Temperature measurement method, electronic device, and computer-readable storage medium

Abstract

The present disclosure relates to a temperature measurement method, an electronic device and a computer readable storage medium, the method comprising: acquiring an infrared image of a region where a target temperature measurement object is located; determining an image region corresponding to the target temperature measurement object in the infrared image based on a pre-trained image recognition model; and calculating a temperature of the target temperature measurement object according to temperature data corresponding to the image region. The present disclosure acquires an original image containing target temperature information, accurately locates a target region where a temperature measurement object is located by using an image recognition model, determines the temperature of the target temperature measurement object based on temperature information of the target region, realizes directional temperature measurement of the target temperature measurement object, and improves the accuracy of temperature measurement.

Description

Technical Field

[0001] This disclosure relates to the field of production safety monitoring technology, and in particular to a temperature measurement method, electronic device, and computer-readable storage medium. Background Technology

[0002] In the electrolytic aluminum production process, the temperature state of the bottom of the electrolytic aluminum cell and the anode and cathode steel bars is directly related to production safety and stable equipment operation. If local temperature anomalies occur, it can easily lead to major accidents such as cell bottom leakage and cathode damage, causing economic losses and threatening personnel safety.

[0003] Currently, the processing of thermal imaging images can only output the highest and lowest temperatures within a specified area, and cannot achieve precise directional temperature measurement of the bottom of the electrolytic aluminum tank and the anode and cathode steel rods. Summary of the Invention

[0004] To address the aforementioned technical problems, this disclosure provides a temperature measurement method, an electronic device, and a computer-readable storage medium to achieve directional temperature measurement.

[0005] In a first aspect, embodiments of this disclosure provide a temperature measurement method, including: Acquire infrared images of the area where the target temperature measurement object is located; Based on a pre-trained image recognition model, the image region corresponding to the target temperature measurement object in the infrared image is determined; Calculate the temperature of the target object based on the temperature data corresponding to the image region.

[0006] In some embodiments, the image recognition model is trained based on the following method: For each sample temperature measurement object, adjust the inspection equipment and the infrared imaging device on the inspection equipment to the temperature measurement pose corresponding to the sample temperature measurement object; Obtain the sample image corresponding to the sample temperature measurement object, and the annotation results of the sample temperature measurement object in the sample image; Based on the sample images and annotation results corresponding to multiple sample temperature measurement objects, the image recognition model to be trained is trained to obtain a pre-trained image recognition model.

[0007] In some embodiments, adjusting the inspection equipment and the infrared imaging device on the inspection equipment to the temperature measurement pose corresponding to the sample temperature measurement object includes: Control the inspection equipment to move to the temperature measurement area where the sample temperature measurement object is located; Adjust the orientation of the inspection equipment and the infrared imaging equipment to ensure that the sample temperature measurement object is within the field of view of the infrared imaging equipment.

[0008] In some embodiments, based on sample images and annotation results corresponding to multiple sample temperature measurement objects, an image recognition model to be trained is trained to obtain a pre-trained image recognition model, including: A preset processing operation is performed on the sample images corresponding to multiple sample temperature measurement objects to obtain processed sample images. The preset processing operation includes at least one of left-right flipping, up-down flipping, and adding mosaic. Based on the processed sample images and annotation results, the image recognition model to be trained is trained to obtain a pre-trained image recognition model.

[0009] In some embodiments, acquiring an infrared image of the area where the target temperature measurement object is located includes: Obtain the target temperature measurement pose corresponding to the target temperature measurement object. The target temperature measurement pose includes the device pose of the inspection equipment and the imaging pose of the infrared imaging device on the inspection equipment. Adjust the position of the inspection equipment to the equipment position; Adjust the infrared imaging device to an imaging orientation; Infrared imaging equipment is used to acquire images, resulting in infrared images of the area where the target temperature measurement object is located.

[0010] In some embodiments, calculating the temperature of the target temperature measurement object based on the temperature data corresponding to the image region includes: Determine the center point of the image region; Using the center point as the center, obtain the temperature of each point within a target area of ​​a preset size; Calculate the average temperature of each point within the target area to obtain the temperature of the target object.

[0011] In some embodiments, the method further includes: When the difference between the temperature of the target object and the preset temperature is greater than the preset threshold, the temperature of the target object is re-acquired based on the pre-trained image recognition model.

