Temperature measurement method, temperature measurement device, terminal equipment and storage medium

Abstract

The present application provides a temperature measurement method, a temperature measurement device, a terminal device and a storage medium, which relate to the field of temperature measurement technology and can accurately and conveniently measure the temperature of a device. The temperature measurement method includes: acquiring a first image, the first image containing information of a first device; inputting the first image into a preset target detection model to obtain a first detection result, the first detection result containing a temperature measurement area of ​​the first device obtained by detection, the temperature measurement area containing at least one temperature measurement target; determining the contour information of each temperature measurement target from the temperature measurement area through a preset image segmentation model; for each temperature measurement target, obtaining the temperature measurement result of the temperature measurement target based on the temperature detection information and the contour information of the first device.

Description

Technical Field

[0001] The present application belongs to the field of temperature measurement technology, and in particular relates to a temperature measurement method, a temperature measurement device, a terminal device and a storage medium. Background Art

[0002] During the operation of the equipment, the temperature of the equipment is often monitored to determine whether the equipment is in normal working condition, and a quick response and maintenance can be given when the temperature of the equipment is detected to be abnormal.

[0003] At present, the temperature of the equipment is usually detected by manually setting a temperature detection device at the temperature measurement point of the equipment. If there are fewer temperature detection devices, the detection effect may be poor; and if multiple temperature detection devices are set at multiple locations of the equipment, the cost will be high and may be limited by the structure of the equipment. In addition, the installation and maintenance of the temperature detection device on the equipment is also time-consuming and labor-intensive, and the labor cost is high. Therefore, there is an urgent need for an accurate and convenient method for detecting the temperature of the equipment. Summary of the invention

[0004] The embodiments of the present application provide a temperature measurement method, a temperature measurement device, a terminal device and a storage medium, which can accurately and conveniently measure the temperature of a device.

[0005] In a first aspect, an embodiment of the present application provides a temperature measurement method, comprising:

[0006] Acquire a first image, where the first image includes image information of a first device;

[0007] Inputting the first image into a preset target detection model to obtain a first detection result, where the first detection result includes a temperature-to-be-measured area of ​​the first device obtained by detection, where the temperature-to-be-measured area includes at least one temperature measurement target;

[0008] Determine the contour information of each temperature measurement target from the temperature measurement area through a preset image segmentation model;

[0009] For each temperature measurement target, a temperature measurement result of the temperature measurement target is obtained according to the temperature detection information for the first device and the profile information.

[0010] The temperature measurement method provided in the embodiment of the present application first obtains a first image containing information of a first device, and then detects the first image through a preset target detection model to determine the temperature measurement area of ​​the first device contained in the first image and at least one temperature measurement target in the temperature measurement area to understand the temperature measurement targets contained in the first image. Then, the temperature measurement area is further processed through a preset image segmentation model, and the contour information of each of the temperature measurement targets is determined from the temperature measurement area to shield the interference factors in the environment, so as to achieve the purpose of separating each temperature measurement target from the first image, so as to avoid interference from the interference factors in the environment when obtaining the temperature measurement results later. Finally, for each temperature measurement target, the temperature measurement result of the temperature measurement target is obtained according to the temperature detection information and the contour information of the first device, so as to achieve the purpose of fine temperature measurement of the temperature measurement target in the temperature measurement area to be measured.

[0011] In a second aspect, an embodiment of the present application provides a temperature measuring device, comprising:

[0012] A first acquisition module, used to acquire a first image, where the first image includes image information of a first device;

[0013] A second acquisition module is used to input the first image into a preset target detection model to obtain a first detection result, where the first detection result includes a temperature-to-be-measured area of ​​the first device obtained by detection, where the temperature-to-be-measured area includes at least one temperature measurement target;

[0014] A determination module, used to determine the contour information of each temperature measurement target from the temperature measurement area through a preset image segmentation model;

[0015] The third acquisition module is used to obtain, for each temperature measurement target, a temperature measurement result of the temperature measurement target according to the temperature detection information of the first device and the profile information.

[0016] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the temperature measurement method is implemented when the processor executes the computer program.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the temperature measurement method when executed by a processor.

[0018] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device executes the temperature measurement method described in any one of the above-mentioned first aspects.

[0019] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0021] Figure 1 It is a flow chart of a temperature measurement method provided in one embodiment of the present application.

[0022] Figure 2 It is a schematic diagram of a specific implementation flow of step S11 of the temperature measurement method provided in one embodiment of the present application.

[0023] Figure 3 is a schematic diagram of a first image provided by an embodiment of the present application.

