A temperature measurement method, device, medium and electronic equipment for electric power equipment
By constructing an infrared and visible light dual-channel overlapping mapping module based on a dual-light camera system and imaging principle, the problem of complex background interference in UAV infrared inspection is solved, enabling high-precision identification and measurement of power equipment temperature, and improving the flexibility and operational efficiency of the UAV temperature measurement system.
Patent Information
- Application Number
- CN202410796546.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-20
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-06-20
AI Technical Summary
In drone infrared inspection, complex background interference leads to insufficient accuracy in temperature identification of power equipment, making it difficult to measure temperature accurately.
A dual-light camera system is adopted, which combines visible light and infrared images. The target detection algorithm marks the equipment, and the visible light image is mapped onto the infrared image using a transformation mapping matrix. Infrared thermal data analysis is performed, and an infrared and visible light dual-channel overlapping mapping module is constructed based on imaging principles to realize temperature identification of power equipment.
It reduces the interference of complex backgrounds on thermal analysis of power equipment, improves the accuracy of temperature identification and the flexibility of UAV temperature measurement, simplifies the complexity of on-site operations, and improves the efficiency of fault diagnosis and preventive maintenance.
Smart Images

Figure CN118362212B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of temperature measurement of power systems, and more specifically, to a temperature measurement method, device, medium and electronic equipment for power equipment. Background Art
[0002] With the rapid growth of the national economy, power equipment, as a core element supporting various infrastructures and daily life, is of vital importance for its stable operation. However, due to the long-term operation of a large number of power equipment outdoors, affected by equipment aging, overload and poor contact, power equipment may experience overhead line short circuit, circuit break, poor contact of cable lead-in wires or metal fittings, aging and damage of insulators or transformer insulation during operation. In order to ensure the safe and efficient operation of power equipment, it is particularly important to detect and identify potential faults in a timely manner. As an important monitoring method, infrared temperature measurement technology for power equipment is based on the infrared radiation energy emitted by an object. Its radiation energy intensity is related to factors such as the temperature, material and color of the object. Infrared imaging technology uses infrared cameras and optical imaging objective lenses to receive the infrared radiation energy distribution graph of the target to be measured, and reflects it on the photosensitive element of the infrared camera to obtain an infrared thermal image. By measuring the surface temperature distribution of the equipment, the working status of the power equipment can be detected non-contact and quickly, and abnormal hot spots of the equipment can be found. It plays an important role in early equipment fault diagnosis, fire risk prevention, regular maintenance and overhaul, and provides a more comprehensive and accurate diagnostic method for power equipment.
[0003] Traditional infrared temperature measurement technology requires operation and maintenance personnel to hold a handheld infrared thermometer at the equipment to be tested, and judge the equipment operating conditions based on the digital display value combined with work experience. With the gradual promotion and application of drones in the field of power equipment inspection, more and more drones equipped with visible light infrared cameras are involved in the front line of operation and maintenance. Drone infrared inspection can measure the temperature of equipment without touching the power equipment. During inspections, drones often take top-down photos and infrared temperature measurements of power equipment. The surrounding environment background will interfere with the accuracy of the equipment temperature measurement and recognition, especially under the influence of high temperatures in summer. The ambient temperature is often high, and the power equipment and the background environment are integrated. The power equipment in the infrared image is difficult to identify, which has a serious impact on the inspection infrared image recognition and temperature measurement, resulting in the current infrared image intelligent recognition and temperature measurement algorithms are significantly insufficient in accuracy. Summary of the invention
[0004] In view of the deficiencies in the prior art, the present invention provides a temperature measurement method, device, medium and electronic equipment for electric power equipment.
[0005] According to one aspect of the present invention, there is provided a temperature measurement method for electric power equipment, comprising:
[0006] The visible light image and infrared image of the temperature measurement device are collected by a pre-calibrated dual-light camera on the drone, and the camera imaging parameters of the dual-light camera are recorded. The dual-light camera includes a visible light camera and an infrared camera, which are calibrated by a standard infrared black body.
[0007] The target detection algorithm is used to detect targets in visible light images and mark target devices, including transformers, tension clamps, parallel-groove clamps, pole-mounted disconnectors, insulators, and lightning arresters.
[0008] According to the predetermined conversion mapping matrix of the visible light camera and the infrared camera and the camera imaging parameters, the marked target device is mapped onto the infrared image to obtain the marked infrared image with the mark of the target device;
[0009] Extract and analyze the infrared thermal data of the target device from the marked infrared image to determine the temperature information of the target device;
[0010] The transformation mapping matrix is:
[0011]
[0012] in, u k , v k Represents the position of the object in the pixel coordinate system of the visible light image, u h , v h Represents the position of the object in the pixel coordinate system of the infrared image, T It is a mapping matrix for converting the position of an object in the pixel coordinate system of a visible light image to the position of an object in the pixel coordinate system of an infrared image.
