Infrared image fault diagnosis method, infrared imaging equipment, medium and product

Abstract

The invention provides an infrared image fault diagnosis method, infrared imaging equipment, a medium and a product. The infrared image fault diagnosis method comprises the following steps: acquiring infrared image data; performing target identification on the infrared image data, and determining a target type and a target edge of a target in the infrared image data; based on the target edge of the target, extracting temperature data in the target edge to obtain target temperature data, and calculating a diagnosis temperature based on the target temperature data; determining a matched diagnosis rule according to the target type; and obtaining a fault diagnosis result of the target according to the diagnosis rule and the diagnosis temperature.

Description

Technical Field

[0001] The present application relates to the field of infrared image technology, and particularly to an infrared image fault diagnosis method, an infrared imaging device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the development of infrared technology, infrared images are often used in fault diagnosis. However, for many complex scenes containing a large number of targets, the amount of infrared image and its temperature data is very large. How to more accurately identify specific types of targets in the infrared image and avoid interference from the surrounding environment on the temperature detection of the targets has become an urgent problem to be solved in the field of intelligent fault diagnosis using infrared images. Summary of the Invention

[0003] To solve the existing technical problems, the present application provides an infrared image fault diagnosis method, an infrared imaging device, a computer-readable storage medium, and a computer program product that can effectively reduce the heat interference of non-targets, simplify operations, and improve detection accuracy.

[0004] In a first aspect, an embodiment of the present application provides an infrared image fault diagnosis method, including:

[0005] Obtain infrared image data;

[0006] Perform target recognition on the infrared image data to determine the target type and target edge of the target in the infrared image data;

[0007] Based on the target edge of the target, extract the temperature data within the target edge to obtain target temperature data, and calculate a diagnostic temperature based on the target temperature data;

[0008] Determine a matching diagnostic rule according to the target type;

[0009] Obtain a fault diagnosis result of the target according to the diagnostic rule and the diagnostic temperature.

[0010] In a second aspect, an embodiment of the present application provides an infrared imaging device, including a memory, a processor, and an infrared image acquisition device;

[0011] The infrared image acquisition device acquires infrared image data and sends it to the processor;

[0012] The processor stores a computer program therein, and the processor is configured to execute the computer program to implement the infrared image fault diagnosis method according to any embodiment of the present application.

[0013] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the infrared image fault diagnosis method described in any embodiment of the present application is implemented.

[0014] In a fourth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the infrared image fault diagnosis method described in any embodiment of the present application is implemented.

[0015] In the above embodiments, in the infrared image fault diagnosis method, by using a target recognition algorithm to identify the target type and target edge of the target in the infrared image data, by specifically extracting the temperature data within the corresponding target area according to the target edge, and by target recognition to identify the target type and determine the target edge, the temperature data within the range of the area belonging to the corresponding target can be more accurately extracted to calculate the diagnostic temperature, so as to exclude the heat interference of non-targets around. Then, by using the diagnostic rule matching the target type of the corresponding target to determine the fault diagnosis result of the target, the operation of the staff can be simplified and the detection accuracy can be improved.

[0016] The infrared imaging device, computer-readable storage medium, and computer program product provided in the above embodiments belong to the same concept as the corresponding embodiments of the infrared image fault diagnosis method, and thus have the same technical effects as the corresponding embodiments of the infrared image fault diagnosis method, which will not be elaborated herein. Description of the Drawings

[0017] Figure 1 It is a schematic diagram of an optional application scenario of the infrared image fault diagnosis method.

[0018] Figure 2 It is a flowchart of the infrared image fault diagnosis method in an embodiment.

[0019] Figure 3 It is an optional schematic diagram of a diagnosis result page in an embodiment.

[0020] Figure 4 It is an optional schematic diagram of a diagnosis result page in another embodiment.

[0021] Figure 5 It is a schematic diagram of the structure of an infrared imaging device in an embodiment. Detailed Embodiments

[0022] The technical solution of the present invention will be further elaborated in detail below with reference to the accompanying drawings of the specification and specific embodiments.

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the following will further describe this application in detail with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

[0024] In the following description, the expression "some embodiments" describes a subset of all possible embodiments. It should be noted that "some embodiments" can be the same subset or different subsets of all possible embodiments, and they can be combined with each other without conflict.

