature compensation value of the target object.

[0009] The current temperature compensation value is used to compensate for the current apparent temperature, thus obtaining the true temperature of the target object.

[0010] In one embodiment, the target parameters also include the measurement distance between the infrared thermal imager and the target object, and the current environmental parameters also include the ambient humidity; determining the temperature difference based on the current ambient temperature and the current apparent temperature includes: determining the current atmospheric transmittance of the infrared spectrum based on the current ambient temperature, ambient humidity, and measurement distance; correcting the reference emissivity of the target object based on the current ambient temperature to obtain the target emissivity; correcting the current apparent temperature based on the atmospheric transmittance and the target emissivity to obtain the corrected apparent temperature; and determining the temperature difference based on the current ambient temperature and the corrected apparent temperature.

[0011] In one embodiment, the current ambient temperature, the current apparent temperature, and the temperature difference are input into the temperature compensation model to obtain the current temperature compensation value of the target object, including: inputting the current ambient temperature, the corrected apparent temperature, and the temperature difference into the temperature compensation model to obtain the current temperature compensation value of the target object.

[0012] In one embodiment, the current ambient temperature, the corrected apparent temperature, and the temperature difference are input into the temperature compensation model to obtain the current temperature compensation value of the target object. This includes: selecting a target sub-model from multiple sub-models included in the temperature compensation model based on the target parameter combination; wherein the target parameter combination includes the current ambient temperature, the measurement distance, and the target emissivity of the target object, and the value range of the parameter combination corresponding to different sub-models is different; and inputting the current ambient temperature, the corrected apparent temperature, and the temperature difference into the target sub-model to obtain the current temperature compensation value of the target object.

[0013] In one embodiment, the current environmental parameters further include wind speed, solar radiation intensity, and ambient light intensity; inputting the current ambient temperature, corrected apparent temperature, and temperature difference into the target sub-model to obtain the current temperature compensation value of the target object includes: inputting the current ambient temperature, corrected apparent temperature, temperature difference, and auxiliary parameters into the target sub-model to obtain the current temperature compensation value of the target object; wherein, the auxiliary parameters include at least one of the following: measurement distance, target emissivity, ambient humidity, wind speed, solar radiation intensity, ambient light intensity, and ambient temperature interaction term, the ambient temperature interaction term refers to a feature term determined based on the current ambient temperature and candidate environmental parameters, and the candidate environmental parameters are at least one other environmental parameter besides the current ambient temperature among the current environmental parameters.

[0014] In one embodiment, a temperature difference is determined based on the current ambient temperature and the current apparent temperature. The current ambient temperature, the current apparent temperature, and the temperature difference are then input into a temperature compensation model to obtain the current temperature compensation value for the target object. This includes: determining the ambient temperature change based on the current ambient temperature and the previous ambient temperature of the target area where the target object is located in the previous sampling period; if the ambient temperature change is greater than a change threshold, determining the temperature difference based on the current ambient temperature and the current apparent temperature, and inputting the current ambient temperature, the current apparent temperature, and the temperature difference into the temperature compensation model to obtain the current temperature compensation value for the target object; if the ambient temperature change is less than or equal to the change threshold, the temperature compensation value corresponding to the previous sampling period is used as the current temperature compensation value for the target object.

[0015] In one embodiment, selecting a target sub-model from multiple sub-models included in the temperature compensation model based on the target parameter combination includes: determining the temperature range to which the current ambient temperature belongs; determining the distance range to which the measurement distance belongs; determining the emissivity range to which the target emissivity belongs; and selecting the target sub-model from multiple sub-models included in the temperature compensation model based on the temperature range, distance range, and emissivity range.

[0016] Secondly, this application also provides an infrared thermal imager temperature measurement device based on ambient temperature self-compensation, comprising:

[0017] The acquisition module is used to acquire the target parameters of the target object; wherein, the target parameters include the current apparent temperature of the target object measured by an infrared thermal imager and the current environmental parameters of the target area where the target object is located, and the current environmental parameters include at least the current ambient temperature;

[0018] The determination module is used to determine the temperature difference based on the current ambient temperature and the current apparent temperature, and input the current ambient temperature, the current apparent temperature, and the temperature difference into the temperature compensation model to obtain the current temperature compensation value of the target object;

[0019] The compensation module is used to compensate the current apparent temperature using the current temperature compensation value to obtain the true temperature of the target object.

[0020] Thirdly, this application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the various method embodiments provided in the first aspect above.

[0021] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the various method embodiments provided in the first aspect above.

[0022] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the various method embodiments provided in the first aspect above.

[0023] The aforementioned infrared thermal imager temperature measurement method, device, and equipment based on ambient temperature self-compensation provide basic data support for compensating for ambient temperature interference by simultaneously acquiring the current apparent temperature of the target object measured by the infrared thermal imager and the current ambient temperature of the target area where the target object is located. It calculates the temperature difference based on the current ambient temperature and the current apparent temperature, and inputs the current ambient temperature, current apparent temperature, and temperature difference into a temperature compensation model to output a temperature compensation value adapted to the current environmental conditions, achieving adaptive quantification of the impact of the current ambient temperature. Finally, it uses this temperature compensation value to correct the current apparent temperature, offsetting the measurement error caused by the current ambient temperature, thereby obtaining a temperature closer to the true target object temperature and effectively improving the accuracy of infrared temperature measurement. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 An application environment diagram for an infrared thermal imager temperature measurement method based on ambient temperature self-compensation provided in an embodiment of this application;

[0026] Figure 2 A flowchart illustrating an infrared thermal imager temperature measurement method based on ambient temperature self-compensation, provided in an embodiment of this application;

[0027] Figure 3 A schematic diagram of a process for determining a temperature difference is provided for an embodiment of this application;

[0028] Figure 4 This application provides a schematic diagram of a process for determining the current temperature compensation value in an embodiment of the present application.

