Infrared thermal imaging AI intelligent temperature measurement method

Abstract

The application relates to the field of infrared thermal imaging technology, and particularly provides an infrared thermal imaging AI intelligent temperature measurement method.The method comprises the following steps: image input and preprocessing, receiving infrared images and sunlight images photographed by an infrared thermal imager, classifying based on pixel value differences, and preprocessing to obtain binary images; image cutting, cutting the binary images, and identifying the boundaries of numbers and symbols; characteristic value calculation and extraction, dividing regions according to the boundaries of the numbers and symbols, and performing feature extraction to construct a characteristic vector; number classification and identification, comparing the characteristic vector with a pre-trained K-nearest neighbor algorithm (KNN) model to identify the numbers and symbols; and image number output, combining the identified numbers and symbols into complete temperature values, outputting the identification result, and storing the identification result for comparison diagnosis.The method automatically and accurately identifies temperature information in the infrared images, and realizes intelligent comparison diagnosis.

Description

Technical Field

[0001] This invention relates to the field of infrared thermal imaging technology, and in particular to an AI-powered intelligent temperature measurement method for infrared thermal imaging, used for temperature detection and fault diagnosis in power equipment inspection and industrial equipment monitoring. Background Technology

[0002] In industrial equipment operation monitoring, infrared thermal imaging technology has been widely used for temperature detection. Traditional infrared temperature measurement methods usually require manual reading and analysis of thermal image spectra, which is not only inefficient but also susceptible to human factors, leading to inaccurate temperature readings. In addition, some existing automatic temperature measurement algorithms suffer from low recognition accuracy and poor anti-interference capabilities when processing infrared images in complex environments, failing to meet the requirements for high-precision and intelligent temperature measurement. Summary of the Invention

[0003] In view of this, the present invention provides an AI-powered intelligent temperature measurement method for infrared thermal imaging, which can automatically and accurately identify temperature information in infrared images and achieve intelligent comparative diagnosis.

[0004] In a first aspect, the present invention provides an infrared thermal imaging AI intelligent temperature measurement method, the method comprising: Step 1: Image Input and Preprocessing. Receive infrared images and sunlight images captured by an infrared thermal imager, classify them based on pixel value differences, and perform preprocessing to obtain a binarized image. Step 2: Image segmentation. The binarized image is segmented to identify the boundaries of numbers and symbols. Step 3: Feature value calculation and extraction. The region is divided according to the boundaries of numbers and symbols, and features are extracted to construct feature vectors. Step 4: Digit classification and recognition. The feature vectors are compared with the pre-trained K-Nearest Neighbors (KNN) model to identify digits and symbols. Step 5: Image digital output. Combine the recognized numbers and symbols into a complete temperature value, output the recognition result and store it for comparison and diagnosis.

[0005] Optionally, step 1 includes: Step 11: Image classification. Based on the difference in pixel values ​​between the infrared image and the daylight image, select the infrared image with a pixel value of 640×512 for classification and recognition. Step 12: Image cropping. Cropping the selected infrared image, locating and cropping the upper left corner of the infrared image, and retaining the highest temperature display area in the upper left corner. Step 13: Denoise the cropped infrared image and perform grayscale conversion based on the grayscale threshold to convert the image pixels into a binary matrix containing only 0 and 1.

[0006] Optionally, step 2 includes: Step 21: Edge detection. Scan the binary matrix horizontally and vertically to identify transition points from 0 to 1 and from 1 to 0, in order to determine the location of the cutting point. Step 22: Character segmentation. Based on the edge detection results, the binary matrix is ​​segmented into multiple independent sub-regions. Each sub-region corresponds to a number or symbol, that is, the numbers and symbols in the image are segmented into individual characters.

[0007] Optionally, step 3 includes: Step 31: Region division. Divide each segmented digital image into 9 regions, i.e., a 3×3 grid, with each region containing a certain number of pixels. Step 32: Feature extraction. Local features: Calculate the proportion of pixels with a value of 1 in each region to obtain 9 feature values ​​A1-A9 to reflect the distribution density of numbers in each region; Global features: Calculate the total proportion of pixels with a value of 1 in the entire image, A10, to characterize the overall density features of the numbers. Step 33: Feature vector construction. The 10 feature values ​​are combined into a feature vector A = [A1, A2, ..., A10], which serves as the feature representation of the digital image. Optionally, step 4 includes: Step 41: Training sample library. During the pre-training process, sample images of 0-9, decimal point, and terminating character are collected in advance, with 5 images for each character, and placed in 12 folders from 0 to 11 for training. The above samples are trained using the KNN algorithm to generate a training model, and the training results are saved in the train_set.pkl file. Step 42: KNN classification. For the feature vector of the digital image to be identified, calculate its Euclidean distance with the feature vectors of all samples in the training set; select the k closest samples, compare the feature vector of the input image with the feature vectors in the training set, and determine the classification result of each character by majority voting. Step 43: Termination of feature recognition. When a termination character is detected, it is determined to be a temperature unit marker, and the recognition process is terminated to ensure that the complete temperature value is correctly extracted.