[0025] In the following description, the terms "first", "second", and "third" are only used to distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first", "second", and "third" can be interchanged with a specific order or sequence when permitted, so that the embodiments of this application described here can be implemented in an order other than that illustrated or described here.

[0026] Please refer to Figure 1 , which is a schematic diagram of an optional application scenario of the infrared image fault diagnosis method provided by the embodiments of this application. The infrared image fault diagnosis method is applied to an infrared imaging device. The infrared imaging device can be various devices for collecting infrared image data, such as an infrared thermal imager, a thermal imaging temperature measuring instrument, etc., or other intelligent devices integrated with devices for collecting infrared image data, such as an infrared thermal imager and a thermal imaging temperature measuring instrument, and having communication and storage functions. Among them, the infrared image fault diagnosis method can include the following processes: S1, collecting infrared image data; S2, using a target recognition algorithm to recognize the targets in the infrared image data, and recognizing the target types and target edges of concern; S3, extracting the temperature data within the target edge to calculate the diagnostic temperature of the corresponding target; S4, performing temperature measurement and diagnosis according to the diagnostic rules and diagnostic temperature corresponding to the target.

[0027] In some optional embodiments, the infrared imaging device may refer to an infrared image fault diagnosis system to which the infrared image fault diagnosis method is applied. The infrared image fault diagnosis system includes a plurality of physically separated hardware devices, such as an infrared image acquisition device and a data processing device communicatively connected to the infrared image acquisition device. The infrared image acquisition device is used to execute the process of S1 in the infrared image fault diagnosis method, and the data processing device is used to execute the processes of S2-S4 in the infrared image fault diagnosis method.

[0028] In some other alternative embodiments, the infrared imaging device includes an infrared thermal imager and a terminal device communicatively connected to the infrared thermal imager. The terminal device is configured to execute the process of S2 in the infrared image fault diagnosis method, and the infrared thermal imager is configured to execute the processes of S1, S3 to S4 in the infrared image fault diagnosis method.

[0029] Please refer to Figure 2 , an infrared image fault diagnosis method provided by an embodiment of the present application, includes the following steps:

[0030] S101, obtain infrared image data.

[0031] Among them, the infrared image data may refer to infrared imaging pictures or infrared video frame data collected by a device with infrared image data collection function; it may also refer to obtaining infrared imaging pictures or infrared video frame data collected and sent by a device with infrared image data collection function. The infrared image data can be obtained by real-time collection of a device with infrared image data collection function, or can be pre-collected and stored. The infrared image data can correspondingly refer to multiple infrared imaging pictures collected in real time, or retrieved from an image database, or obtained from other devices through communication, or multiple infrared image frames extracted from infrared video data.

[0032] It should be noted that the infrared image is generated based on the infrared radiation (thermal radiation) emitted or reflected by an object. Thus, the infrared image actually contains both image information and temperature information at the same time. In an alternative specific example, the infrared image data includes temperature data and image data, and can be represented by a temperature data set T mn and an image data set Y mn as follows:

[0033] T p =(x p , w p , t p ), T p ∈T mn ; where x p , w p are the coordinates of point p, and t p is the temperature data value of point p.

[0034] Y p =(x p , w p , y p ), Y p ∈Y mn ; where x p , w p are the coordinates of point p, and y p is the gray value of point p.

[0035] S103. Perform target recognition on the infrared image data to determine the target type and target edge of the target in the infrared image data.

[0036] The target refers to the overall or partial imaging of the target object contained in the infrared image. The target type refers to different target objects or different parts of the target object in the infrared image. The target edge refers to the edge contour of the target object contained in the infrared image. For example, taking the application of the infrared image fault diagnosis method in the field of power equipment inspection as an example, the target refers to multiple components in the power inspection scenario, and the target type correspondingly refers to component A, component B, and component C. Perform target recognition on the infrared image data to determine component A, component B, and component C contained in the infrared image, and determine the respective edge contours corresponding to the recognized component A, component B, and component C; in another optional example, the target type correspondingly refers to parts a1, a2, and a3 corresponding to device a. Perform target recognition on the infrared image data to determine parts a1, a2, and a3 of device a contained in the infrared image, and determine the respective edge contours corresponding to the recognized parts a1, a2, and a3.