[0012] In some embodiments, the method further includes: Generate a temperature measurement report for the target object, which includes the output of the image recognition model and the temperature of the target object.

[0013] In a second aspect, embodiments of this disclosure provide an electronic device, including: Memory; Processor; and Computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in the first aspect.

[0014] Thirdly, embodiments of this disclosure provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method described in the first aspect.

[0015] Fourthly, embodiments of this disclosure also provide a computer program product, which includes a computer program or instructions that, when executed by a processor, implement the temperature measurement method described above.

[0016] The temperature measurement method, electronic device, and computer-readable storage medium provided in this disclosure acquire an original image containing target temperature information, accurately locate the target area where the temperature measurement object is located using an image recognition model, and determine the temperature of the target temperature measurement object based on the temperature information of the target area, thereby achieving directional temperature measurement of the target temperature measurement object and improving the accuracy of temperature measurement. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0018] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0019] Figure 1 A flowchart of a temperature measurement method provided in this embodiment of the disclosure; Figure 2 A data acquisition flowchart is provided for an embodiment of this disclosure; Figure 3 A flowchart of a temperature measurement method provided in another embodiment of this disclosure; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0020] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0021] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0022] This disclosure provides a temperature measurement method, which will be described below with reference to specific embodiments.

[0023] Figure 1 This is a flowchart illustrating a temperature measurement method provided in an embodiment of this disclosure. This method can be applied to directional temperature measurement of the bottom of an electrolytic aluminum tank and the anode and cathode steel rods. It is understood that the temperature measurement method provided in this disclosure can also be applied to other scenarios.

[0024] The following is about Figure 1 The temperature measurement method shown is described below, and the specific steps of this method are as follows: S101. Obtain an infrared image of the area where the target temperature measurement object is located.

[0025] The target temperature measurement objects refer to the key components that need to be monitored in the electrolytic aluminum production process, specifically the bottom of the electrolytic aluminum tank and the anode and cathode steel bars. The temperature of these components is directly related to the safety of electrolytic aluminum production and the stable operation of the equipment. Abnormal temperatures can easily lead to major production accidents such as tank bottom leakage and cathode damage.

[0026] Infrared images are images captured by infrared thermal imaging gimbal cameras that reflect the temperature distribution on the surface of an object. Each pixel in the image corresponds to a temperature value, and different temperature areas will appear in different grayscale or color representations in the image. For example, high-temperature areas usually appear in brighter colors or higher grayscale values.

[0027] Obtain raw image data containing temperature information of the target object to be measured, providing a foundation for subsequent image recognition and temperature calculation.

[0028] S102. Based on the pre-trained image recognition model, determine the image region corresponding to the target temperature measurement object in the infrared image.

[0029] The pre-trained image recognition model can be an image recognition model optimized based on the YOLOv8n.pt model. This model has been trained with a large number of infrared image samples of the bottom of the electrolytic aluminum tank and the anode and cathode steel bars. Furthermore, the recognition capability under complex working conditions has been improved through data augmentation mechanisms. It can accurately identify the target temperature measurement object in complex scenarios such as equipment obstruction, complex lighting, and material accumulation at the bottom of the tank in the electrolytic aluminum workshop.

[0030] The image region corresponding to the target temperature measurement object refers to the pixel region in the infrared image that corresponds to the target temperature measurement object in the actual physical space. Specifically, it is represented by the rectangular coordinate range of the target output by the model.

[0031] The original infrared image is input into the trained image recognition model, which outputs the coordinates of the target area to determine the image area required for temperature calculation.

[0032] In actual model output, there may be a situation where there are multiple target temperature measurement objects in one image area. It is necessary to determine that the target temperature measurement object in the image area is the correct target temperature measurement object.

[0033] S103. Calculate the temperature of the target object based on the temperature data corresponding to the image area.

[0034] The temperature data corresponding to the image region refers to the temperature value of the pixel in the infrared image. These temperature values ​​constitute a temperature matrix corresponding to the pixel dimension of the image. The temperature value of each pixel can be directly obtained through the imaging principle of the infrared camera.

[0035] The temperature of the target object is obtained by calculating the temperature values ​​of multiple points within the target image area.