[0008] Optionally, step 5 includes: Step 51: Numerical combination. Combine the identified individual characters in sequence to form a complete temperature value and output it for display. Step 52: Data storage. Associate each identified temperature value with the device identifier and store it in the historical database to form a record of device temperature changes. Step 53: Comparison and diagnosis. When the temperature of the same device is measured again, historical data is automatically retrieved for comparison and analysis of temperature change trends. If the temperature exceeds the preset threshold, an abnormal warning is triggered to achieve intelligent monitoring of equipment status and fault prediction.

[0009] Optionally, in step 13, based on the grayscale difference between the temperature value and the background, the grayscale threshold is set to 150; pixels with a grayscale value greater than or equal to 150 are assigned 1, and the rest are assigned 0.

[0010] Optionally, in step 42, k=20 is determined by cross-validation to balance model complexity and generalization ability.

[0011] In a second aspect, embodiments of the present invention provide a computer-readable storage medium comprising a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to execute the infrared thermal imaging AI intelligent temperature measurement method in the first aspect or any possible implementation thereof.

[0012] Thirdly, embodiments of the present invention provide an electronic device, including: one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the device, cause the device to perform the infrared thermal imaging AI intelligent temperature measurement method in the first aspect or any possible implementation of the first aspect.

[0013] The technical solution provided by this invention includes image input and preprocessing: receiving infrared images and sunlight images captured by an infrared thermal imager, classifying them based on pixel value differences, and performing preprocessing to obtain a binarized image; image segmentation: segmenting the binarized image to identify the boundaries of numbers and symbols; feature value calculation and extraction: dividing the region according to the boundaries of numbers and symbols and extracting features to construct feature vectors; number classification and recognition: comparing the feature vectors with a pre-trained K-Nearest Neighbors (KNN) model to identify numbers and symbols; and image digital output: combining the identified numbers and symbols into a complete temperature value, outputting the recognition result, and storing it for comparative diagnosis. This method automatically and accurately identifies temperature information in infrared images and achieves intelligent comparative diagnosis. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 A flowchart of the infrared thermal imaging AI intelligent temperature measurement method provided in an embodiment of the present invention; Figure 2 A flowchart for digital classification and recognition provided in an embodiment of the present invention; Figure 3 A flowchart for image data comparison and diagnosis provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0018] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in the embodiments of this invention are also intended to include the plural forms unless the context clearly indicates otherwise.

[0019] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0020] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0021] Figure 1The flowchart of the infrared thermal imaging AI intelligent temperature measurement method provided by the embodiments of the present invention is as follows: Figure 1 As shown, the method includes: Step 1, Image input and preprocessing: Receive the infrared image and daylight image captured by the infrared thermal imager, classify them based on the pixel value difference, and perform preprocessing to obtain a binary image.

[0022] In the embodiments of the present invention, Step 1 includes: Step 11, Image classification: According to the pixel value difference between the infrared image and the daylight image, select the infrared image with a pixel value of 640×512 for classification and recognition; since only the infrared image contains temperature information, this step automatically distinguishes the two types of images through pixel features to ensure the accuracy of the subsequent processing object.

[0023] Step 12, Image cropping: Crop the selected infrared image, locate and intercept the upper left corner area of the infrared image, and retain the area with the highest temperature display in the upper left corner; this operation focuses on key information, reduces the redundant data volume in subsequent processing, and improves the efficiency of the algorithm.

[0024] Step 13, Denoise the cropped infrared image and perform gray-scale conversion according to the gray-scale value threshold to convert the image pixel points into a binary matrix containing only 0 and 1. This step simplifies the image data structure, highlights the edge features of the temperature numbers, and lays a foundation for subsequent cutting and recognition.

[0025] In the embodiments of the present invention, in Step 13, based on the gray-scale difference characteristics between the temperature numbers and the background, the gray-scale value threshold is set to 150; pixels with a gray-scale value greater than or equal to 150 are assigned 1, and the rest are assigned 0, ensuring that the digital features are clearly prominent.

[0026] Step 2, Image cutting: Cut the binary image to identify the boundaries of numbers and symbols.