[0029] Figure 5 A flowchart illustrating the selection of a target sub-model is provided for an embodiment of this application.

[0030] Figure 6 A schematic diagram of a process for determining the temperature difference and the current temperature compensation value is provided in an embodiment of this application;

[0031] Figure 7A schematic flowchart of another infrared thermal imager temperature measurement method based on ambient temperature self-compensation provided in this application embodiment;

[0032] Figure 8 A structural block diagram of an infrared thermal imager temperature measurement device based on ambient temperature self-compensation provided in an embodiment of this application;

[0033] Figure 9 This is an internal structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0035] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0036] The infrared thermal imager temperature measurement method based on ambient temperature self-compensation provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed in the cloud or on other network servers. Terminal 102 can collect the current apparent temperature of the target object using an infrared thermal imager and collect the current environmental parameters of the target area using various sensors. The collected data is then transmitted to server 104. Server 104 calculates the true temperature of the target object using an infrared thermal imager temperature measurement method based on environmental temperature self-compensation and feeds it back to terminal 102. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. Server 104 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0037] In one exemplary embodiment, such as Figure 2 As shown, an infrared thermal imager temperature measurement method based on ambient temperature self-compensation is provided, which is then applied to... Figure 1 Taking server 104 as an example, the following steps are included:

[0038] S201, obtain the target parameters of the target object.

[0039] The target parameters include the current apparent temperature of the target object measured by an infrared thermal imager and the current environmental parameters of the target area where the target object is located. The current environmental parameters include at least the current ambient temperature.

[0040] The target object refers to the object or area that needs to be measured, such as equipment parts in industrial production, power transmission lines in power systems, and human body parts in the medical field.

[0041] The so-called apparent temperature refers to the infrared radiation temperature of the target object directly detected by the infrared thermal imager. This temperature does not exclude the interference of environmental factors and is not the true temperature of the target object.

[0042] The so-called current environmental parameters refer to the relevant physical parameters of the surrounding environment of the target object, which include at least the current ambient temperature.

[0043] Optionally, an infrared thermal imager receives the infrared radiation signal emitted by the target object and converts it into an electrical signal, which is then processed to obtain the current apparent temperature. An ambient temperature sensor collects the current ambient temperature of the target area where the target object is located. The infrared thermal imager and the ambient temperature sensor can actively send the corresponding current apparent temperature and current ambient temperature to the server 104. The server 104 can also actively retrieve the corresponding current apparent temperature and current ambient temperature from the infrared thermal imager and the ambient temperature sensor to obtain the target parameters of the target object.

[0044] As an optional implementation, a high-precision, fast-response ambient temperature sensor can be selected to ensure accurate and real-time acquisition of ambient temperature data. The sensor should be strategically positioned, ideally in a well-ventilated location away from heat sources to guarantee data accuracy. For example, the sensor could be installed approximately 1 meter from the target object, in a location free from direct sunlight and with good ventilation. Furthermore, to ensure accuracy, multiple ambient temperature sensors can be used for multi-point measurements, and the average value can be taken as the current ambient temperature.

[0045] S202, determine the temperature difference based on the current ambient temperature and the current apparent temperature, and input the current ambient temperature, the current apparent temperature and the temperature difference into the temperature compensation model to obtain the current temperature compensation value of the target object.

[0046] The temperature difference refers to the numerical difference between the current ambient temperature and the current apparent temperature.

[0047] A temperature compensation model is a mathematical model that is trained in advance using a large amount of experimental data to calculate temperature compensation values.

[0048] Optionally, server 104 obtains the current ambient temperature and the current apparent temperature, performs a difference operation between the current apparent temperature and the current ambient temperature to obtain the temperature difference; inputs the three parameters of current ambient temperature, current apparent temperature and temperature difference into a pre-trained temperature compensation model, and the temperature compensation model uses the learned mapping relationship between the input features and the temperature compensation value to output the current temperature compensation value of the target object.

[0049] As an optional implementation, the training process of the above-mentioned temperature compensation model includes a data acquisition stage, a data preprocessing stage, a feature engineering stage, a model selection and training stage, and a model optimization stage.

[0050] Data Acquisition Phase: Collect environmental parameters (at least ambient temperature), raw infrared thermometry values ​​(i.e., apparent temperature), and actual temperature values ​​simultaneously measured using contact standard instruments (such as thermocouples) under different environmental conditions. Collect environmental parameters ranging from extremely low temperatures (e.g., -20°C) to extremely high temperatures (e.g., 50°C or even higher) to ensure that the training data fully covers all possible environmental temperature ranges. Sampling should be intensive when the ambient temperature changes. Record the ambient and internal temperatures when the infrared thermal imager performs NUC (Non-Uniformity Correction), which helps the temperature compensation model learn how to compensate for errors caused by temperature drift.

[0051] Data preprocessing stage: The collected data is processed to handle missing values ​​and outliers, as well as to standardize or normalize, to obtain a clean training dataset.

[0052] Feature engineering stage: Extract features such as ambient temperature, apparent temperature, and the temperature difference between the two.