[0036] This embodiment of the disclosure acquires an original image containing target temperature information, uses an image recognition model to accurately locate the target area where the temperature measurement object is located, and determines the temperature of the target temperature measurement object based on the temperature information of the target area, thereby realizing directional temperature measurement of the target temperature measurement object and improving the accuracy of temperature measurement.

[0037] In some embodiments, the image recognition model is trained as follows: for each sample temperature measurement object, the inspection equipment and the infrared imaging device on the inspection equipment are adjusted to the temperature measurement pose corresponding to the sample temperature measurement object; the sample image corresponding to the sample temperature measurement object and the annotation result of the sample temperature measurement object in the sample image are obtained; based on the sample images and annotation results corresponding to multiple sample temperature measurement objects respectively, the image recognition model to be trained is trained to obtain the pre-trained image recognition model.

[0038] The process of adjusting the inspection equipment and the infrared imaging device on the inspection equipment to the temperature measurement posture corresponding to the sample temperature measurement object includes: controlling the inspection equipment to move to the temperature measurement area where the sample temperature measurement object is located; and adjusting the posture of the inspection equipment and the infrared imaging device so that the sample temperature measurement object is within the field of view of the infrared imaging device.

[0039] The sample temperature measurement objects refer to the bottom of the electrolytic aluminum tank and the anode and cathode steel bars used to train the image recognition model. Electrolytic aluminum tank bottoms and corresponding anode and cathode steel bars in different production states and locations are selected as samples to represent different working conditions in the electrolytic aluminum workshop, such as tank bottoms with different usage times and anode and cathode steel bars with different degrees of wear.

[0040] Temperature measurement pose refers to the position and posture of the inspection equipment (inspection robot), as well as the posture of the infrared imaging equipment (infrared thermal imaging gimbal camera) on the inspection equipment, such as angle and orientation, so as to ensure that the sample temperature measurement object is fully presented in the field of view of the infrared imaging equipment.

[0041] The inspection equipment is moved to the vicinity of the sample temperature measurement object, and its position and attitude information are acquired in real time. The viewing angle of the infrared imaging equipment is adjusted, and the camera is aligned with the sample temperature measurement object through horizontal and vertical adjustments. If adjusting the viewing angle of the infrared imaging equipment cannot make the sample temperature measurement object fully appear in the field of view of the infrared imaging equipment, the position and attitude of the inspection equipment are readjusted until the sample temperature measurement object is fully appearing in the field of view of the infrared imaging equipment.

[0042] For each sample object, the aforementioned temperature measurement pose was determined. During this process, infrared imaging equipment was used to continuously acquire images, resulting in video files. Frame extraction was used to extract qualified images as sample images, which were then divided into training, validation, and test sets.

[0043] Based on the selected dataset, the regions and specific objects of temperature measurement for each sample image are manually labeled, resulting in a labeling result for each sample image. The sample images are used as input to the image recognition model to be trained, and the labeled results of the sample images are used as the output of the image recognition model to be trained. Iterative training is then performed to finally obtain a trained image recognition model.

[0044] Optionally, preset processing operations are performed on the sample images corresponding to multiple sample temperature measurement objects to obtain processed sample images. The preset processing operations include at least one of left-right flipping, up-down flipping, and adding mosaic. Based on the processed sample images and the annotation results, the image recognition model to be trained is trained to obtain a pre-trained image recognition model.

[0045] By adding data augmentation mechanisms such as left-right flipping, up-down flipping, and mosaic, the regional feature extraction capability of the image recognition model can be enhanced, thereby improving the recognition accuracy under complex working conditions.

[0046] Figure 2 This is a data acquisition flowchart provided as an embodiment of the present disclosure. Figure 2 As shown, the training set data collection process is as follows: S201. Start the training set data acquisition program.

[0047] S202. Adjust the position of the inspection equipment to be near the sample temperature measurement object, and adjust the posture of the inspection equipment.

[0048] S203. Adjust the attitude of the infrared imaging device.

[0049] S204. Determine whether the sample temperature measurement object can be fully displayed.

[0050] If yes, proceed to S205. If no, proceed to S202.

[0051] S205. Save the temperature measurement pose corresponding to the sample temperature measurement object.

[0052] S206. Determine whether the temperature measurement pose of each sample object has been collected.

[0053] If yes, proceed to S207. If no, proceed to S202.

[0054] S207, End.