[0037] S105. Based on the target edge of the target, extract the temperature data within the target edge to obtain target temperature data, and calculate the diagnostic temperature based on the target temperature data.

[0038] Based on the target edge of the target, extract the temperature data within the target edge to obtain the target temperature data corresponding to the target. In this way, for each target, the temperature data contained within the edge contour of the target itself can be accurately extracted to calculate the diagnostic temperature corresponding to the target, which can avoid the interference of the temperature data of other targets or non-targets around the target. In an optional example, perform target recognition on the infrared image to determine a component A, a component B, and a component C contained in the infrared image, and determine the respective edge contours corresponding to the recognized component A, component B, and component C. For component A, extract the temperature data within the edge contour of component A (the influence of the temperature data of component B and component C on calculating the diagnostic temperature of component A can be excluded) to obtain the target temperature data of component A for calculating the diagnostic temperature of component A; correspondingly, for component B, extract the temperature data within the edge contour of component B (the influence of the temperature data of component A and component C on calculating the diagnostic temperature of component B can be excluded) to obtain the target temperature data of component B for calculating the diagnostic temperature of component B; for component C, extract the temperature data within the edge contour of component C (the influence of the temperature data of component A and component B on calculating the diagnostic temperature of component C can be excluded) to obtain the target temperature data of component C for calculating the diagnostic temperature of component C. Among them, the target temperature data is usually saved in the form of a temperature data set for subsequent data analysis and research applications.

[0039] S107. Determine a matching diagnostic rule according to the target type.

[0040] A diagnostic rule refers to a set of logics or conditions used to judge, classify, or identify the fault problems corresponding to the target. Different target types correspond to different diagnostic rules.

[0041] It should be noted that the corresponding relationship between the target type and the diagnostic rule can be set in advance. After determining the target type of the target in the infrared image data through target recognition of the infrared image data, the diagnostic rule matching the current target type can be determined according to the corresponding relationship between the target type and the diagnostic rule. The diagnostic rule can be preset, or can be configured by the user through a configuration interface provided for the user to set parameters, or can also be obtained by initializing the client program that executes the infrared image fault diagnosis method, or obtained by upgrading the client program that executes the infrared image fault diagnosis method. Through the diagnostic rule, it can be determined whether there is a fault problem according to whether the diagnostic temperature corresponding to the target meets the conditions constrained by its corresponding diagnostic rule.

[0042] S109. Obtain the fault diagnosis result of the target according to the diagnostic rule and the diagnostic temperature.

[0043] For each target, according to the diagnostic temperature calculated based on the temperature data within its own edge contour, the diagnostic temperature is used to identify and diagnose the fault problem through the diagnostic rule matching its target type, and the fault diagnosis result of the target is obtained.

[0044] In the infrared image fault diagnosis method provided by the above embodiment, by using the target recognition algorithm to identify the target type and target edge of the target in the infrared image data, by extracting the temperature data in the corresponding target area specifically according to the target edge, and by target recognition to identify the target type and determine the target edge, the temperature data within the range of the area belonging to the corresponding target can be extracted more accurately to calculate the diagnostic temperature, so as to exclude the heat interference of the surrounding non-targets, and then use the diagnostic rule matching the target type of the corresponding target to determine the fault diagnosis result of the target, which can simplify the operation of the staff and improve the detection accuracy.

[0045] In some embodiments, step S103 includes:

[0046] Use the target recognition algorithm to perform target recognition on the infrared image data, identify the target category and target contour of the target to be measured, and calculate the mask of the target to be measured according to the target contour;

[0047] After the mask of the target to be measured is processed by the non-maximum suppression algorithm, it is then processed by dilation or erosion to obtain the final mask of the target to be measured.

[0048] The target category of the target to be measured is usually preset according to the target that needs to be recognized in the fault diagnosis scenario of the infrared image fault diagnosis method provided by this application embodiment. Taking a certain power inspection scenario as an example, according to different types of components that need to be recognized for faults in the inspection scenario, such as component A, component B, and component C are potential fault risk points that need to be recognized in this inspection scenario, so as to determine that the target to be measured and its target category can be: targets to be measured A, B, and C, and their corresponding target categories can be category A, category B, and category C respectively.