[0053] Model Selection and Training Phase: A temperature compensation model is constructed based on machine learning algorithms, prioritizing efficient models such as gradient boosting trees. When sufficient data is available, neural networks can be used. Temperature compensation models can employ Support Vector Regression (SVR), neural networks, gradient boosting trees, and random forests. SVR performs well in high-dimensional spaces, especially suitable for situations where the number of features is not particularly large. It effectively handles nonlinear relationships through kernel functions, but is sensitive to hyperparameters (such as the penalty coefficient C and kernel parameter gamma), requiring careful tuning. Training on large datasets is relatively slow. Neural Networks (NNs) can automatically learn extremely complex nonlinear relationships and interactions between features. For such multi-factor coupled physical problems, neural networks typically achieve optimal performance. A small, fully connected network with only 3-5 layers is designed, using the ReLU (Rectified Linear Unit) activation function. Gradient boosting trees (such as XGBoost, LightGBM, and CatBoost) often perform excellently on tabular data problems, with fast training speeds, insensitivity to outliers, and typically do not require complex feature scaling. Random forests have powerful ensemble algorithms, strong resistance to overfitting, and fast training speeds. You can start by trying gradient boosting trees, as they typically achieve good benchmark performance quickly. Once you have enough data, you can then use neural networks for model training through transfer learning.

[0054] The ambient temperature, apparent temperature, and the temperature difference between them, after feature engineering, are used as inputs. The difference between the actual temperature value and the apparent temperature (i.e., the temperature compensation value) is used as the label to train the temperature compensation model, enabling it to learn the mapping relationship between the input features and the temperature compensation value. Grid search, random search, or more advanced Bayesian optimization are used to find the optimal combination of hyperparameters, and regularization, Dropout, and early stopping techniques are employed to prevent overfitting.

[0055] Model optimization phase: The temperature compensation model is evaluated using standard evaluation metrics for regression problems. For example, mean squared error or root mean square error is used to measure the absolute value of the temperature compensation output by the model. Mean absolute error is less sensitive to outliers than mean squared error and has stronger interpretability. The coefficient of determination reflects the temperature compensation model's ability to explain data fluctuations; the closer it is to 1, the better the performance of the temperature compensation model. The trained 32-bit floating-point temperature compensation model is converted into an 8-bit integer model, significantly reducing computation and memory usage. Unimportant weights and connections in the neural network are removed, resulting in a sparser, smaller model.

[0056] As an alternative implementation, a fine-tuning mechanism can be introduced to fine-tune the temperature compensation model. When it is confirmed that a measurement by the temperature compensation model is inaccurate, a more reliable reference value (such as a contact temperature measurement value) can be manually entered. The environmental data and reference value at this moment are recorded to form a new calibration data point. The current temperature compensation model is periodically fine-tuned using the accumulated new data, allowing the model to gradually adapt to the specific operating environment and aging conditions of the target object (such as equipment). An error correction mechanism is established, and the temperature measuring equipment (such as an infrared thermal imager) is calibrated periodically. Measurement errors are calculated and corrected by comparing the model with a standard temperature source or an object with a known temperature. Simultaneously, when conducting actual measurements outdoors or in complex environments, the effectiveness of the temperature compensation model can be verified by comparing it with other reliable temperature measurement methods (such as thermocouples), and the model can be further optimized based on the comparison results. The temperature measurement results (i.e., the actual temperature of the target object) and environmental parameters are monitored in real time. When the measurement error exceeds a certain threshold, timely feedback is provided, and compensation parameters are automatically adjusted or an alarm is issued.

[0057] As an alternative implementation, considering that environmental changes are sometimes gradual, taking into account time series characteristics can improve stability. Therefore, environmental parameters from historical time periods can be obtained. These historical time periods can be the past few seconds before the current sampling period, for example, environmental parameters from the past 5 time points. These historical environmental parameters, along with the current ambient temperature, current apparent temperature, and temperature difference, are used as inputs to the temperature compensation model, allowing the model to perceive the changing trends and thus output more accurate values.

[0058] S203, using the current temperature compensation value, compensates for the current apparent temperature to obtain the true temperature of the target object.

[0059] The so-called true temperature refers to the actual temperature of the target object, that is, the accurate temperature value obtained after eliminating the interference of current environmental factors.

[0060] Optionally, the true temperature of the target object can be obtained by adding the current temperature compensation value to the current apparent temperature.

[0061] This infrared thermal imager temperature measurement method based on ambient temperature self-compensation simultaneously acquires the current apparent temperature of the target object and the current ambient temperature of the target area, providing basic data support for compensation of ambient temperature interference. It calculates the temperature difference based on the current ambient temperature and the current apparent temperature, and inputs these three values ​​into a temperature compensation model to output a temperature compensation value adapted to the current environmental conditions, achieving adaptive quantification of the impact of the current ambient temperature. Finally, this temperature compensation value is used to correct the current apparent temperature, offsetting the measurement error caused by the current ambient temperature, thereby obtaining a temperature closer to the true target object temperature and effectively improving the accuracy of infrared temperature measurement.

[0062] Based on the above embodiments, in an exemplary embodiment, the target parameters further include the measurement distance between the infrared thermal imager and the target object, and the current environmental parameters further include ambient humidity; the determination of the temperature difference in S202 above is further refined. Optionally, such as Figure 3 As shown, the following steps may be included:

[0063] S301 determines the current atmospheric transmittance of the infrared spectrum based on the current ambient temperature, ambient humidity, and measurement distance.

[0064] The atmospheric transmittance refers to the ratio of the radiation energy that reaches the infrared thermal imager through the atmosphere to the radiation energy of the source when infrared radiation propagates in the atmosphere. It reflects the degree of atmospheric attenuation of infrared radiation.