[0055] This embodiment of the disclosure significantly increases the diversity of samples by performing data augmentation processing on sample images, enabling the model to learn target features under different shooting angles and different interference scenarios. This improves the model's generalization ability and anti-interference ability, allowing the trained model to accurately identify the area of ​​the target temperature measurement object in actual temperature measurement scenarios, even when encountering complex working conditions, further improving the accuracy and stability of the temperature measurement method.

[0056] In some embodiments, acquiring an infrared image of the area where the target temperature measurement object is located includes: acquiring the target temperature measurement pose corresponding to the target temperature measurement object, the target temperature measurement pose including the device pose of the inspection equipment and the imaging pose of the infrared imaging device on the inspection equipment; adjusting the pose of the inspection equipment to the device pose; adjusting the infrared imaging device to the imaging pose; and using the infrared imaging device to acquire an image to obtain an infrared image of the area where the target temperature measurement object is located.

[0057] Based on the temperature measurement poses corresponding to the sample temperature measurement objects saved in the above embodiments, when a sample temperature measurement object is taken as the target temperature measurement object, the pre-saved temperature measurement pose of that sample temperature measurement object is the target temperature measurement pose. The inspection equipment and infrared imaging equipment are adjusted according to the target temperature measurement pose, and image acquisition is performed under the target temperature measurement pose to obtain an infrared image of the area where the target temperature measurement object is located.

[0058] In some embodiments, calculating the temperature of the target temperature measurement object based on the temperature data corresponding to the image region includes: determining the center point of the image region; obtaining the temperature of each point within a target region of a preset size, with the center point as the center; and calculating the average temperature of each point within the target region to obtain the temperature of the target temperature measurement object.

[0059] The center point of the image region refers to the geometric center point of the image region corresponding to the target temperature measurement object output by the image recognition model. For a rectangular image region, it can be calculated from the coordinates of the vertex corner of the region.

[0060] The target area of ​​the preset size refers to a pixel area of ​​a fixed size centered on the center point of the image area. For example, the target area consists of 121 points, with 11 pixels above, below, left, and right on each side of the center point of the image area.

[0061] The temperature at each point refers to the temperature value corresponding to each pixel in the infrared image acquired by the infrared imaging device. These temperature values ​​form a temperature matrix corresponding to the pixel dimension of the image. The temperature value of each pixel can be directly obtained through the imaging principle of the infrared camera, reflecting the actual temperature at that location. The average temperature value of each temperature value within the target area is the temperature of the target object being measured.

[0062] This embodiment calculates the temperature of the target object by averaging multiple temperature values ​​within a target area of ​​a preset size around the center point of the target temperature measurement object. This reduces the random error of temperature measurement at a single point, meets the precise monitoring needs of production and maintenance, and further improves the accuracy of temperature measurement.

[0063] In some embodiments, the method further includes: when the difference between the temperature of the target temperature measurement object and the preset temperature is greater than a preset threshold, re-acquiring the temperature of the target temperature measurement object based on a pre-trained image recognition model.

[0064] The preset temperature can be a historical normal temperature value of the target object or a normal temperature of similar targets in the same area. When the difference between the temperature of the target object and the preset temperature is greater than the preset threshold, it indicates that the temperature of the target object is abnormal or that the current temperature measurement result is incorrect. To avoid false positives, the temperature of the target object must be re-obtained at least once based on the pre-trained image recognition model.

[0065] Optionally, after re-obtaining the temperature of the target temperature measurement object based on the pre-trained image recognition model, if the difference between the re-obtained temperature and the preset temperature is still greater than the preset threshold, it should be reported to the maintenance personnel in a timely manner. If the difference between the re-obtained temperature and the preset temperature is less than or equal to the preset threshold, the next target temperature measurement object should be tested according to the normal procedure.

[0066] For example, the preset threshold is 20°C.

[0067] In some embodiments, the method further includes: generating a temperature measurement report of the target temperature measurement object, the temperature measurement report including the output of the image recognition model and the temperature of the target temperature measurement object.

[0068] The temperature measurement report is used to report to maintenance personnel. It includes the selected target object for temperature measurement, the selected image area, and the temperature information of the target object. It presents the temperature measurement results intuitively, which makes it easier for maintenance personnel to quickly locate problems and conduct on-site manual verification, significantly improving the efficiency of workers and maintenance.