[0013] Optionally, the calibration process of the bifocal camera is:
[0014] Control the calibration distance between the drone and the standard infrared black body to obtain the temperature measurement results at different calibration distances, where the calibration distance is set to 1m to 15m and calibrated at intervals of one meter;
[0015] According to the temperature measurement results at different calibration distances and the actual temperature data of the standard infrared black body, the compensation values at different calibration distances are determined;
[0016] According to the compensation values at different calibration distances, the calibrated distance compensation curve is determined.
[0017] Optionally, the camera imaging parameters include focal length, focal length multiple, gimbal rotation angle, and aperture, and the process of determining the conversion mapping matrix includes:
[0018] By controlling the infrared calibration chessboard as a three-dimensional customer-provided component to stably translate and rotate, and adjusting the camera imaging parameters at the same time, multiple sets of infrared chessboard images and visible light chessboard images are collected;
[0019] According to multiple sets of infrared chessboard images, visible light chessboard images and corresponding camera imaging parameters, the visible light coordinate mapping matrix and the infrared coordinate mapping matrix are solved respectively;
[0020] The conversion mapping matrix is solved according to the visible light coordinate mapping matrix and the infrared coordinate mapping matrix.
[0021] Optionally, solving a conversion mapping matrix according to the visible light coordinate mapping matrix and the infrared coordinate mapping matrix includes:
[0022] Determine the visible light coordinate mapping matrix between the visible light coordinate system and the world coordinate system:
[0023]
[0024] Determine the infrared coordinate mapping matrix between the infrared coordinate system and the world coordinate system:
[0025]
[0026] According to the visible light coordinate mapping matrix and the infrared coordinate mapping matrix, solve the conversion mapping matrix:
[0027]
[0028] in, ,get:
[0029]
[0030] In the formula, M k is the visible light coordinate mapping matrix between objects and pixels in the world coordinate system in visible light imaging, M h is the infrared coordinate mapping matrix between objects and pixels in the world coordinate system in infrared imaging, x w , y w , z w is the coordinate position of the object in the world coordinate system.
[0031] Optionally, extracting and analyzing infrared thermal data of the target device from the marked infrared image to determine temperature information of the target device includes:
[0032] The infrared thermal data of the target device is extracted and analyzed from the marked infrared image to determine the maximum temperature and average temperature of the target device.
[0033] Optionally, it also includes:
[0034] comparing the average temperature of the target device with the ambient temperature of the target device to determine a first temperature difference;
[0035] Compare the maximum temperature of the target device with the maximum temperature of the same type of device in the same scene as the target device to determine a second temperature difference;
[0036] When the first temperature difference satisfies the first preset condition and the second temperature difference satisfies the second preset condition, it is determined that the temperature of the target device is normal; otherwise, it is determined that the temperature of the target device is abnormal.
[0037] Optionally, the visible light sensor of the visible light camera has effective pixels of not less than 12 million pixels and supports digital zoom or optical zoom mode, and the infrared sensor of the infrared camera has a sensing wavelength range of 7.5~13.5μm, a scene adaptation range of -25℃ to 135℃, and a sensitivity higher than 50mk.
[0038] According to another aspect of the present invention, there is provided a temperature measuring device for electric power equipment, comprising:
[0039] The acquisition module is used to acquire the visible light image and infrared image of the temperature measurement device through the pre-calibrated dual-light camera on the drone, and record the camera imaging parameters of the dual-light camera, wherein the dual-light camera includes a visible light camera and an infrared camera, which are calibrated by a standard infrared black body;
[0040] The detection module is used to detect targets in visible light images using a target detection algorithm and mark target devices, where the target devices include: transformers, tension clamps, parallel-groove clamps, pole-mounted disconnectors, insulators, and lightning arresters;
[0041] A mapping module, used to map the marked target device onto the infrared image according to a predetermined conversion mapping matrix of a visible light camera and an infrared camera and camera imaging parameters, and obtain a marked infrared image with the mark of the target device;
[0042] The analysis module is used to extract and analyze the infrared thermal data of the target device from the marked infrared image to determine the temperature information of the target device; wherein,
[0043] The transformation mapping matrix is:
[0044]
[0045] in, u k , v k Represents the position of the object in the pixel coordinate system of the visible light image, u h, v h Represents the position of the object in the pixel coordinate system of the infrared image, T It is a mapping matrix for converting the position of an object in the pixel coordinate system of a visible light image to the position of an object in the pixel coordinate system of an infrared image.