[0065] Optionally, ambient humidity data can be collected in real time using a humidity sensor. The humidity sensor should be placed in a suitable location close to the ambient temperature sensor to ensure that the collected humidity data reflects the true humidity of the target object's environment. The measurement distance can be obtained using the ranging function built into a laser rangefinder or an infrared thermal imager. After obtaining the current ambient temperature, ambient humidity, and measurement distance, server 104 can use an atmospheric transmission model based on physical principles to calculate the current atmospheric transmittance of the infrared spectrum. Considering that gases such as water vapor and carbon dioxide in the atmosphere have absorption characteristics for infrared radiation, and that ambient temperature, ambient humidity, and measurement distance affect these absorption characteristics, thus affecting the atmospheric transmittance, an atmospheric transmission model is constructed based on the absorption characteristics of gases such as water vapor and carbon dioxide for infrared radiation at different temperatures and humidity levels. The current ambient temperature, ambient humidity, and measurement distance are then substituted into this atmospheric transmission model as input parameters to output the current atmospheric transmittance of the infrared spectrum.

[0066] S302, based on the current ambient temperature, corrects the reference emissivity of the target object to obtain the target emissivity.

[0067] The so-called reference emissivity refers to the reference emissivity value of the target object's material, which is stored in advance in the material emissivity database. The material emissivity database stores the reference emissivity of different material objects under standard environmental conditions. The reference emissivity values ​​of different material objects are different. For example, the reference emissivity of metal materials is usually between 0.1 and 0.3, and the reference emissivity of non-metallic materials is usually between 0.8 and 0.95.

[0068] The so-called target emissivity refers to the actual emissivity of the target object after correction for the current ambient temperature.

[0069] Optionally, based on the material information of the target object, a corresponding reference emissivity can be retrieved from a pre-established material emissivity database. Since ambient temperature affects the radiation characteristics of an object, the reference emissivity needs to be corrected according to the current ambient temperature to obtain a more accurate target emissivity. Therefore, a preset emissivity correction algorithm can be used to correct the reference emissivity based on the current ambient temperature to obtain the target emissivity. This emissivity correction algorithm is based on experimental data and can adjust the reference emissivity according to changes in ambient temperature.

[0070] S303, based on atmospheric transmittance and target emissivity, corrects the current apparent temperature to obtain the corrected apparent temperature.

[0071] The so-called corrected apparent temperature refers to the current apparent temperature after excluding the effects of atmospheric attenuation and emissivity.

[0072] Optionally, a preset temperature correction formula can be used, taking the current apparent temperature, atmospheric transmissivity, and target emissivity as input parameters to calculate the corrected apparent temperature. The temperature correction formula can be derived based on the basic principles of infrared radiation measurement. Its core idea is to compensate for the attenuation effect of the atmosphere on infrared radiation based on atmospheric transmissivity, and to correct for the effects caused by differences in the object's radiation characteristics based on the target emissivity.

[0073] For example, the temperature correction formula can be: Corrected apparent temperature = Current apparent temperature × Atmospheric transmissibility × Target emissivity / Reference emissivity.

[0074] S304, determine the temperature difference based on the current ambient temperature and the corrected apparent temperature.

[0075] Optionally, the difference between the corrected apparent temperature and the current ambient temperature can be calculated to obtain the temperature difference.

[0076] As an optional implementation, the current ambient temperature, the corrected apparent temperature, and the temperature difference are input into the temperature compensation model to obtain the current temperature compensation value of the target object.

[0077] The training process of this temperature compensation model is the same as or similar to the training process of the temperature compensation model mentioned in S202 above. It can directly adopt the training process of the temperature compensation model mentioned in S202 above, or it can be based on the training process of the temperature compensation model in S202 above, and further add the process of using atmospheric transmissivity and target emissivity to correct the apparent temperature in its data preprocessing stage to obtain the corrected temperature. In the model selection and training stage, the ambient temperature, the corrected temperature, and the temperature difference between the two are used as the input of the temperature compensation model to train the temperature compensation model.

[0078] This embodiment further introduces two parameters: measurement distance and ambient humidity. An atmospheric transport model is constructed to calculate the atmospheric transport rate. The target emissivity is obtained by correcting the reference emissivity of the target object based on the current ambient temperature. Then, the current apparent temperature is corrected using the atmospheric transport rate and the target emissivity to obtain the corrected apparent temperature. The current ambient temperature, the corrected apparent temperature, and the temperature difference are used as input parameters for a temperature compensation model to obtain the temperature compensation value, thereby further calculating the true temperature of the target object. This method not only considers the influence of ambient temperature but also fully considers the effects of measurement distance and ambient humidity on infrared radiation propagation and the object's radiation characteristics. Through multi-dimensional parameter correction and compensation, it further reduces the interference of various environmental factors and differences in the object's own radiation characteristics on the temperature measurement results, improving the accuracy of temperature measurement of the target object.

[0079] Based on the above embodiments, in one exemplary embodiment, the determination of the aforementioned current temperature compensation value is further refined. Optionally, such as Figure 4 As shown, the following steps may be included:

[0080] S401, select the target sub-model from multiple sub-models included in the temperature compensation model based on the target parameter combination.

[0081] The target parameter combination includes the current ambient temperature, measurement distance, and target emissivity of the target object. The range of values ​​for the parameter combination varies for different sub-models.

[0082] Optionally, the current ambient temperature, measurement distance, and target emissivity can be extracted from the target parameter combination, and the value range of each of these three parameters can be determined. Based on the value range of these three parameters, the corresponding sub-model can be selected from multiple sub-models of the temperature compensation model as the target sub-model.