[0024] Figure 4 It is a structural schematic diagram of a temperature measuring device provided in one embodiment of the present application.

[0025] Figure 5 It is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In the following description, specific details such as specific system structures and technologies are provided for illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details.

[0027] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0028] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0029] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0030] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0031] See also Figure 1 , Figure 1 It is a flow chart for implementing a temperature measurement method provided in an embodiment of the present application. In this embodiment, the temperature measurement method is used to measure the temperature of the equipment during the operation and maintenance of the equipment, so as to understand the working status of the equipment through the measured temperature, and the execution subject is the terminal device. The terminal device can be the robot itself that performs the operation and maintenance tasks, or it can be other devices other than the robot. When the terminal device is other devices other than the robot, data communication can be performed between the terminal device and the robot to realize data interaction between the two, as well as operations such as control of the robot.

[0032] like Figure 1 As shown, the temperature measurement method provided in the embodiment of the present application includes the following steps:

[0033] S11: Acquire a first image, where the first image includes image information of a first device.

[0034] In step S11, the first image is a picture containing information of the first device taken by the terminal device through a camera device. It can be understood that the appearance of the first device and the background environment where the first device is located can be understood through the first image.

[0035] For example, the first device is a substation installed in a corner, and the terminal device takes a picture of the corner through a camera device, and the picture includes image information of the substation.

[0036] The first device is a target device whose working status needs to be known. For example, during the operation and maintenance of a substation, a transformer whose working status needs to be known.

[0037] In this embodiment, since the first image contains the image information of the first device, the performance structure of the first device can be understood by acquiring the first image, and the performance structure may include the overall shape structure of the first device, the components of the first device that can be observed from the outside and may be measured, the external performance part of the first device corresponding to the determined temperature measurement target, and the sub-device of the first device, etc. Therefore, acquiring the first image can better determine the temperature measurement target corresponding to the first device, so as to provide a basis for data analysis.

[0038] As for when to acquire the first image, it may include but is not limited to the following three scenarios.

[0039] Scenario 1: When the robot drives to a preset area according to navigation information, a first image is acquired.

[0040] For example, when an inspection robot performing an inspection task in a substation drives to a room where a first device is installed according to navigation information, the inspection robot acquires a first image through a camera device.

[0041] Scenario 2: When the robot detects a target signal sent by the first device, a first image is acquired.

[0042] For example, when an inspection robot performing an inspection task in a substation drives to a room where a first device is installed and detects a target signal broadcast by the first device, it means that the inspection robot is within an observable distance range from the first device, and the inspection robot obtains a first image through a camera device.

[0043] Scenario 3: When a temperature measurement instruction is received, a first image is acquired.

[0044] For example, when an inspection robot performing an inspection task in a substation drives to a room where a first device is installed and receives a temperature measurement instruction for the first device, the inspection robot acquires a first image through a camera device.

[0045] It should be understood that, in practical applications, the camera device for acquiring the first image can be set on the terminal device, or set outside the terminal device and communicated with the terminal device. After the camera device acquires the first image, it can be transmitted back to the terminal device so that the terminal device processes the first image, thereby determining the temperature measurement target, and measuring the temperature of the temperature measurement target to obtain the temperature measurement result of the temperature measurement target.

[0046] S12: Input the first image into a preset target detection model to obtain a first detection result, where the first detection result includes a temperature-measured area of ​​the first device obtained by detection, where the temperature-measured area includes at least one temperature measurement target.

[0047] In step S12, the temperature-measured area is an area including the temperature-measured target in the first device. Figure 3 The temperature measurement area corresponding to the temperature measurement target A or the temperature measurement target B in the figure.

[0048] The temperature measurement target is a component or sub-device in the first device whose temperature is to be measured. It is understandable that in order to better understand the working state of the first device, there is at least one temperature measurement target in the first device.

[0049] For example, see Figure 3 The points to be measured in the first device include A and B, and the rectangular area determined based on the two points is the area to be measured, and the area to be measured includes two temperature measurement targets, A and B.

[0050] In this embodiment, a pre-trained preset target detection model is pre-stored in the terminal device. The preset target detection model is obtained by training the initial preset target detection model based on a sample training set using a machine learning algorithm. The initial preset target detection model is a deep learning network model provided by the present application for realizing the detection of a temperature measurement target in a first image with an image of the first device as a reference.

[0051] It is understandable that the preset target detection model can be pre-trained by the terminal device, or it can be pre-trained by other devices and then the file corresponding to the preset target detection model can be transplanted to the terminal device. In other words, the execution subject of training the preset target detection model and the execution subject of using the preset target detection model for temperature measurement target detection can be the same or different. For example, when other devices are used to train the initial preset target detection model, after the other devices finish training the initial preset target detection model, the model parameters of the initial preset target detection model are fixed, and the file corresponding to the preset target detection model is obtained, and then the file is transplanted to the terminal device.