[0049] A mask is a binary or pixel-level label used to represent a specific area or object in an image. A mask can be a matrix with the same size as the image, and each pixel value in the matrix correspondingly represents whether the pixel belongs to a certain target or area.

[0050] The mask of the target to be measured can refer to the mask of the boundary corresponding to the target to be measured determined by mask calculation according to the target contour after the target contour of the target to be measured is recognized by the target recognition algorithm.

[0051] The non-maximum suppression algorithm (Non-Maximum Suppression, nms) processing means removing overlapping boundaries and retaining the most credible one.

[0052] The target recognition algorithm can be selected from various known traditional target recognition algorithms or deep learning-based target recognition algorithms that can detect the target category and its location in the image.

[0053] In the above embodiment, the target recognition algorithm is first used to perform target recognition on the infrared image data, the target to be measured and the target contour in the infrared image are recognized, the mask of the target to be measured is calculated, the mask of the target to be measured is processed by the non-maximum suppression algorithm, and then processed by dilation or erosion to adjust the size and shape of the target area to be measured, and the final mask (Mask_final) of the target to be measured is obtained. The final mask is used to more accurately express the edge contour of the target to be measured.

[0054] In some embodiments, the using the target recognition algorithm to perform target recognition on the infrared image data, recognizing the target category and the target contour of the target to be measured, and calculating the mask of the target to be measured according to the target contour includes:

[0055] Use a pre-trained convolutional neural network as a feature extractor, and train it with an object detection algorithm to obtain an object recognition model; wherein, the object detection algorithm is selected from one of the following: RCNN, Fast RCNN, Faster RCNN, YOLO, SSD;

[0056] Input the infrared image data into the object recognition model;

[0057] Output the object category and object contour of the object to be measured through the object recognition model, and calculate the mask of the interface of the object to be measured by using the object contour.

[0058] In this embodiment, the object recognition algorithm uses a deep learning-based method. A pre-trained convolutional neural network is used as a feature extractor, and a training dataset marked with the object category of the object to be measured, the mask of the object to be measured, and the object bounding box is used to train the feature extractor to obtain an object recognition model. Among the selected object detection algorithms, the basic principle of RCNN is to use selective search to generate candidate regions, extract features through CNN, and finally classify with SVM; the basic principle of Fast RCNN is to integrate classification and bounding box regression into the same network, improving the speed; the basic principle of Faster RCNN is to introduce a Region Proposal Network (RPN) to improve the detection efficiency; YOLO can transform object detection into a regression problem, directly predicting the bounding box and class probability, with high speed and suitable for real-time scenarios; SSD can perform detection on feature maps of multiple scales, suitable for the detection of multi-scale objects. RCNN, Fast RCNN, and Faster RCNN all belong to two-stage object detection algorithms and are applicable to scenarios with higher accuracy requirements, while YOLO and SSD both belong to single-stage object detection algorithms and are applicable to scenarios with higher real-time requirements.

[0059] In the above embodiment, the infrared image fault diagnosis method identifies the objects contained in the infrared image by using an object recognition model based on deep learning, identifies the object category and object contour of the object to be measured contained in the image, calculates the mask of the boundary of the object to be measured, and uses the object recognition result to improve the accuracy of fault diagnosis.

[0060] In some embodiments, step S105 includes:

[0061] Extract the temperature data at the position of the final mask in the temperature dataset of the infrared image data according to the final mask of the object to be measured, and obtain the target temperature data of the object to be measured;

[0062] Calculate the diagnostic temperature based on the target temperature data.

[0063] The final mask is obtained by adjusting according to the self - shape contour of the target to be measured on the basis that the target recognition algorithm recognizes the target contour and calculates the mask of the boundary of the target to be measured.

[0064] In the above - mentioned embodiment, by using the final mask of the target to be measured obtained according to the target recognition result, the temperature data at the position of the final mask is extracted, and the temperature data only contained in the target to be measured itself is obtained to calculate its corresponding diagnostic temperature, which can exclude the interference of other targets or non - targets in the image and improve the accuracy of the diagnostic temperature of the target to be measured.