[0083] As an optional implementation, during the training of the temperature compensation model, when the amount of collected data is large enough, the training data can be divided according to the range of values ​​for ambient temperature, measurement distance, and emissivity to obtain multiple different dataset subsets; then, for the dataset subsets corresponding to the combination of these three parameters, different combined datasets are determined, and a sub-model is trained using each combined dataset, thereby forming multiple sub-models corresponding to different parameter combination value ranges.

[0084] Alternatively, the training data can be divided into multiple intervals according to the ambient temperature to obtain multiple temperature intervals. Each temperature interval can then be further divided into multiple temperature-distance sub-intervals according to the measurement distance. Each temperature-distance sub-interval can then be further divided into multiple temperature-distance-emissivity sub-intervals according to the emissivity, thereby obtaining a data subset corresponding to each temperature-distance-emissivity sub-interval. Each data subset can then be used to train a sub-model. For example, the ambient temperature can be divided into multiple temperature ranges such as below 0℃, 10℃-40℃, and above 40℃, or divided according to different weather conditions, such as constant indoor temperature, sunny outdoor temperature, rainy weather, and foggy weather. Each temperature range can be further divided into multiple temperature-distance sub-ranges according to the measurement distance, such as dividing the measurement distance into multiple ranges such as below 1 meter, 1-10 meters, and above 10 meters. Each temperature-distance sub-range can be further divided into multiple temperature-distance-emissivity sub-ranges according to emissivity, such as dividing the emissivity into multiple ranges such as below 0.6, 0.6-0.9, and above 0.9. A sub-model can be trained using the data subset corresponding to each temperature-distance-emissivity sub-range.

[0085] S402, input the current ambient temperature, the corrected apparent temperature, and the temperature difference into the target sub-model to obtain the current temperature compensation value of the target object.

[0086] Optionally, the mapping relationship between the input features learned by the target sub-model and the temperature compensation value can be used to process the current ambient temperature, the corrected apparent temperature, and the temperature difference to obtain the current temperature compensation value of the target object.

[0087] In this embodiment, by selecting the corresponding target sub-model based on the target parameter combination to calculate the temperature compensation value, it is possible to more accurately adapt to the temperature measurement scenario within a specific parameter range, further improve the accuracy of the temperature compensation value calculation, and thus improve the accuracy of the final temperature measurement result, thereby better adapting to diverse temperature measurement scenarios under different parameter combinations.

[0088] Based on the above embodiments, in an exemplary embodiment, the current temperature compensation value obtained using the target sub-model in S402 is further refined. Optionally, this may include the following steps:

[0089] Input the current ambient temperature, the corrected apparent temperature, the temperature difference, and auxiliary parameters into the target sub-model to obtain the current temperature compensation value of the target object.

[0090] The auxiliary parameters include at least one of the following: measurement distance, target emissivity, ambient humidity, wind speed, solar radiation intensity, ambient light, and ambient temperature interaction term. The ambient temperature interaction term refers to the feature term determined based on the current ambient temperature and candidate environmental parameters. The candidate environmental parameter is at least one other environmental parameter besides the current ambient temperature among the current environmental parameters.

[0091] Optionally, wind speed data can be collected in real time using a wind speed sensor. The wind speed sensor should be placed in a location that accurately reflects the airflow around the target object. To reduce the impact of wind speed on heat dissipation from the target object's surface, windbreaks can be installed around the target object (such as equipment) to reduce interference from strong winds on temperature measurement. Solar radiation intensity data can be collected using a solar radiation sensor. This sensor should be placed facing the direction of solar radiation. For outdoor equipment, a protective cover with temperature control can be used to prevent direct sunlight while maintaining a relatively stable internal temperature. Ambient light data can be collected using a light sensor. The ambient temperature interaction parameter reflects the synergistic effect of the current ambient temperature and other environmental parameters on the temperature measurement result. This can be the product of the current ambient temperature and a candidate environmental parameter, such as the product of the current ambient temperature and ambient humidity, or the product of the current ambient temperature and solar radiation intensity, or the ratio of the current ambient temperature to a candidate environmental parameter, such as the ratio of the current ambient temperature to wind speed. The current ambient temperature, the corrected apparent temperature, the temperature difference, and the selected auxiliary parameters are input into the target sub-model. Since the target sub-model has learned the mapping relationship between these input features and the temperature compensation value during the training process, the target sub-model determines the current temperature compensation value of the target object based on these current input features.

[0092] As an optional implementation, the auxiliary parameters may also include polynomial terms. A polynomial term refers to a characteristic term determined based on the core environmental parameters in the current environmental parameters. The core environmental parameters may include the current ambient temperature and wind speed. The polynomial term may be a characteristic term obtained by squaring the current ambient temperature or a characteristic term obtained by squaring the wind speed.

[0093] It should be noted that the training process of the sub-model is similar to that of the temperature compensation model mentioned in S202 above. The difference is that the sub-model can be trained by selecting the ambient temperature, the corrected temperature, the temperature difference between the two, and auxiliary parameters (which can be one or more of the above parameters) as inputs within a specific parameter range.

[0094] In this embodiment, auxiliary parameters are used as one of the input features of the target sub-model. This allows for a comprehensive consideration of the influence of these parameters and their interaction with ambient temperature on the temperature compensation value, thus eliminating various environmental interference factors more comprehensively and outputting a more accurate current temperature compensation value. This makes the final temperature measurement result closer to the true temperature of the target object.