[0052] After acquiring the first image to be detected, the terminal device detects the first image through a preset target detection model to determine the temperature measurement area to be measured of the first device contained in the first image and at least one temperature measurement target included in the temperature measurement area to be measured, so as to understand the temperature measurement target contained in the first image, so as to facilitate the subsequent determination of the temperature measurement result corresponding to the temperature measurement target.

[0053] S13: Determine contour information of each temperature measurement target in the temperature measurement area through a preset image segmentation model.

[0054] In step S13, after obtaining the first detection result, in order to better measure the temperature of the temperature measurement target, the terminal device further performs image segmentation processing on the temperature measurement area through a preset image segmentation model, and determines the contour information of each of the temperature measurement targets in the temperature measurement area to be measured, so as to separate the corresponding temperature measurement target from the temperature measurement area according to the contour information of each temperature measurement target, thereby completing the purpose of separating each temperature measurement target from the first image, and thereby shielding interference factors in the environment, so as to avoid interference from interference factors in the environment when subsequently obtaining the temperature measurement result of the temperature measurement target.

[0055] For example, see Figure 3 The temperature measurement area includes two temperature measurement targets. The preset image segmentation model is used to determine the contour information corresponding to the temperature measurement target A and the temperature measurement target B from the temperature measurement area, so as to separate the temperature measurement target A and the temperature measurement target B from the first image, thereby facilitating the temperature measurement operation.

[0056] In this embodiment, a pre-trained preset image segmentation model is pre-stored in the terminal device. The preset image segmentation model is obtained by training the initial preset image segmentation model based on a sample training set using a machine learning algorithm. Among them, the initial preset image segmentation model is a deep learning network model provided by the present application for realizing segmentation processing of the temperature measurement targets in the temperature measurement area when the image of the temperature measurement area contains various temperature measurement targets as references.

[0057] It is understandable that the preset image segmentation model can be pre-trained by the terminal device, or it can be pre-trained by other devices and then the file corresponding to the preset image segmentation model can be transplanted to the terminal device. In other words, the execution subject of training the preset image segmentation model and the execution subject of using the preset image segmentation model for temperature measurement target detection can be the same or different. For example, when other devices are used to train the initial preset image segmentation model, after the other devices finish training the initial preset image segmentation model, the model parameters of the initial preset image segmentation model are fixed, and the file corresponding to the preset image segmentation model is obtained, and then the file is transplanted to the terminal device.

[0058] S14: For each temperature measurement target, obtain a temperature measurement result of the temperature measurement target according to the temperature detection information of the first device and the profile information.

[0059] In step S14, the temperature detection information is data obtained by performing temperature detection on the environment area where the first device is located. The temperature detection information can be used to understand the temperature detection conditions of each temperature measurement target in the first device and the temperature detection conditions of the first device other than the temperature measurement target.

[0060] It can be understood that the temperature detection information includes temperature detection data corresponding to each temperature measurement target in the temperature measurement area.

[0061] The temperature measurement result is used to describe the temperature condition corresponding to the temperature measurement target. For example, the first device is a transformer, and component A in the transformer is the temperature measurement target. The temperature of component A is 50° C. as known from the temperature measurement result.

[0062] In this embodiment, the position of the temperature measurement target in the first image can be located through the contour information of the temperature measurement target, and the temperature detection condition of the corresponding position recorded in the temperature detection information is determined based on the position, thereby obtaining the temperature measurement result of the temperature measurement target.

[0063] For example, see Figure 3 After determining the contour information corresponding to the temperature measurement target A and the temperature measurement target B respectively through the preset image segmentation model, the temperature measurement result of the temperature measurement target A is determined to be 36°C and the temperature measurement result of the temperature measurement target B is determined to be 40°C according to the temperature detection information of the first device and the contour information corresponding to each temperature measurement target.

[0064] In some embodiments, for each temperature measurement target, obtaining a temperature measurement result of the temperature measurement target according to the temperature detection information for the first device and the profile information includes:

[0065] For each temperature measurement target, determine whether the area occupied by the temperature measurement target meets a preset area condition according to the contour information corresponding to the temperature measurement target;

[0066] If the area occupied by the temperature measurement target meets the preset area condition, the step of obtaining the temperature measurement result of the temperature measurement target according to the temperature detection information of the first device and the profile information is performed;

[0067] If the area occupied by the temperature measurement target does not meet the preset area condition, the first image is input into a preset target detection model to obtain a third detection result, and the contour information of the temperature measurement target is determined from the temperature measurement area to be measured by a preset image segmentation model, and the temperature measurement result of the temperature measurement target is obtained according to the temperature detection information for the first device and the contour information. The third detection result includes the temperature measurement area to be measured of the first device obtained by detection, and the temperature measurement area to be measured includes at least one temperature measurement target.