[0065] It should be noted that the diagnostic temperature can be used to calculate and measure the characteristic temperature indicating whether there is a preset fault for the corresponding target to be measured according to the diagnostic rules corresponding to different targets to be measured. The diagnostic rules corresponding to different targets to be measured can be different, and the diagnostic temperatures that need to be calculated for different targets to be measured can also be different. For example, for the target to be measured A, the diagnostic rule for determining whether there is a fault 1 in the target to be measured A is to determine whether the maximum temperature of the target to be measured A exceeds the temperature threshold A1. In this way, calculating the diagnostic temperature based on the target temperature data of the target to be measured A means calculating the maximum temperature of the target to be measured A. Another example is that for the target to be measured B, the diagnostic rule for determining whether there is a fault 1 in the target to be measured B is to determine whether the maximum temperature of the target to be measured B exceeds the temperature threshold B1 and whether the average temperature exceeds the temperature threshold B2. In this way, calculating the diagnostic temperature based on the target temperature data of the target to be measured B means calculating the maximum temperature and the average temperature of the target to be measured B. In an optional specific example, the diagnostic temperature includes at least one of the following: the maximum temperature, the minimum temperature, the average temperature, and the standard temperature difference within the final mask.

[0066] In some embodiments, after obtaining the final mask of the target to be measured, the infrared image fault diagnosis method further includes:

[0067] According to the final mask, the boundary coordinate set of the target to be measured is calculated by using the binary image contour extraction function, and the target boundary box of the target to be measured is drawn according to the boundary coordinate set; wherein, the binary image contour extraction function is the findContours function.

[0068] The target boundary box is a boundary box representing the position and range of the target in computer vision. In this embodiment, the target boundary box is a boundary contour line drawn along the edge contour conforming to the target shape. The binary image contour extraction function can be selected from known functions for extracting contours from binary images, such as the findContours function in the OpenCV library. Please refer to Figure 3, is a schematic diagram of drawing a corresponding boundary contour line for the edge contour of the target to be measured according to the final mask of the target to be measured. In the target temperature measurement page, drawing an edge contour line for the target edge of the recognized target can facilitate more intuitively seeing the contour of the target to be temperature measured. The user can judge whether the target selected for current image temperature measurement is correct by visually looking at the edge contour line of the target, and whether the range of the temperature data of the target based on which the reference temperature of the target is obtained is accurate.

[0069] In the above embodiment, according to the final mask of the target to be measured, drawing and displaying a corresponding boundary contour line for the edge contour of the target to be measured is beneficial for the user to intuitively and quickly judge the extraction range of the temperature data based on which the diagnostic temperature of the target is calculated. The user can thereby confirm the accuracy of the diagnostic temperature of the current obtained target.

[0070] In some embodiments, step S109 includes:

[0071] Based on a touch command for clicking on a diagnostic identifier in the diagnostic result page, obtaining the fault diagnosis result of the target according to the diagnostic rule and the diagnostic temperature, and displaying the fault diagnosis result on the diagnostic result page; and / or;

[0072] Based on a touch command for clicking on a diagnostic identifier in the diagnostic result page, clearing the current fault diagnosis result, re-determining the diagnostic rule matching the current target type, obtaining the fault diagnosis result of the target according to the diagnostic rule and the diagnostic temperature, and displaying the fault diagnosis result on the diagnostic result page.

[0073] Among them, the diagnostic result page can refer to one of the interfaces of the client program of the infrared image fault diagnosis method, or can include multiple interfaces that support mutual jumping after manual clicking. For example, if the infrared image includes multiple types of targets to be measured, the diagnostic result page can display the fault diagnosis result information corresponding to multiple types of targets to be measured one by one in multiple interfaces.