[0069] Figure 3 A flowchart of a temperature measurement method provided in another embodiment of this disclosure is shown below. Figure 3 As shown, the method includes the following steps: S301. Adjust the position of the inspection equipment to the position of the equipment corresponding to the target temperature measurement object.

[0070] S302. Adjust the infrared imaging device to the imaging posture corresponding to the target temperature measurement object.

[0071] S303. Use infrared imaging equipment to acquire images and obtain infrared images of the area where the target temperature measurement object is located.

[0072] S304. Based on the output of the image recognition model, calculate the average temperature within the target area to obtain the temperature of the target object.

[0073] S305. Determine whether the difference between the temperature of the target temperature measurement object and the preset temperature is greater than the preset threshold.

[0074] If yes, proceed to S304. If no, proceed to S306.

[0075] S306. Upload temperature measurement report.

[0076] S307. Determine whether all target temperature measurement objects have completed temperature measurement.

[0077] If yes, proceed to S308. If no, proceed to S301.

[0078] S308, End.

[0079] This disclosure also provides a temperature measuring device. The temperature measuring device provided in this disclosure can execute the processing flow provided in the temperature measuring method embodiments. The temperature measuring device includes: an acquisition module, a determination module, and a calculation module. The acquisition module is used to acquire an infrared image of the area where the target temperature measuring object is located; the determination module is used to determine the image region corresponding to the target temperature measuring object in the infrared image based on a pre-trained image recognition model; and the calculation module is used to calculate the temperature of the target temperature measuring object based on the temperature data corresponding to the image region.

[0080] Optionally, the temperature measurement device includes a training module, used to adjust the inspection equipment and the infrared imaging device on the inspection equipment to the temperature measurement pose corresponding to the sample temperature measurement object for each sample temperature measurement object; acquire the sample image corresponding to the sample temperature measurement object, and the annotation result of the sample temperature measurement object in the sample image; and train the image recognition model to be trained based on the sample images and annotation results corresponding to multiple sample temperature measurement objects respectively, to obtain a pre-trained image recognition model.

[0081] Optionally, the training module is also used to control the inspection equipment to move to the temperature measurement area where the sample temperature measurement object is located; and to adjust the posture of the inspection equipment and the infrared imaging equipment so that the sample temperature measurement object is within the field of view of the infrared imaging equipment.

[0082] Optionally, the training module is also used to perform preset processing operations on the sample images corresponding to multiple sample temperature measurement objects to obtain processed sample images. The preset processing operations include at least one of left-right flipping, up-down flipping, and adding mosaic. Based on the processed sample images and the annotation results, the image recognition model to be trained is trained to obtain a pre-trained image recognition model.

[0083] Optionally, the acquisition module is used to acquire the target temperature measurement pose corresponding to the target temperature measurement object. The target temperature measurement pose includes the device pose of the inspection equipment and the imaging pose of the infrared imaging device on the inspection equipment. The module adjusts the pose of the inspection equipment to the device pose, adjusts the infrared imaging device to the imaging pose, and uses the infrared imaging device to acquire images to obtain an infrared image of the area where the target temperature measurement object is located.

[0084] Optionally, the calculation module is used to determine the center point of the image area; with the center point as the center, the temperature of each point within the target area of ​​a preset size is obtained; the average temperature of each point within the target area is calculated to obtain the temperature of the target object being measured.

[0085] Optionally, the temperature measuring device also includes a retry module, which is used to re-obtain the temperature of the target object based on a pre-trained image recognition model when the difference between the temperature of the target object and the preset temperature is greater than a preset threshold.

[0086] Optionally, the temperature measuring device also includes a generation module for generating a temperature measurement report of the target object, which includes the output of the image recognition model and the temperature of the target object.

[0087] The temperature measuring device provided in this disclosure can be used to execute the technical solutions of the above method embodiments. Its implementation principle and technical effects are similar, and will not be repeated here.

[0088] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. The electronic device provided in an embodiment of this disclosure can execute the processing flow provided in the temperature measurement method embodiment, such as... Figure 4 As shown, the electronic device 40 includes: a memory 41, a processor 42, a computer program, and a communication interface 43; wherein the computer program is stored in the memory 41 and configured to be executed by the processor 42 using the temperature measurement method described above.

[0089] In addition, this disclosure also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the temperature measurement method described in the above embodiments.