[0068] In some embodiments, for each temperature measurement target, obtaining a temperature measurement result of the temperature measurement target according to the temperature detection information for the first device and the profile information includes:

[0069] For each temperature measurement target, determining whether the profile information of the temperature measurement target meets a preset profile information condition;

[0070] If the profile information of the temperature measurement target meets the preset profile information condition, the temperature measurement result of the temperature measurement target is obtained according to the temperature detection information for the first device and the profile information.

[0071] The temperature measurement method provided in the embodiment of the present application first obtains a first image containing information of a first device, and then detects the first image through a preset target detection model to determine the temperature measurement area of ​​the first device contained in the first image and at least one temperature measurement target in the temperature measurement area to understand the temperature measurement target contained in the first image. Then, the temperature measurement area is further processed through a preset image segmentation model, and the contour information of each temperature measurement target is determined from the temperature measurement area to shield the interference factors in the environment, so as to achieve the purpose of separating each temperature measurement target from the first image, so as to avoid interference from the interference factors in the environment when obtaining the temperature measurement results later. Finally, for each temperature measurement target, the temperature measurement result of the temperature measurement target is obtained according to the temperature detection information and the contour information of the first device, and the purpose of fine temperature measurement of the temperature measurement target in the temperature measurement area to be measured is achieved.

[0072] See also Figure 2 In one embodiment of the present application, the acquiring of the first image includes:

[0073] S21: Obtain temperature matrix data collected by the infrared camera;

[0074] S22: Generate the first image according to the temperature matrix data.

[0075] In this embodiment, the temperature matrix data is used to describe the temperature of the environment area where the first device is located. It is understandable that the temperature matrix data includes the temperature of the temperature measurement target in the temperature measurement area corresponding to the first device, and the temperature of other places other than the temperature measurement target.

[0076] In this embodiment, the first image may be a color infrared image generated based on temperature matrix data, or a non-color image generated based on temperature matrix data.

[0077] In this embodiment, the temperature values ​​of each point in the environment area where the first device is located and the temperature values ​​of each point in the first device are collected by an infrared camera, and temperature matrix data is obtained according to the temperature values ​​of each point. Further, a preset image generation process is performed according to the temperature matrix data to obtain a first image, for example, after a preset color image process is performed according to the temperature matrix data, the first image is mapped. According to the scheme of this embodiment, since the temperature matrix data can be converted into a color infrared image by processing, but the temperature matrix data cannot be reversely generated from the color infrared image, after the temperature matrix data is obtained in this embodiment, the collected temperature matrix data can be used as a backup, or so that the working status of the first device can be secondary checked based on the temperature matrix data in the future, so as to better understand the working status of the first device.

[0078] In one possible scenario, such as in a substation operation and maintenance scenario, since the energized equipment in the substation has good main-background separation and equipment distinctiveness in the infrared image compared to the environment, collecting temperature matrix data through an infrared camera and generating a first image is conducive to achieving the purpose of hierarchical detection of the first device and the temperature measurement target, and can better locate the temperature measurement target accurately through hierarchical detection, thereby accurately measuring the temperature or performing operations such as defect analysis.

[0079] In some embodiments, the temperature matrix data includes multiple rows of temperature data. After the first image is generated according to the temperature matrix data, there is a one-to-one correspondence between the first image and the temperature matrix data.

[0080] For example, a temperature value included in a row in the temperature matrix data, the position of the temperature value in the temperature matrix data corresponds to the position of a pixel in the first image, that is, there is a one-to-one correspondence between the position of the temperature value of the temperature matrix data and the position of the pixel in the first image. The purpose is that when it is necessary to understand the temperature condition of a certain temperature measurement target in the first image, based on the position of the temperature measurement target, the temperature data of the corresponding position can be directly found from the temperature matrix data, and the temperature data can be used as the temperature measurement result of the temperature measurement target.

[0081] In one embodiment, in order to facilitate the detection of the temperature measurement target and overcome the limitation that the current detection algorithm has difficulty in detecting small targets, after obtaining the first image, the first image is finely labeled at three levels, that is, the first level is labeled as a rectangular frame of the first device, the second level is the rectangular frame of the temperature measurement target, and the third level is the contour area of ​​the temperature measurement target.