[0027] In the embodiments of the present invention, Step 2 includes: Step 21, Edge detection: Scan the binary matrix in the horizontal and vertical directions to identify the transition points from 0 to 1 and from 1 to 0. The above transition points correspond to the edge positions of numbers and symbols to determine the positions of the cutting points; Step 22, Character segmentation: According to the results of edge detection, divide the binary matrix into multiple independent sub-regions, and each sub-region corresponds to a number or symbol (such as numbers 0-9, decimal point ".", and the character "She"), that is, the numbers and symbols in the image are segmented into single characters. This step decomposes the continuous temperature numbers into basic units that can be independently recognized.

[0028] Step 3, Feature value calculation and extraction: Perform region division according to the boundaries of numbers and symbols, and perform feature extraction to construct a feature vector.

[0029] In the embodiment of the present invention, step 3 includes: Step 31, region division: evenly divide each segmented digital image into 9 regions, that is, a 3×3 grid, and each region contains a certain number of pixel points; Step 32, feature extraction: local features: calculate the proportion of pixel values of 1 in each region to obtain 9 feature values A1 - A9 to reflect the distribution density of the digit in each region; global feature: calculate the total proportion A10 of pixel values of 1 in the entire image to characterize the overall density feature of the digit; Step 33, feature vector construction: combine the above 10 feature values into a feature vector A = [A1, A2,..., A10] as the feature representation of the digital image. This feature extraction method takes into account both local details and global characteristics and effectively characterizes the morphological differences of different digits.

[0030] Step 4, digit classification and recognition: compare the feature vector with a pre-trained K-Nearest Neighbor (KNN) algorithm model to identify digits and symbols.

[0031] In the embodiment of the present invention, as Figure 2 shown, step 4 includes: Step 41, training sample library: during the pre-training process, pre-collect sample images of 0 - 9, decimal points, and termination characters, 5 for each character, and put them into 12 folders numbered from 0 to 11 for training; train the above samples through the KNN algorithm to generate a training model, and save the training result as a train_set.pkl file; Step 42, KNN classification: for the feature vector of the digital image to be recognized, calculate its Euclidean distance from all sample feature vectors in the training set; select the k samples with the closest distance, compare the feature vector of the input image with the feature vectors in the training set, and determine the classification result of each character through the majority voting method; In the embodiment of the present invention, k = 20 is determined through cross-validation in step 42 to balance the model complexity and generalization ability and avoid overfitting or underfitting. The Euclidean distance is used to calculate the similarity of feature vectors, which is suitable for classification tasks in high-dimensional feature spaces.

[0032] Step 43, termination feature recognition: when the termination character is recognized, it is determined as the temperature unit symbol, and the recognition process is terminated to ensure correct interception of the complete temperature value.

[0033] In the embodiment of the present invention, the termination character is the character "摄". When the character "摄" is recognized, it is determined as the temperature unit symbol, and the recognition process is terminated.

[0034] Step 5: Image digital output. Combine the recognized numbers and symbols into a complete temperature value, output the recognition result and store it for comparison and diagnosis.

[0035] In this embodiment of the invention, step 5 includes: Step 51: Numerical combination. Combine the recognized individual characters in sequence to form a complete temperature value (e.g., 11.6) and output it for display. Step 52: Data storage. Associate each identified temperature value with the device identifier and store it in the historical database to form a record of device temperature changes. Step 53: Comparison and diagnosis. When the temperature of the same device is measured again, historical data is automatically retrieved for comparison and analysis of temperature change trends. If the temperature exceeds the preset threshold, an abnormal warning is triggered to achieve intelligent monitoring of equipment status and fault prediction.

[0036] In embodiments of the present invention, such as Figure 3 As shown, image data comparison diagnosis specifically includes: The infrared image data is parsed, and the parsed data is saved in the last_data_set.pkl file in dictionary form. The data in the last_data_set.pkl file is read, and the new data is added to the dictionary value set. The data is output in the form of an Excel spreadsheet, and the two most recent data are compared and diagnosed. The diagnostic data is output in the last column of the spreadsheet.