[0095] Based on the above embodiments, in an exemplary embodiment, the selection of the aforementioned target sub-model is further refined. Optionally, such as... Figure 5 As shown, the following steps may be included:

[0096] S501, determine the temperature range to which the current ambient temperature belongs.

[0097] The so-called temperature range refers to the pre-defined range of ambient temperature values. The division is mainly based on the degree of difference in the influence of ambient temperature on infrared thermometry within different temperature ranges, while also taking into account the common temperature ranges in actual temperature measurement scenarios.

[0098] Optionally, the current ambient temperature value can be compared with the range values ​​of each preset temperature range to determine the temperature range to which the current ambient temperature belongs.

[0099] S502, determine the distance interval to which the measured distance belongs.

[0100] The so-called distance range refers to the pre-defined range of measurement distance values. The division is mainly based on the differences in the degree of atmospheric attenuation of infrared radiation at different measurement distances, as well as the effective measurement distance range of the infrared thermal imager.

[0101] Optionally, the measured distance can be compared with the range values ​​of each preset distance interval to determine the distance interval to which the measured distance belongs.

[0102] S503, determine the emissivity range to which the target emissivity belongs.

[0103] The so-called emissivity range refers to a pre-defined range of emissivity values. The basis for this division is mainly the difference in the radiation characteristics of objects within different emissivity ranges, as well as the emissivity distribution range of common materials.

[0104] Optionally, the target emissivity can be compared with the range values ​​of each pre-defined emissivity interval to determine the emissivity interval to which the target emissivity belongs.

[0105] S504 selects the target sub-model from multiple sub-models included in the temperature compensation model based on the temperature range, distance range, and emissivity range.

[0106] Optionally, since each sub-model corresponds to a unique combination of temperature range, distance range, and emissivity range, the target sub-model can be determined from among multiple sub-models based on the temperature range, distance range, and emissivity range to which the target object belongs.

[0107] It should be noted that, Figure 5 The above is just one execution order of S501-S504. The execution order of S501-S503 can be parallel or serial, and no limitation is made here.

[0108] In this embodiment, by selecting the corresponding sub-model according to the interval to which the actual parameters belong, the selection process of the sub-model is made more standardized and accurate, reducing the probability of errors in the sub-model selection process, improving the stability and reliability of the method, and thus ensuring the accuracy of the final temperature measurement results.

[0109] Based on the above embodiments, in an exemplary embodiment, the determination of the temperature difference and the current temperature compensation value in S202 is further refined. Optionally, such as Figure 6 As shown, the following steps may be included:

[0110] S601, determine the change in ambient temperature based on the current ambient temperature and the previous ambient temperature of the target area where the target object is located in the previous sampling period.

[0111] The sampling period refers to the time interval for collecting target parameters, and its setting can be adjusted according to the needs of the actual temperature measurement scenario. The change in ambient temperature refers to the absolute value of the difference between the current ambient temperature and the previous ambient temperature.

[0112] Optionally, the previous ambient temperature of the target area where the target object is located in the previous sampling period can be obtained, and the difference between the current ambient temperature and the previous ambient temperature can be calculated to determine the amount of change in ambient temperature.

[0113] S602, determine whether the change in ambient temperature is greater than the change threshold; if yes, that is, if the change in ambient temperature is greater than the change threshold, execute S603; if no, that is, if the change in ambient temperature is less than or equal to the change threshold, execute S604.

[0114] S603 determines the temperature difference based on the current ambient temperature and the current apparent temperature, and inputs the current ambient temperature, the current apparent temperature, and the temperature difference into the temperature compensation model to obtain the current temperature compensation value of the target object.

[0115] The so-called change threshold refers to a pre-set critical value used to determine whether the change in ambient temperature is significant. The setting of this threshold can be based on experimental data and actual application requirements.

[0116] Optionally, the change in ambient temperature can be compared with a threshold value. If the change in ambient temperature is greater than the threshold value, it indicates that the ambient temperature has changed significantly. In this case, the temperature compensation value of the previous sampling period can no longer accurately reflect the temperature measurement error under the current environment, and the current temperature compensation value needs to be recalculated.

[0117] S604 uses the temperature compensation value corresponding to the previous sampling period as the current temperature compensation value of the target object.

[0118] If the change in ambient temperature is not greater than the change threshold, the temperature compensation value corresponding to the previous sampling period will be used as the current temperature compensation value of the target object.

[0119] In this embodiment, a threshold value for the change in ambient temperature is set to determine whether a significant change has occurred. The temperature compensation value is recalculated only when the ambient temperature changes significantly; otherwise, the compensation value from the previous sampling period is directly used. This design ensures the accuracy of temperature measurement results when the ambient temperature changes significantly, while avoiding repetitive and complex calculations when the ambient temperature is relatively stable. This effectively improves the computational efficiency of the method, reduces the computational load on the server, and extends the lifespan of the equipment. Furthermore, this method can dynamically adjust the calculation strategy of the compensation value according to changes in ambient temperature, balancing measurement accuracy and computational efficiency. It has greater practicality and flexibility, and can better adapt to temperature measurement scenarios with different rates of environmental change.

[0120] Based on the above embodiments, in an exemplary embodiment, such as Figure 7 As shown, the method may further include the following steps:

[0121] S701, obtain the target parameters of the target object.

[0122] S702, determine the change in ambient temperature based on the current ambient temperature and the previous ambient temperature of the target area where the target object is located in the previous sampling period.

[0123] S703, determine whether the change in ambient temperature is greater than the change threshold; if yes, that is, if the change in ambient temperature is greater than the change threshold, execute S705; if no, that is, if the change in ambient temperature is less than or equal to the change threshold, execute S704.