[0082] As a possible implementation of the present application, generating the first image according to the temperature matrix data includes:

[0083] Performing a preset filtering process on the temperature matrix data to obtain filtered temperature matrix data;

[0084] Performing standard normal distribution processing on the filtered temperature matrix data to obtain normalized temperature matrix data;

[0085] Normalizing the normalized temperature matrix data to obtain normalized temperature matrix data;

[0086] Generating a grayscale image according to the normalized temperature matrix data;

[0087] The first image is obtained according to the grayscale image.

[0088] In this embodiment, the preset filtering process includes at least one of a median filtering process and a mean filtering process.

[0089] It is understandable that in the process of collecting temperature matrix data, it often includes more time periods, and the environment and equipment temperature in different time periods may be different. Therefore, in order to make the pixel distribution of the first image generated by the same temperature measurement point more uniform, it is necessary to perform preset filtering processing, standard normal distribution processing and normalization processing on the temperature matrix data, and generate a grayscale image based on the normalized temperature matrix data, and then obtain a first image with a relatively uniform pixel distribution according to the grayscale image. Among them, the standard normal distribution processing and normalization processing can refer to the relevant technical solutions in the prior art, which will not be repeated here.

[0090] In some embodiments, color image processing is performed on the grayscale image to obtain the first image.

[0091] In an embodiment of the present application, the temperature detection information includes the temperature matrix data.

[0092] The step of obtaining, for each temperature measurement target, a temperature measurement result of the temperature measurement target according to the temperature detection information of the first device and the profile information includes:

[0093] For each temperature measurement target, a temperature measurement result of the temperature measurement target is obtained according to the temperature matrix data and the profile information.

[0094] In this embodiment, since the temperature matrix data includes the temperatures of each point in the environmental area corresponding to the first device, and the first image is generated based on the temperature matrix data, after determining the contour information of the temperature measurement target in the first image, the contour information can be matched with the corresponding position in the temperature matrix data, and the temperature corresponding to the successfully matched position can be used as the temperature measurement result of the temperature measurement target.

[0095] In an embodiment of the present application, inputting the first image into a preset target detection model to obtain a first detection result includes:

[0096] Inputting the first image into a first object detection model to obtain a second detection result, where the second detection result includes information of an initial area in the first image, where the initial area includes image information of the first device;

[0097] Obtaining a second image according to the initial area in the first image;

[0098] The second image is input into a second object detection model to obtain the first detection result.

[0099] In this embodiment, after acquiring the first image, the terminal device first inputs the first image into the first target detection model in order to determine the temperature measurement target corresponding to the first device in the first image, so as to preliminarily locate the position of the first device in the first image through the first detection model, and obtain a second detection result that can describe the initial area containing the image information of the first device. Further, in order to further determine the position of the temperature measurement target corresponding to the first device, first obtain the second image according to the initial area in the first image, and use the second image as input data of the second target detection model, so as to accurately locate the position of the temperature measurement target corresponding to the first device in the initial area through the second target detection model, and obtain a first detection result that can describe the temperature measurement area to be measured of the first device, so as to continue to detect the temperature measurement target in the temperature measurement area to be measured based on the preset image segmentation model, and obtain the contour information of each temperature measurement target, so as to facilitate shielding the background information other than the temperature measurement target in the temperature measurement area to be measured based on the contour information.

[0100] It can be understood that since the objects detected by the first target detection model and the second target detection model are different, the first target detection model and the second target detection model can be obtained by training the initial first target detection model and the initial second target detection model using different training data sets respectively.

[0101] In one embodiment, a temperature measurement method is provided, which mainly involves a training process of a first target detection model, a second target detection model and a preset image segmentation model.

[0102] In this embodiment, a plurality of temperature matrix data are obtained, and a training image is obtained based on the conversion of each temperature matrix data. For each training image, according to the principle of three-level annotation, the first device, the temperature measurement area and the temperature measurement target in the training image are located and annotated at three levels. Then, the training data set corresponding to each annotation level is obtained according to the aforementioned annotation separation and cropping. The first data set corresponds to the annotation of level one, including the training image for annotating the position of the first device; the second data set corresponds to the annotation of level two, including the sub-image of the first device in the training image and the temperature measurement area; the third data set corresponds to the annotation of level three, including the temperature measurement target separated from the training image and excluding the background. After obtaining the above three data sets, the initial first target detection model, the initial second target detection model and the initial image segmentation model are trained using the first data set, the second data set and the third data set respectively to obtain the final first target detection model, the second target detection model and the preset image segmentation model.