[0037] This invention innovatively divides a binarized digital image into nine regions using a nine-grid feature extraction method. The proportion of '1's in each region is extracted as a local feature (A1-A9), while a global density feature (A10) is calculated, forming a 10-dimensional feature vector. This fusion of local and global features effectively represents differences in digital morphology, improving recognition accuracy. Adaptive KNN classification optimization dynamically selects k=20 through cross-validation, balancing model complexity and generalization ability. Euclidean distance is used to measure the similarity of the high-dimensional feature space, combined with majority voting for rapid classification, particularly suitable for accurate identification of infrared temperature data. A dual-image intelligent filtering mechanism automatically distinguishes between infrared and sunlight images based on pixel value differences (640×512), accurately locating the temperature region in the upper left corner, reducing redundant data processing, and improving algorithm efficiency. Historical data comparison and diagnosis establishes a device temperature database, automatically retrieving historical data for trend analysis to achieve temperature anomaly warning. This intelligent diagnostic mechanism, which links single temperature measurements with historical data, overcomes the limitations of traditional single-point temperature measurement.

[0038] The present invention adopts a combined method of feature extraction and classification, a complete technical solution combining nine-grid area division, local-global feature vector construction, and adaptive KNN classification, including the specific steps of feature extraction, the dimension design of feature vectors, and the KNN parameter optimization method. Dual-image preprocessing process: A preprocessing process based on pixel features to screen infrared images, locate temperature regions, and perform binary processing, especially the setting method of the gray threshold (≥150) and the edge detection algorithm for image cutting. Intelligent diagnosis system architecture: An intelligent diagnosis system architecture for temperature data storage, historical comparison, and anomaly warning, including the associated design of the database, the algorithm logic for trend analysis, and the warning trigger mechanism. Termination feature recognition technology: A technical solution using the character "摄" as the recognition termination flag, including the feature extraction method of this character and its application logic in the classification process.

[0039] Compared with the prior art, the present invention has the following beneficial effects: 1. High-precision recognition: Through unique image preprocessing, cutting, and feature extraction methods, combined with the KNN machine learning algorithm, the recognition accuracy of temperature numbers in infrared thermal imaging maps is effectively improved, and a relatively high recognition accuracy can still be maintained especially in complex environments.

[0040] 2. Intelligent diagnosis: Automatically compares and diagnoses historical data of equipment temperatures, can timely detect abnormal changes in equipment temperatures, provides strong support for equipment fault warning, and improves the safety and reliability of equipment operation.

[0041] 3. High-efficiency automation: The entire temperature measurement process has a high degree of automation, without manual intervention, greatly improves the temperature measurement efficiency, reduces labor costs, and is applicable to large-scale equipment inspection and long-term monitoring.

[0042] 4. Strong adaptability: By cross-validating to select an appropriate k value and using the Euclidean distance metric method, the algorithm has strong adaptability and robustness to infrared images in different environments.

[0043] In the technical solution provided by the present invention, the method includes image input and preprocessing, receiving infrared images and daylight images taken by an infrared thermal imager, classifying based on pixel value differences, and performing preprocessing to obtain a binary image; image cutting, cutting the binary image to identify the boundaries of numbers and symbols; eigenvalue calculation and extraction, dividing regions according to the boundaries of numbers and symbols, and performing feature extraction to construct feature vectors; digital classification and recognition, comparing the feature vectors with a pre-trained K-nearest neighbor algorithm KNN model to identify numbers and symbols; image digital output, combining the identified numbers and symbols into a complete temperature value, and outputting and storing the recognition result for comparison diagnosis. This method automatically and accurately identifies the temperature information in infrared images and realizes intelligent comparison diagnosis.

[0044] The various steps in the embodiments of the present invention can be performed by an electronic device. This electronic device includes, but is not limited to, tablet computers, portable PCs, and desktop computers.

[0045] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is running, it controls the electronic device containing the computer-readable storage medium to execute the above-described embodiment of the infrared thermal imaging AI intelligent temperature measurement method.

[0046] Figure 4 A schematic diagram of an electronic device provided in an embodiment of the present invention, such as... Figure 4 As shown, the electronic device 21 includes a processor 211, a memory 212, and a computer program 213 stored in the memory 212 and executable on the processor 211. When the computer program 213 is executed by the processor 211, it implements the infrared thermal imaging AI intelligent temperature measurement method in the embodiment. To avoid repetition, it will not be described in detail here.

[0047] Electronic device 21 includes, but is not limited to, processor 211 and memory 212. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 21 and does not constitute a limitation on electronic device 21. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device may also include input / output devices, network access devices, buses, etc.

[0048] The processor 211 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0049] The memory 212 can be an internal storage unit of the electronic device 21, such as a hard disk or RAM of the electronic device 21. The memory 212 can also be an external storage device of the electronic device 21, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or FlashCard equipped on the electronic device 21. Furthermore, the memory 212 can include both internal and external storage units of the electronic device 21. The memory 212 is used to store computer programs and other programs and data required by network devices. The memory 212 can also be used to temporarily store data that has been output or will be output.