[0124] S704 uses the temperature compensation value corresponding to the previous sampling period as the current temperature compensation value of the target object.

[0125] S705 determines the current atmospheric transmittance of the infrared spectrum based on the current ambient temperature, humidity, and measurement distance.

[0126] S706, based on the current ambient temperature, corrects the reference emissivity of the target object to obtain the target emissivity.

[0127] S707 corrects the current apparent temperature based on atmospheric transmissivity and target emissivity to obtain the corrected apparent temperature.

[0128] S708 determines the temperature difference based on the current ambient temperature and the corrected apparent temperature.

[0129] S709, determine the temperature range to which the current ambient temperature belongs.

[0130] S710, determine the distance interval to which the measured distance belongs.

[0131] S711, determine the emissivity range to which the target emissivity belongs.

[0132] S712 selects the target sub-model from multiple sub-models included in the temperature compensation model based on the temperature range, distance range, and emissivity range.

[0133] S713 inputs the current ambient temperature, corrected apparent temperature, temperature difference, and auxiliary parameters into the target sub-model to obtain the current temperature compensation value of the target object.

[0134] S714 uses the current temperature compensation value to compensate for the current apparent temperature, thereby obtaining the true temperature of the target object.

[0135] The specific implementation methods of S701-S714 are the same as those in the above method embodiments, and will not be repeated here.

[0136] It should be noted that the parameters and specific examples mentioned in the above method embodiments are only one type, and they can also be other parameters and their corresponding examples, which are not limited here.

[0137] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0138] Based on the same inventive concept, this application also provides an infrared thermal imager temperature measurement device for implementing the aforementioned infrared thermal imager temperature measurement method based on ambient temperature self-compensation. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the infrared thermal imager temperature measurement device based on ambient temperature self-compensation provided below can be found in the limitations of the infrared thermal imager temperature measurement method based on ambient temperature self-compensation described above, and will not be repeated here.

[0139] In one exemplary embodiment, such as Figure 8 As shown, an infrared thermal imager temperature measurement device based on ambient temperature self-compensation is provided, including: an acquisition module 801, a determination module 802, and a compensation module 803, wherein:

[0140] The acquisition module 801 is used to acquire the target parameters of the target object; wherein, the target parameters include the current apparent temperature of the target object measured by an infrared thermal imager and the current environmental parameters of the target area where the target object is located, and the current environmental parameters include at least the current ambient temperature;

[0141] The determination module 802 is used to determine the temperature difference based on the current ambient temperature and the current apparent temperature, and input the current ambient temperature, the current apparent temperature and the temperature difference into the temperature compensation model to obtain the current temperature compensation value of the target object;

[0142] The compensation module 803 is used to compensate the current apparent temperature using the current temperature compensation value to obtain the true temperature of the target object.

[0143] In one embodiment, the target parameters also include the measurement distance between the infrared thermal imager and the target object, and the current environmental parameters also include the ambient humidity; the determining module 802 is specifically used to: determine the current atmospheric transmittance of the infrared spectrum based on the current ambient temperature, ambient humidity and measurement distance; correct the reference emissivity of the target object based on the current ambient temperature to obtain the target emissivity; correct the current apparent temperature based on the atmospheric transmittance and the target emissivity to obtain the corrected apparent temperature; and determine the temperature difference based on the current ambient temperature and the corrected apparent temperature.

[0144] In one embodiment, the determining module 802 may include a determining unit, used to input the current ambient temperature, the corrected apparent temperature and the temperature difference into the temperature compensation model to obtain the current temperature compensation value of the target object.

[0145] In one embodiment, the determining unit specifically includes: a selection subunit, used to select a target submodel from multiple submodels included in the temperature compensation model according to the target parameter combination; wherein the target parameter combination includes the current ambient temperature, measurement distance and target emissivity of the target object, and the value range of the parameter combination corresponding to different submodels is different; and a determining subunit, used to input the current ambient temperature, the corrected apparent temperature and the temperature difference into the target submodel to obtain the current temperature compensation value of the target object.

[0146] In one embodiment, the current environmental parameters also include wind speed, solar radiation intensity, and ambient light intensity; the determining sub-unit is specifically used to: input the current ambient temperature, the corrected apparent temperature, the temperature difference, and auxiliary parameters into the target sub-model to obtain the current temperature compensation value of the target object; wherein, the auxiliary parameters include at least one of the following: measurement distance, target emissivity, ambient humidity, wind speed, solar radiation intensity, ambient light intensity, and ambient temperature interaction term, the ambient temperature interaction term refers to the feature term determined based on the current ambient temperature and candidate environmental parameters, and the candidate environmental parameters are at least one other environmental parameter besides the current ambient temperature among the current environmental parameters.

[0147] In one embodiment, the selection sub-unit is specifically used to: determine the temperature range to which the current ambient temperature belongs; determine the distance range to which the measurement distance belongs; determine the emissivity range to which the target emissivity belongs; and select the target sub-model from multiple sub-models included in the temperature compensation model based on the temperature range, distance range, and emissivity range.

[0148] In one embodiment, the determining module 802 is specifically used to: determine the change in ambient temperature based on the current ambient temperature and the previous ambient temperature of the target area where the target object is located in the previous sampling period; if the change in ambient temperature is greater than the change threshold, determine the temperature difference based on the current ambient temperature and the current apparent temperature, and input the current ambient temperature, the current apparent temperature, and the temperature difference into the temperature compensation model to obtain the current temperature compensation value of the target object; if the change in ambient temperature is less than or equal to the change threshold, use the temperature compensation value corresponding to the previous sampling period as the current temperature compensation value of the target object.