[0103] In an embodiment of the present application, the second image includes the initial area magnified according to the target magnification.

[0104] In this embodiment, the initial area is magnified according to the target magnification factor. Its purpose is that when the temperature measurement target corresponding to the first device contained in the first image is very small and difficult to be directly detected by the target detection algorithm due to the accuracy problem of the algorithm, after the initial area containing the first device is magnified by the target magnification factor, the position of the first device in the initial area after the target magnification factor is magnified in the second image can be better detected by the second target detection model, and a first detection result of the temperature measurement area to be measured containing the first device obtained by detection is obtained, so that the temperature measurement target can be measured more finely in the subsequent process.

[0105] In one embodiment, the initial area is magnified by a target magnification by means of coordinate transformation. Specifically, after the initial area in the first image is initially determined by the first target detection model, the pixels of the initial area are magnified by means of coordinate transformation to obtain a second image, so that when the second image is detected by the second target detection model, the temperature area to be measured in the second image can be better detected, and finally the first detection result is obtained.

[0106] That is to say, when the deep learning target detection algorithm is currently used to detect targets, due to the accuracy of the algorithm, there is a problem that it is impossible or difficult to accurately detect small targets in the image. The solution of this embodiment can better solve this problem, that is, the solution of this embodiment can better avoid the problem of small target detection based on the deep learning target detection algorithm, and achieve the purpose of detecting small targets, thereby more finely detecting the temperature measurement target corresponding to the first device, so as to better determine the temperature measurement result of the temperature measurement target.

[0107] In an embodiment of the present application, after obtaining the temperature measurement result of each temperature measurement target according to the temperature detection information of the first device and the profile information, the method further includes:

[0108] Defect diagnosis information of each temperature measurement target is determined according to the temperature measurement result of each temperature measurement target.

[0109] In this embodiment, the defect diagnosis information describes whether there is a defect at the temperature measurement target. For example, when the temperature measurement result of the temperature measurement target shows that the temperature of the temperature measurement target is higher than the preset temperature value, it means that the temperature measurement target has an overheating defect, and the corresponding defect diagnosis information describes that the temperature measurement target has an overheating defect.

[0110] It can be understood that since the temperature measurement results can describe the temperature conditions of the temperature measurement targets, the working state of the first device can be reflected through the temperature conditions. Therefore, when the first device is in a normal working state, the temperature measurement results corresponding to each temperature measurement target also appear normal. When the first device is in an abnormal working state, there will be abnormal temperature measurement results in the temperature measurement results corresponding to each temperature measurement target.

[0111] In this embodiment, the temperature measurement result includes the position information of the temperature measurement target and the corresponding temperature value. Whenever the temperature measurement result of a temperature measurement target is obtained, the temperature value of the temperature measurement target is compared with the preset temperature value. If it is determined that the temperature value of the temperature measurement target is higher than the preset temperature value, it is determined that the temperature of the temperature measurement target has an overheating defect, indicating that the working state of the first device is abnormal. On the contrary, if it is determined that the temperature value of the temperature measurement target is lower than or equal to the preset temperature value, it is determined that the temperature of the temperature measurement target does not have an overheating defect, indicating that the first device is in a normal working state.

[0112] In a possible application scenario, the first device is a substation device in a substation that is energized and in operation. According to the temperature measurement results of each of the temperature measurement targets, the defect diagnosis information of each of the temperature measurement targets is determined, and then it is determined whether the substation device has a defect according to the defect diagnosis information, thereby achieving the purpose of automatic defect analysis of the substation device.

[0113] In some embodiments, when the defect diagnosis information of the temperature measurement targets exceeding a preset number ratio indicates that the temperature of the temperature measurement targets is abnormal, it is determined that the working state of the first device is abnormal. According to the information of the abnormal working state of the first device, abnormal alarm information is generated and sent to the second device, so that the user can view the abnormal situation of the first device through the second device.

[0114] Among them, the preset number ratio is the minimum ratio between the number of normal temperature measurement targets indicated by the defect diagnosis information and the number of abnormal temperature measurement targets indicated by the defect diagnosis information when it is determined that the working state of the first device is abnormal.