[0090] In some embodiments, the computer program is executed by a processor to: acquire an infrared image of the area where the target temperature measurement object is located; determine the image region corresponding to the target temperature measurement object in the infrared image based on a pre-trained image recognition model; and calculate the temperature of the target temperature measurement object based on the temperature data corresponding to the image region.

[0091] The image recognition model is trained as follows: For each sample temperature measurement object, the inspection equipment and its infrared imaging device are adjusted to the corresponding temperature measurement pose; a sample image of the sample temperature measurement object and its annotation results are acquired; based on the sample images and annotation results corresponding to multiple sample temperature measurement objects, the image recognition model to be trained is trained to obtain a pre-trained image recognition model. Adjusting the inspection equipment and its infrared imaging device to the corresponding temperature measurement pose includes: controlling the inspection equipment to move into the temperature measurement area where the sample temperature measurement object is located; adjusting the posture of the inspection equipment and the infrared imaging device so that the sample temperature measurement object is within the field of view of the infrared imaging device. Based on the sample images and annotation results corresponding to multiple sample temperature measurement objects, the image recognition model to be trained is trained to obtain a pre-trained image recognition model. This includes: performing preset processing operations on the sample images corresponding to multiple sample temperature measurement objects to obtain processed sample images. The preset processing operations include at least one of left-right flipping, up-down flipping, and adding mosaic. Based on the processed sample images and annotation results, the image recognition model to be trained is trained to obtain a pre-trained image recognition model.

[0092] In some embodiments, the computer program is executed by the processor to: acquire the target temperature measurement pose corresponding to the target temperature measurement object, the target temperature measurement pose including the device pose of the inspection equipment and the imaging pose of the infrared imaging device on the inspection equipment; adjust the pose of the inspection equipment to the device pose; adjust the infrared imaging device to the imaging pose; and use the infrared imaging device to acquire images to obtain an infrared image of the area where the target temperature measurement object is located.

[0093] In some embodiments, a computer program is executed by a processor to: determine the center point of an image region; obtain the temperature of each point within a target region of a preset size, centered on the center point; and calculate the average temperature of each point within the target region to obtain the temperature of the target object being measured.

[0094] In some embodiments, a computer program is executed by a processor to achieve the following: when the difference between the temperature of the target temperature measurement object and a preset temperature is greater than a preset threshold, the temperature of the target temperature measurement object is re-acquired based on a pre-trained image recognition model.

[0095] In some embodiments, a computer program is executed by a processor to generate a temperature measurement report of the target object, the temperature measurement report including the output of an image recognition model and the temperature of the target object.

[0096] Furthermore, this disclosure also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, implement the temperature measurement method described above.

[0097] In some embodiments, when the computer program or instructions are executed by a processor, they perform the following: acquiring an infrared image of the area where the target temperature measurement object is located; determining the image region corresponding to the target temperature measurement object in the infrared image based on a pre-trained image recognition model; and calculating the temperature of the target temperature measurement object based on the temperature data corresponding to the image region.

[0098] The image recognition model is trained as follows: For each sample temperature measurement object, the inspection equipment and its infrared imaging device are adjusted to the corresponding temperature measurement pose; a sample image of the sample temperature measurement object and its annotation results are acquired; based on the sample images and annotation results corresponding to multiple sample temperature measurement objects, the image recognition model to be trained is trained to obtain a pre-trained image recognition model. Adjusting the inspection equipment and its infrared imaging device to the corresponding temperature measurement pose includes: controlling the inspection equipment to move into the temperature measurement area where the sample temperature measurement object is located; adjusting the posture of the inspection equipment and the infrared imaging device so that the sample temperature measurement object is within the field of view of the infrared imaging device. Based on the sample images and annotation results corresponding to multiple sample temperature measurement objects, the image recognition model to be trained is trained to obtain a pre-trained image recognition model. This includes: performing preset processing operations on the sample images corresponding to multiple sample temperature measurement objects to obtain processed sample images. The preset processing operations include at least one of left-right flipping, up-down flipping, and adding mosaic. Based on the processed sample images and annotation results, the image recognition model to be trained is trained to obtain a pre-trained image recognition model.