[0074] The diagnostic identifier can refer to an icon displayed at a preset position on the diagnostic result page. The setting of the diagnostic identifier can provide an indication for the user to click on the diagnostic identifier in the diagnostic result page to indicate the viewing of the fault diagnosis result of the current input infrared image. Please refer to Figure 4, in an optional specific example, the diagnosis result page includes a display area for the target to be measured, a display area for the diagnosis temperature, and a display area for the fault result information. The diagnosis identifier is a stethoscope icon displayed on the diagnosis result page. The user can click on the stethoscope icon to trigger the computer program for executing the infrared image fault diagnosis method to perform diagnosis on the currently input infrared image, and display the fault diagnosis result on the current diagnosis result page. Among them, the step of displaying the fault diagnosis result on the diagnosis result page includes: displaying the recognized target to be measured in the display area of the target to be measured, and drawing a contour boundary line on the edge contour of the target to be measured based on the target recognition result of the target recognition algorithm; displaying the diagnosis temperature calculated from the target temperature data of the target to be measured in the display area of the diagnosis temperature; and displaying the fault type calculated based on the diagnosis rule matched with the target to be measured and its corresponding diagnosis temperature in the display area of the fault result information.

[0075] Optionally, the setting of the diagnosis identifier can also be such that when the user clicks it, it triggers the computer program for executing the infrared image fault diagnosis method to re - execute the diagnosis on the currently input infrared image, and display the updated fault diagnosis result obtained from the re - execution of the diagnosis on the current diagnosis result page. For example, in one example, after the user manually adjusts the contour boundary line of the target to be measured and then clicks the diagnosis identifier, it triggers the computer program for executing the infrared image fault diagnosis method to re - execute the diagnosis according to the adjusted contour boundary line of the target to be measured. The infrared image fault diagnosis method further includes: after adjusting the contour boundary line based on the adjustment operation information of the contour boundary line of the target to be measured, when receiving a touch command to click the diagnosis identifier, re - execute the diagnosis based on the adjusted contour boundary line of the target to be measured according to the touch command, and display the updated fault diagnosis result obtained from the re - execution of the diagnosis on the current diagnosis result page.

[0076] Optionally, the diagnosis result page may also include a target type option. When the infrared image includes multiple types of targets to be tested, the target types identified by the target recognition algorithm are formed into target type options that can be selected by the user. The display of the fault diagnosis result on the diagnosis result page includes: based on the user's selection of the target type option, obtaining the selection instruction for the target type option, and displaying the diagnosis result corresponding to the selected target type on the current diagnosis result page. It should be noted that the target type option can be a drop-down menu option, or a plurality of target type controls displayed in a specified area of ​​the diagnosis result page, and so on. Various forms that can display the currently identified target type and provide the user with a selection based on interactive operations are all acceptable. In this embodiment, the diagnosis result page supports user interactive operations to select the target type to be displayed on the diagnosis result page, which is conducive to meeting the needs of users in different application scenarios and facilitating users to select the target type they are currently concerned about to view the corresponding fault diagnosis results.

[0077] Optionally, the diagnostic result page may also include a configuration identifier for the diagnostic rules, such as a diagnostic rule viewing icon that can be set in the diagnostic result page. When a touch command to click on the diagnostic rule viewing icon is received, the display interface of the diagnostic rules of the target to be tested is entered, and at least one of the configuration operations of modifying, adding, and deleting the diagnostic rules of the target to be tested is supported. By setting the diagnostic rule viewing icon, the user can click on the diagnostic rule viewing icon to enter the display interface of the diagnostic rules of the target to be tested, and the user is supported to view, modify, add, delete, and other configuration operations on the diagnostic rules of the target to be tested.

[0078] Optionally, the diagnosis result page may also include a display control icon for target temperature data of the target to be measured, and when a touch command for clicking the display control icon for the target temperature data is received, the target temperature data obtained by extracting the temperature data within the target edge of the target to be measured is displayed on the diagnosis result page. By setting the display control icon for the target temperature data, the user can click the display control icon for the target temperature data, triggering the computer program of the infrared image fault diagnosis method to display the target temperature data obtained by extracting the temperature data within the target edge of the target to be measured on the diagnosis result page.

[0079] In the above embodiment, the setting of the diagnosis result page provides an interface for users to perform interactive operations, which can support users to complete various interactive controls and interactive configurations according to different application requirements, improve ease of use, and help meet more application scenario requirements and increase the application scenarios of infrared image fault diagnosis methods.

[0080] In some embodiments, step S109 further includes:

[0081] Based on a touch command for clicking on a deletion flag in the diagnostic result page, clear the display of the current fault diagnostic result.