[0115] The temperature measurement method provided in the embodiment of the present application first obtains a first image containing information of a first device, and then detects the first image through a preset target detection model to determine the temperature measurement area of ​​the first device contained in the first image and at least one temperature measurement target in the temperature measurement area to understand the temperature measurement target contained in the first image. Then, the temperature measurement area is further processed through a preset image segmentation model, and the contour information of each temperature measurement target is determined from the temperature measurement area to shield the interference factors in the environment, so as to achieve the purpose of separating each temperature measurement target from the first image, so as to avoid interference from the interference factors in the environment when obtaining the temperature measurement results later. Finally, for each temperature measurement target, the temperature measurement result of the temperature measurement target is obtained according to the temperature detection information and the contour information of the first device, and the purpose of fine temperature measurement of the temperature measurement target in the temperature measurement area to be measured is achieved.

[0116] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0117] Corresponding to the temperature measurement method described in the above embodiment, Figure 4 A structural block diagram of a temperature measuring device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0118] Reference Figure 4 , the temperature measuring device 100 comprises:

[0119] A first acquisition module 101 is used to acquire a first image, where the first image includes image information of a first device;

[0120] A second acquisition module 102 is used to input the first image into a preset target detection model to obtain a first detection result, where the first detection result includes a temperature-to-be-measured area of ​​the first device obtained by detection, where the temperature-to-be-measured area includes at least one temperature measurement target;

[0121] A determination module 103 is used to determine the contour information of each temperature measurement target from the temperature measurement area through a preset image segmentation model;

[0122] The third acquisition module 104 is used to obtain, for each temperature measurement target, a temperature measurement result of the temperature measurement target according to the temperature detection information of the first device and the profile information.

[0123] In one embodiment, the first acquisition module 101 is further used to acquire temperature matrix data collected by an infrared camera; and generate the first image according to the temperature matrix data.

[0124] In one embodiment, the first acquisition module 101 is also used to perform a preset filtering process on the temperature matrix data to obtain filtered temperature matrix data; perform standard normal distribution processing on the filtered temperature matrix data to obtain normalized temperature matrix data; perform normalization processing on the normalized temperature matrix data to obtain normalized temperature matrix data; generate a grayscale image based on the normalized temperature matrix data; and obtain the first image based on the grayscale image.

[0125] In one embodiment, the temperature detection information includes the temperature matrix data.

[0126] The third acquisition module 104 is further used to obtain, for each temperature measurement target, a temperature measurement result of the temperature measurement target according to the temperature matrix data and the profile information.

[0127] In one embodiment, the second acquisition module 102 is also used to input the first image into a first target detection model to obtain a second detection result, wherein the second detection result includes information of an initial area in the first image, and the initial area includes image information of the first device; obtain a second image based on the initial area in the first image; and input the second image into a second target detection model to obtain the first detection result.

[0128] In one embodiment, the second image includes the initial area magnified according to the target magnification.

[0129] In one embodiment, the temperature measuring device 100 further includes a diagnosis module.

[0130] The diagnosis module is used to determine the defect diagnosis information of each temperature measurement target according to the temperature measurement result of each temperature measurement target.

[0131] A temperature measuring device provided in this embodiment may specifically be a robot, which is used to implement any temperature measuring method described in the method embodiment. The functions of each module may refer to the corresponding description in the method embodiment, and the implementation principles and technical effects are similar, which will not be repeated here.

[0132] Figure 5 This is a schematic diagram of the structure of a terminal device provided in an embodiment of the present application. Figure 5 As shown, the terminal device 5 of this embodiment includes: at least one processor 50 ( Figure 5 Only one processor is shown in the figure), a memory 51, and a computer program 52 stored in the memory 51 and executable on the at least one processor 50, wherein the processor 50 implements the steps of any one of the above-mentioned temperature measurement method embodiments when executing the computer program 52.

[0133] The terminal device 5 may be a robot, a mobile phone, a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will understand that Figure 5 It is only an example of the terminal device 5 and does not constitute a limitation on the terminal device 5. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0134] The processor 50 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) 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, etc.

[0135] In some embodiments, the memory 51 may be an internal storage unit of the terminal device 5, such as a hard disk or memory of the terminal device 5. In other embodiments, the memory 51 may also be an external storage device of the terminal device 5, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 5. Further, the memory 51 may also include both an internal storage unit and an external storage device of the terminal device 5. The memory 51 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 51 may also be used to temporarily store data that has been output or is to be output.

[0136] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices, means / modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0137] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the modules in the above-mentioned device can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0138] An embodiment of the present application also provides a terminal device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the above-mentioned method embodiments when executing the computer program.