[0099] In some embodiments, when the computer program or instructions are executed by the processor, the following are implemented: obtaining the target temperature measurement pose corresponding to the target temperature measurement object, the target temperature measurement pose including the device pose of the inspection equipment and the imaging pose of the infrared imaging device on the inspection equipment; adjusting the pose of the inspection equipment to the device pose; adjusting the infrared imaging device to the imaging pose; and using the infrared imaging device to acquire images to obtain an infrared image of the area where the target temperature measurement object is located.

[0100] In some embodiments, when the computer program or instructions are executed by a processor, they perform the following: determining the center point of an image region; obtaining the temperature of each point within a target region of a preset size, centered on the center point; and calculating the average temperature of each point within the target region to obtain the temperature of the target temperature measurement object.

[0101] In some embodiments, when the computer program or instructions are executed by the processor, the following is implemented: when the difference between the temperature of the target temperature measurement object and the preset temperature is greater than a preset threshold, the temperature of the target temperature measurement object is re-acquired based on the pre-trained image recognition model.

[0102] In some embodiments, when the computer program or instructions are executed by a processor, the following is achieved: generating a temperature measurement report of the target temperature measurement object, the temperature measurement report including the output of the image recognition model and the temperature of the target temperature measurement object.

[0103] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0104] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A temperature measurement method, characterized in that, The method includes: Acquire infrared images of the area where the target temperature measurement object is located; Based on a pre-trained image recognition model, the image region corresponding to the target temperature measurement object in the infrared image is determined; The temperature of the target temperature measurement object is calculated based on the temperature data corresponding to the image region.

2. The method according to claim 1, characterized in that, The image recognition model was trained using the following method: For each sample temperature measurement object, the inspection equipment and the infrared imaging device on the inspection equipment are adjusted to the temperature measurement pose corresponding to the sample temperature measurement object; Obtain the sample image corresponding to the sample temperature measurement object, and the annotation results of the sample image for the sample temperature measurement object; Based on the sample images and annotation results corresponding to multiple sample temperature measurement objects, the image recognition model to be trained is trained to obtain the pre-trained image recognition model.

3. The method according to claim 2, characterized in that, The step of adjusting the inspection equipment and the infrared imaging device on the inspection equipment to the temperature measurement pose corresponding to the sample temperature measurement object includes: Control the inspection equipment to move to the temperature measurement area where the sample temperature measurement object is located; Adjust the orientation of the inspection equipment and the infrared imaging equipment so that the sample temperature measurement object is within the field of view of the infrared imaging equipment.

4. The method according to claim 2, characterized in that, The image recognition model to be trained is obtained by training sample images and annotation results corresponding to multiple sample temperature measurement objects, including: A preset processing operation is performed on the sample images corresponding to the multiple sample temperature measurement objects to obtain processed sample images. The preset processing operation includes at least one of left-right flipping, up-down flipping, and adding mosaic. Based on the processed sample images and the annotation results, the image recognition model to be trained is trained to obtain the pre-trained image recognition model.

5. The method according to claim 1, characterized in that, The acquisition of the infrared image of the area where the target temperature measurement object is located includes: Obtain the target temperature measurement pose corresponding to the target temperature measurement object, wherein the target temperature measurement pose includes the device pose of the inspection equipment and the imaging pose of the infrared imaging device on the inspection equipment; Adjust the pose of the inspection equipment to the pose of the equipment. Adjust the infrared imaging device to the imaging posture; The infrared imaging device is used to acquire images, thereby obtaining an infrared image of the area where the target temperature measurement object is located.

6. The method according to claim 1, characterized in that, The step of calculating the temperature of the target temperature measurement object based on the temperature data corresponding to the image region includes: Determine the center point of the image region; Using the center point as the center, obtain the temperature of each point within a target area of ​​a preset size; The average temperature of each point within the target area is calculated to obtain the temperature of the target temperature measurement object.

7. The method according to claim 1, characterized in that, The method further includes: When the difference between the temperature of the target temperature measurement object and the preset temperature is greater than a preset threshold, the temperature of the target temperature measurement object is re-acquired based on the pre-trained image recognition model.

8. The method according to claim 1, characterized in that, The method further includes: A temperature measurement report is generated for the target temperature measurement object, the temperature measurement report including the output result of the image recognition model and the temperature of the target temperature measurement object.

9. An electronic device, characterized in that, include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in any one of claims 1-8.

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 method as described in any one of claims 1-8.

Images