[0082] In this embodiment, a deletion flag is set in the diagnostic result page, and the user can click on the deletion flag to indicate an instruction to clear the display of the fault diagnostic result for the currently input infrared image.

[0083] On the other hand, an embodiment of the present application further provides an infrared imaging device. Please refer to Figure 5 , which is an optional hardware structure schematic diagram of the infrared imaging device provided by the embodiment of the present application. The infrared imaging device includes a processor 111, a memory 112 connected to the processor 111, and an infrared image acquisition device 113. The memory 112 is used to store various types of data to support the operation of the infrared imaging device, and stores a computer program for implementing the infrared image fault diagnosis method provided by any embodiment of the present application. When the computer program is executed by the processor, the steps of the infrared image fault diagnosis method provided by any embodiment of the present application are implemented, and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here.

[0084] Optionally, the infrared imaging device includes a data acquisition module for acquiring infrared image data of a fault diagnosis scenario. The infrared image data includes infrared temperature data and infrared image data. A data storage module for storing infrared image data and caching data required for the execution process of the computer program corresponding to the infrared image fault diagnosis method. An intelligent recognition module for performing target recognition on the infrared image data to determine the target type and target edge of the target in the infrared image data, and correspondingly drawing a boundary contour line for the edge contour of the recognized target. An intelligent diagnosis module for finding a corresponding diagnosis rule according to the target type of the recognized target, calculating a diagnosis temperature by extracting the temperature data within the target edge range corresponding to the target edge recognized by the intelligent recognition module, and automatically performing fault diagnosis according to the diagnosis rule and the diagnosis temperature to obtain the fault diagnosis result of the corresponding target and display it.

[0085] Among them, the infrared imaging device includes a display module connected to the processor 111, and the display module is used to display various interactive pages during the execution of the infrared image fault diagnosis method, such as a diagnostic result page, etc.

[0086] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements each process of the above-mentioned embodiment of the infrared image fault diagnosis method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium includes, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0087] The embodiments of the present application also provide a computer program product, including a computer program. When the computer program is executed by a processor, it implements each process of the above-mentioned embodiment of the infrared image fault diagnosis method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0088] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or device including the element.

[0089] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0090] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present application, and all of them should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An infrared image fault diagnosis method, characterized in that, Including: Obtaining infrared image data; Performing target recognition on the infrared image data to determine the target type and target edge of the target in the infrared image data; Based on the target edge of the target, extracting temperature data within the target edge to obtain target temperature data, and calculating a diagnostic temperature based on the target temperature data; Determining a matching diagnostic rule according to the target type; Obtaining a fault diagnosis result of the target according to the diagnostic rule and the diagnostic temperature.

2. The infrared image fault diagnosis method according to claim 1, characterized in that, The performing target recognition on the infrared image data to determine the target type and target edge of the target in the infrared image data includes: Using a target recognition algorithm to perform target recognition on the infrared image data, identifying the target category and target contour of the target to be measured, and calculating a mask of the target to be measured according to the target contour; After processing the mask of the target to be measured by a non-maximum suppression algorithm and then performing dilation or erosion processing, obtaining a final mask of the target to be measured.

3. The infrared image fault diagnosis method according to claim 2, wherein The using a target recognition algorithm to perform target recognition on the infrared image data, identifying the target category and target contour of the target to be measured, and calculating a mask of the target to be measured according to the target contour includes: Using a pre-trained convolutional neural network as a feature extractor, and obtaining a target recognition model after training with a target detection algorithm; wherein, the target detection algorithm is selected from one of the following: RCNN, Fast RCNN, Faster RCNN, YOLOVx, SSD; Inputting the infrared image data into the target recognition model; Outputting the target category and target contour of the target to be measured through the target recognition model, and calculating a mask of the boundary of the target to be measured by using the target contour.

4. The infrared image fault diagnosis method according to claim 2, wherein The based on the target edge of the target, extracting temperature data within the target edge to obtain target temperature data, and calculating a diagnostic temperature based on the target temperature data includes: According to the final mask of the target to be measured, extracting the temperature data at the position of the final mask in the temperature dataset of the infrared image data to obtain the target temperature data of the target to be measured; Calculating a diagnostic temperature based on the target temperature data.