[0139] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0140] An embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0141] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the device / terminal device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0142] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0143] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0144] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0145] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0146] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A temperature measurement method, It is characterized in that include: Acquire a first image, where the first image includes image information of a first device; Inputting the first image into a preset target detection model to obtain a first detection result, including: inputting the first image into a first target detection model to obtain a second detection result, the second detection result including information of an initial area in the first image, the initial area including image information of the first device; obtaining a second image according to the initial area in the first image; inputting the second image into a second target detection model to obtain the first detection result, the first detection result including a temperature-to-be-measured area of ​​the first device obtained by detection, the temperature-to-be-measured area including at least one temperature measurement target; Determine the contour information of each temperature measurement target from the temperature measurement area through a preset image segmentation model; For each temperature measurement target, determine whether the area occupied by the temperature measurement target meets a preset area condition according to the contour information corresponding to the temperature measurement target; If the area occupied by the temperature measurement target meets the preset area condition, for each temperature measurement target, according to the temperature detection information of the first device and the contour information of the temperature measurement target, obtain the temperature measurement result of the temperature measurement target; If the area occupied by the temperature measurement target does not meet the preset area condition, the first image is input into a preset target detection model to obtain a third detection result, and the contour information of the temperature measurement target is determined from the temperature measurement area through a preset image segmentation model, and the temperature measurement result of the temperature measurement target is obtained based on the temperature detection information and the contour information for the first device; wherein the third detection result includes the temperature measurement area to be measured of the first device obtained by detection, and the temperature measurement area to be measured includes at least one temperature measurement target.

2. The temperature measurement method according to claim 1, It is characterized in that The acquiring of the first image comprises: Get the temperature matrix data collected by the infrared camera; The first image is generated according to the temperature matrix data.

3. The temperature measurement method according to claim 2, It is characterized in that Generating the first image according to the temperature matrix data includes: Performing a preset filtering process on the temperature matrix data to obtain filtered temperature matrix data; Performing standard normal distribution processing on the filtered temperature matrix data to obtain normalized temperature matrix data; Normalizing the normalized temperature matrix data to obtain normalized temperature matrix data; Generating a grayscale image according to the normalized temperature matrix data; The first image is obtained according to the grayscale image.

4. The temperature measurement method according to claim 2, It is characterized in that The temperature detection information includes the temperature matrix data; The step of obtaining, for each temperature measurement target, a temperature measurement result of the temperature measurement target according to the temperature detection information of the first device and the profile information includes: For each temperature measurement target, a temperature measurement result of the temperature measurement target is obtained according to the temperature matrix data and the profile information.

5. The temperature measurement method according to claim 1, It is characterized in that The second image includes the initial area magnified according to the target magnification.

6. The temperature measurement method according to any one of claims 1 to 5, It is characterized in that After obtaining the temperature measurement result of each temperature measurement target according to the temperature detection information of the first device and the profile information, the method further includes: Defect diagnosis information of each temperature measurement target is determined according to the temperature measurement result of each temperature measurement target.

7. A temperature measuring device, It is characterized in that The temperature measuring device comprises: A first acquisition module, used to acquire a first image, where the first image includes image information of a first device; a second acquisition module, configured to input the first image into a preset target detection model to obtain a first detection result, wherein the first detection result includes a temperature-to-be-measured area of ​​the first device obtained by detection, wherein the temperature-to-be-measured area includes at least one temperature measurement target; the second acquisition module is further configured to input the first image into a first target detection model to obtain a second detection result, wherein the second detection result includes information of an initial area in the first image, wherein the initial area includes image information of the first device; obtain a second image based on the initial area in the first image; and input the second image into a second target detection model to obtain the first detection result; A determination module, used to determine the contour information of each temperature measurement target from the temperature measurement area through a preset image segmentation model; A third acquisition module is used to obtain, for each temperature measurement target, a temperature measurement result of the temperature measurement target according to the temperature detection information of the first device and the profile information; The temperature measuring device is further used to determine, for each temperature measurement target, whether the area occupied by the temperature measurement target meets a preset area condition according to the contour information corresponding to the temperature measurement target; If the area occupied by the temperature measurement target meets the preset area condition, then for each temperature measurement target, obtaining the temperature measurement result of the temperature measurement target according to the temperature detection information of the first device and the profile information of the temperature measurement target; If the area occupied by the temperature measurement target does not meet the preset area condition, the first image is input into a preset target detection model to obtain a third detection result, and the contour information of the temperature measurement target is determined from the temperature measurement area through a preset image segmentation model, and the temperature measurement result of the temperature measurement target is obtained based on the temperature detection information and the contour information for the first device; wherein the third detection result includes the temperature measurement area to be measured of the first device obtained by detection, and the temperature measurement area to be measured includes at least one temperature measurement target.

8. A terminal device, It is characterized in that The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the temperature measurement method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the temperature measurement method according to any one of claims 1 to 6 is implemented.

Images