[0046] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute the method described in any one of the above aspects of the present invention.
[0047] According to another aspect of the present invention, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of the above aspects of the present invention.
[0048] Therefore, the present invention proposes a method for temperature measurement based on the imaging principle of infrared and visible light dual-channel overlap mapping identification of power equipment drones. Through the joint judgment of infrared and visible light multi-spectral, it reduces the interference of complex background on the thermal analysis effect of power equipment, effectively reduces the impact of complex background, reduces the standardization requirements of drone infrared photography, and simplifies the complexity of on-site operations. Using drones as the carrying platform makes the temperature measurement system more flexible and adaptable. Combined with intelligent target detection and thermal analysis, it improves the efficiency of operation and data analysis, and provides an effective means for fault diagnosis and preventive maintenance. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings:
[0050] Figure 1 is a flow chart of a temperature measurement method for electric power equipment provided by an exemplary embodiment of the present invention;
[0051] Figure 2 is a schematic diagram of an imaging principle provided by an exemplary embodiment of the present invention;
[0052] Figure 3 It is a schematic diagram of the principle of infrared and visible light dual-channel coincidence mapping provided by an exemplary embodiment of the present invention;
[0053] Figure 4 It is a schematic diagram of mapping a visible light image power equipment marking frame and an infrared image provided by an exemplary embodiment of the present invention;
[0054] Figure 5 It is a schematic diagram of the hardware system structure of a temperature measurement method for electric power equipment provided by an exemplary embodiment of the present invention;
[0055] Figure 6 is a software system schematic diagram of a temperature measurement method for electric power equipment provided by an exemplary embodiment of the present invention;
[0056] Figure 7 It is a technical route schematic diagram of a temperature measurement method for electric power equipment provided by an exemplary embodiment of the present invention;
[0057] Figure 8 It is a blackbody calibration diagram of different distances of a drone infrared module provided by an exemplary embodiment of the present invention;
[0058] Fig. 9 is a schematic diagram of visible light image target detection based on YOLO v5 provided by an exemplary embodiment of the present invention;
[0059] Fig.10 is a schematic diagram of an infrared calibration chessboard provided by an exemplary embodiment of the present invention;
[0060] Fig.11 This is an infrared thermal imaging temperature measurement analysis diagram of electric power equipment provided by an exemplary embodiment of the present invention;
[0061] Fig.12 It is a schematic diagram of the acceptance operation process provided by an exemplary embodiment of the present invention;
[0062] Fig.13 It is a schematic diagram of a visible light infrared dual-channel image acquisition operation of a drone provided by an exemplary embodiment of the present invention;
[0063] Fig.14 is a schematic structural diagram of a temperature measuring device for electric power equipment provided by an exemplary embodiment of the present invention;
[0064] Fig.15 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION
[0065] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described here.
[0066] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
[0067] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.
[0068] It should also be understood that, in the embodiments of the present invention, “plurality” may refer to two or more than two, and “at least one” may refer to one, two or more than two.
[0069] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.
[0070] In addition, the term "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.
[0071] It should also be understood that the description of the various embodiments of the present invention focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.
[0072] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.
[0073] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.
[0074] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.
[0075] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.
[0076] Embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.
[0077] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment, where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.
[0078] Exemplary Methods
[0079] Figure 1 FIG. 1 is a flow chart of a temperature measurement method for electric power equipment provided by an exemplary embodiment of the present invention. This embodiment can be applied to electronic equipment, such as Figure 1 As shown, the temperature measurement method 100 of the electric power equipment includes the following steps:
[0080] Step 101, collecting visible light images and infrared images of the temperature measurement device through a pre-calibrated dual-light camera on a drone, and recording the camera imaging parameters of the dual-light camera, wherein the dual-light camera includes a visible light camera and an infrared camera, which are calibrated by a standard infrared black body;
[0081] Step 102, using a target detection algorithm to perform target detection on the visible light image, and marking target equipment, wherein the target equipment includes: transformers, tension clamps, parallel trench clamps, pole disconnectors, insulators, and lightning arresters;
[0082] Step 103, mapping the marked target device onto the infrared image according to the predetermined conversion mapping matrix of the visible light camera and the infrared camera and the camera imaging parameters, and obtaining a marked infrared image with the mark of the target device;
[0083] Step 104, extract and analyze the infrared thermal data of the target device from the marked infrared image to determine the temperature information of the target device; wherein,
[0084] The transformation mapping matrix is:
[0085]
[0086] in, u k , v k Represents the position of the object in the pixel coordinate system of the visible light image, u h , v h Represents the position of the object in the pixel coordinate system of the infrared image,T It is a mapping matrix for converting the position of an object in the pixel coordinate system of a visible light image to the position of an object in the pixel coordinate system of an infrared image.