5. The infrared image fault diagnosis method according to claim 4, wherein, After obtaining the final mask of the target to be measured, further including: According to the final mask, calculating a set of boundary coordinates of the target to be measured through a binary image contour extraction function, and drawing a target bounding box of the target to be measured according to the set of boundary coordinates; wherein, the binary image contour extraction function is the findContours function; Wherein, the diagnostic temperature includes at least one of the following: the maximum temperature, the minimum temperature, the average temperature, and the standard temperature difference within the range of the final mask.

6. The infrared image fault diagnosis method according to any one of claims 1 to 5, characterized in that, The obtaining a fault diagnosis result of the target according to the diagnostic rule and the diagnostic temperature includes: Based on a touch command for clicking a diagnostic identifier on a diagnostic result page, obtaining a fault diagnosis result of the target according to the diagnostic rule and the diagnostic temperature, and displaying the fault diagnosis result on the diagnostic result page; and / or; Based on a touch command for clicking on a diagnostic identifier in the diagnostic result page, clear the current fault diagnostic result, re-determine the diagnostic rule that matches the current target type, obtain the fault diagnostic result of the target according to the diagnostic rule and the diagnostic temperature, and display the fault diagnostic result on the diagnostic result page.

7. The infrared image fault diagnosis method according to claim 6, characterized in that, The obtaining the fault diagnostic result of the target according to the diagnostic rule and the diagnostic temperature further includes: Based on a touch command for clicking on a deletion identifier in the diagnostic result page, clear the display of the current fault diagnostic result.

8. The infrared image fault diagnosis method according to claim 6, wherein The diagnostic result page includes a display area for the target to be measured, a display area for the diagnostic temperature, and a display area for fault result information. The diagnostic identifier includes a stethoscope icon displayed on the diagnostic result page; The displaying the fault diagnostic result on the diagnostic result page includes: Display the identified target to be measured in the display area of the target to be measured, and draw a contour boundary line on the edge contour of the target to be measured based on the target recognition result of the target recognition algorithm; Display the diagnostic temperature calculated for the target temperature data of the target to be measured in the display area of the diagnostic temperature; Display the fault type calculated based on the diagnostic rule that matches the target to be measured and its corresponding diagnostic temperature in the display area of the fault result information.

9. The infrared image fault diagnosis method according to claim 8, wherein, It further includes: After adjusting the contour boundary line based on the adjustment operation information of the contour boundary line of the target to be measured, when receiving a touch command for clicking on the diagnostic identifier, re-execute the diagnosis according to the touch command based on the adjusted contour boundary line of the target to be measured, and display the updated fault diagnostic result obtained from the re-executed diagnosis on the diagnostic result page.

10. The infrared image fault diagnosis method according to claim 6, characterized in that, The diagnostic result page further includes a target type option. If the infrared image includes multiple types of targets to be measured, form selectable target type options from the target types identified by the target recognition algorithm; The displaying the fault diagnostic result on the diagnostic result page includes: based on the obtained selection instruction for the target type option, display the diagnostic result corresponding to the selected target type on the current diagnostic result page; and / or The diagnostic result page further includes a viewing icon for the diagnostic rule. When receiving a touch command for clicking on the viewing icon for the diagnostic rule, enter the display interface of the diagnostic rule for the target to be measured, and support configuration operations such as modifying, adding, and deleting at least one of the diagnostic rules for the target to be measured; and / or The diagnostic result page further includes a display control icon for the target temperature data of the target to be measured. When receiving a touch command for clicking on the display control icon for the target temperature data, display the target temperature data extracted based on the temperature data within the target edge of the target to be measured on the diagnostic result page.

11. An infrared imaging device, including a memory, a processor, and an infrared image acquisition device; The infrared image acquisition device acquires infrared image data and sends it to the processor; A computer program is stored in the processor, and the processor is configured to execute the computer program to implement the infrared image fault diagnosis method according to any one of claims 1 to 10.

12. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, it implements the infrared image fault diagnosis method according to any one of claims 1 to 10.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the infrared image fault diagnosis method according to any one of claims 1 to 10.

Images