[0050] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0051] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An infrared thermal imaging AI intelligent temperature measurement method, characterized in that, The method includes: Step 1: Image Input and Preprocessing. Receive infrared images and sunlight images captured by an infrared thermal imager, classify them based on pixel value differences, and perform preprocessing to obtain a binarized image. Step 2: Image segmentation. The binarized image is segmented to identify the boundaries of numbers and symbols. Step 3: Feature value calculation and extraction. The region is divided according to the boundaries of numbers and symbols, and features are extracted to construct feature vectors. Step 4: Digit classification and recognition. The feature vectors are compared with the pre-trained K-Nearest Neighbors (KNN) model to identify digits and symbols. Step 5: Image digital output. Combine the recognized numbers and symbols into a complete temperature value, output the recognition result and store it for comparison and diagnosis.

2. The method according to claim 1, characterized in that, Step 1 includes: Step 11: Image classification. Based on the difference in pixel values ​​between the infrared image and the daylight image, select the infrared image with a pixel value of 640×512 for classification and recognition. Step 12: Image cropping. Cropping the selected infrared image, locating and cropping the upper left corner of the infrared image, and retaining the highest temperature display area in the upper left corner. Step 13: Denoise the cropped infrared image and perform grayscale conversion based on the grayscale threshold to convert the image pixels into a binary matrix containing only 0 and 1.

3. The method according to claim 2, characterized in that, Step 2 includes: Step 21: Edge detection. Scan the binary matrix horizontally and vertically to identify transition points from 0 to 1 and from 1 to 0, in order to determine the location of the cutting point. Step 22: Character segmentation. Based on the edge detection results, the binary matrix is ​​segmented into multiple independent sub-regions. Each sub-region corresponds to a number or symbol, that is, the numbers and symbols in the image are segmented into individual characters.

4. The method according to claim 3, characterized in that, Step 3 includes: Step 31: Region division. Divide each segmented digital image into 9 regions, i.e., a 3×3 grid, with each region containing a certain number of pixels. Step 32: Feature extraction. Local features: Calculate the proportion of pixels with a value of 1 in each region to obtain 9 feature values ​​A1-A9 to reflect the distribution density of numbers in each region; Global features: Calculate the total proportion of pixels with a value of 1 in the entire image, A10, to characterize the overall density features of the numbers. Step 33: Feature vector construction. Combine the above 10 feature values ​​into a feature vector A=[A1, A2, ..., A10], which serves as the feature representation of the digital image.

5. The method according to claim 4, characterized in that, Step 4 includes: Step 41: Training sample library. During the pre-training process, sample images of 0-9, decimal point, and terminating character are collected in advance, with 5 images for each character, and placed in 12 folders from 0 to 11 for training. The above samples are trained using the KNN algorithm to generate a training model, and the training results are saved in the train_set.pkl file. Step 42: KNN classification. For the feature vector of the digital image to be identified, calculate its Euclidean distance with the feature vectors of all samples in the training set; select the k closest samples, compare the feature vector of the input image with the feature vectors in the training set, and determine the classification result of each character by majority voting. Step 43: Termination of feature recognition. When a termination character is detected, it is determined to be a temperature unit marker, and the recognition process is terminated to ensure that the complete temperature value is correctly extracted.

6. The method according to claim 5, characterized in that, Step 5 includes: Step 51: Numerical combination. Combine the identified individual characters in sequence to form a complete temperature value and output it for display. Step 52: Data storage. Associate each identified temperature value with the device identifier and store it in the historical database to form a record of device temperature changes. Step 53: Comparison and diagnosis. When the temperature of the same device is measured again, historical data is automatically retrieved for comparison and analysis of temperature change trends. If the temperature exceeds the preset threshold, an abnormal warning is triggered to achieve intelligent monitoring of equipment status and fault prediction.

7. The method according to claim 2, characterized in that, In step 13, based on the grayscale difference between the temperature value and the background, the grayscale threshold is set to 150; pixels with a grayscale value greater than or equal to 150 are assigned 1, and the rest are assigned 0.

8. The method according to claim 4, characterized in that, In step 42, k=20 is determined through cross-validation to balance model complexity and generalization ability.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the infrared thermal imaging AI intelligent temperature measurement method as described in any one of claims 1 to 8.

10. An electronic device, characterized in that, include: One or more processors; Memory; And one or more computer programs, wherein the one or more computer programs are stored in the memory, the one or more computer programs including instructions that, when executed by the device, cause the device to perform the infrared thermal imaging AI intelligent temperature measurement method according to any one of claims 1 to 8.

Images