[0149] The modules in the aforementioned infrared thermal imager temperature measurement device based on ambient temperature self-compensation can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0150] In one exemplary embodiment, an electronic device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9As shown, this electronic device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores target parameters, the actual temperature of the target object, etc. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When the computer program is executed by the processor, it implements an infrared thermal imager temperature measurement method based on ambient temperature self-compensation.

[0151] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0152] In one exemplary embodiment, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0153] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0154] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0155] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0156] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0157] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for measuring temperature using an infrared thermal imager based on self-compensation of ambient temperature, characterized in that, The method includes: Obtain target parameters of the target object; wherein, the target parameters include the current apparent temperature of the target object measured by an infrared thermal imager and the current environmental parameters of the target area where the target object is located, and the current environmental parameters include at least the current ambient temperature; Based on the current ambient temperature and the current apparent temperature, the temperature difference is determined, and the current ambient temperature, the current apparent temperature, and the temperature difference are input into the temperature compensation model to obtain the current temperature compensation value of the target object; The current apparent temperature is compensated using the current temperature compensation value to obtain the true temperature of the target object.

2. The method according to claim 1, characterized in that, The target parameters also include the measurement distance between the infrared thermal imager and the target object, and the current environmental parameters also include ambient humidity; the temperature difference is determined based on the current ambient temperature and the current apparent temperature, including: The current atmospheric transmittance of the infrared spectrum is determined based on the current ambient temperature, the ambient humidity, and the measurement distance. Based on the current ambient temperature, the reference emissivity of the target object is corrected to obtain the target emissivity; The current apparent temperature is corrected based on the atmospheric transmittance and the target emissivity to obtain the corrected apparent temperature; The temperature difference is determined based on the current ambient temperature and the corrected apparent temperature.

3. The method according to claim 2, characterized in that, The step of inputting the current ambient temperature, the current apparent temperature, and the temperature difference into the temperature compensation model to obtain the current temperature compensation value of the target object includes: The current ambient temperature, the corrected apparent temperature, and the temperature difference are input into the temperature compensation model to obtain the current temperature compensation value of the target object.

4. The method according to claim 3, characterized in that, The step of inputting the current ambient temperature, the corrected apparent temperature, and the temperature difference into the temperature compensation model to obtain the current temperature compensation value of the target object includes: Based on the target parameter combination, a target sub-model is selected from multiple sub-models included in the temperature compensation model; wherein, the target parameter combination includes the current ambient temperature, the measurement distance, and the target emissivity of the target object, and the value range of the parameter combination corresponding to different sub-models is different; The current ambient temperature, the corrected apparent temperature, and the temperature difference are input into the target sub-model to obtain the current temperature compensation value of the target object.

5. The method according to claim 4, characterized in that, The current environmental parameters also include wind speed, solar radiation intensity, and ambient light intensity; the step of inputting the current ambient temperature, the corrected apparent temperature, and the temperature difference into the target sub-model to obtain the current temperature compensation value of the target object includes: The current ambient temperature, the corrected apparent temperature, the temperature difference, and auxiliary parameters are input into the target sub-model to obtain the current temperature compensation value of the target object. The auxiliary parameters include at least one of the following: measurement distance, target emissivity, ambient humidity, wind speed, solar radiation intensity, ambient light intensity, and ambient temperature interaction item. The ambient temperature interaction item refers to a feature item determined based on the current ambient temperature and candidate environmental parameters. The candidate environmental parameters are at least one other environmental parameter besides the current ambient temperature among the current environmental parameters.

6. The method according to claim 4, characterized in that, The step of selecting a target sub-model from multiple sub-models included in the temperature compensation model based on the target parameter combination includes: Determine the temperature range to which the current ambient temperature belongs; Determine the distance interval to which the measured distance belongs; Determine the emissivity range to which the target emissivity belongs; Based on the temperature range, the distance range, and the emissivity range, a target sub-model is selected from multiple sub-models included in the temperature compensation model.

7. The method according to any one of claims 1-6, characterized in that, The step of determining the temperature difference based on the current ambient temperature and the current apparent temperature, and inputting the current ambient temperature, the current apparent temperature, and the temperature difference into the temperature compensation model to obtain the current temperature compensation value of the target object includes: The change in ambient temperature is determined based on the current ambient temperature and the previous ambient temperature of the target area where the target object is located in the previous sampling period. When the change in ambient temperature is greater than the change threshold, the temperature difference is determined based on the current ambient temperature and the current apparent temperature, and the current ambient temperature, the current apparent temperature and the temperature difference are input into the temperature compensation model to obtain the current temperature compensation value of the target object; If the change in ambient temperature is less than or equal to the change threshold, the temperature compensation value corresponding to the previous sampling period shall be used as the current temperature compensation value of the target object.

8. An infrared thermal imager temperature measurement device based on ambient temperature self-compensation, characterized in that, The device includes: An acquisition module is used to acquire target parameters of a target object; wherein, the target parameters include the current apparent temperature of the target object measured by an infrared thermal imager and the current environmental parameters of the target area where the target object is located, and the current environmental parameters include at least the current ambient temperature; The determination module is used to determine the temperature difference based on the current ambient temperature and the current apparent temperature, and input the current ambient temperature, the current apparent temperature and the temperature difference into the temperature compensation model to obtain the current temperature compensation value of the target object; The compensation module is used to compensate the current apparent temperature using the current temperature compensation value to obtain the true temperature of the target object.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images