[0087] Specifically, visible light and infrared radiation are both types of electromagnetic radiation, where the wavelength range of visible light is 400nm to 760nm, and the wavelength range of infrared radiation is between 700nm and 1000nm (1mm). Visible light imaging is based on the reflectivity of an object to light (which is essentially an electromagnetic wave) and is formed by capturing sunlight or other light sources reflected by the object. Visible light imaging has clear texture features and high spatial resolution, but does not have pixel temperature information, making it difficult to analyze the heating conditions of an object. Infrared cameras capture infrared radiation emitted when an object exchanges heat with its surroundings and convert it into infrared images or videos. However, in the inspection of power equipment, infrared imaging is easily interfered by the background, and due to its small wavelength range, the information carried by low-resolution images is limited.
[0088] Whether it is visible light imaging or infrared imaging, the principles are similar to a certain extent. The electromagnetic waves generated or reflected by objects in the real world are converted into pixel coordinate points in the plane through the camera's optical (visible light, infrared) components and sensor components. Figure 2 As shown in the figure, the camera imaging model is constructed, which includes the world coordinate system (O w , X w , Y w , Z w )、Camera coordinate system(O c , X c , Y c , Z c ), image physical coordinate system (O, X, Y), pixel coordinate system (U, V), a total of 4 sets of coordinate systems. Among them, the coordinates in the world coordinate system are usually used to represent the absolute position of an object in the real world. Its origin O w and the coordinate axis (X w , Y w , Z w ) can be defined according to the specific application scenario, and usually a point that is convenient for describing the position of the object and the camera is selected as the origin; the camera coordinate system describes the position and direction of the camera in the real world, and its origin O c Usually located at the optical center of the camera, Z cThe axis coincides with the optical axis of the camera; the image physical coordinate system describes the projection position of the object on the image plane, and its origin O is usually located at the center (or principal point) of the image plane, and the X axis and Y axis are parallel to the horizontal and vertical directions of the image respectively; the pixel coordinate system converts the points in the image physical coordinate system into points in the pixel coordinate system, and its origin U0 and V0 are usually located in the upper left corner of the image, and the U axis and V axis are along the horizontal and vertical directions of the image respectively. In the joint comparison of infrared and visible light dual-channel imaging, (X d , Y d ) and (X p , Y p ) are the actual coordinates on the image and the physical coordinates of the image point after distortion correction. w To the image point P d The transformation of is obtained by three transformations of the above four coordinate systems, which can be expressed as Equation 1 according to the imaging model:
[0089] (1)
[0090] In the formula, d x , dy are the distances between pixels in the X and Y directions on the photosensitive device; u and v are the positions of objects in the pixel coordinate system. u 0. v 0 are the pixel coordinates of the intersection of the optical axis and the imaging plane; x w 、y w , z w is the coordinate position of the object in the world coordinate system; f x , f y The lenses are X and Y The effective focal length in the direction; R is the 3×3 rotation transformation matrix from the world coordinate system to the camera coordinate system, t The translation vector from the world coordinate system to the camera coordinate system.
[0091] Formula 1 can be simplified as: ,in , which is the mapping matrix between object and pixel coordinates in the world coordinate system.
[0092] In the visible light coordinate system, its imaging transformation matrix can be expressed as , and in the infrared coordinate system, its imaging transformation matrix can be expressed as .
[0093] Therefore, for the same real object, visible light infrared dual-channel imaging can establish the correspondence between the visible light and infrared image pixel coordinate systems. , which can be further simplified as , .
[0094] in, u k , v k Represents the position of the object in the pixel coordinate system of the visible light image, u h , v h Represents the position of the object in the pixel coordinate system of the infrared image, M k is the mapping matrix between objects and pixel coordinates in the world coordinate system in visible light imaging, M h is the mapping matrix between objects and pixel coordinates in the world coordinate system in infrared imaging, T The mapping matrix for the position conversion between the object in the pixel coordinate system of the visible light image and the object in the pixel coordinate system of the infrared image is shown in the schematic diagram of the principle of the double-channel overlap mapping of infrared and visible light. Figure 3 shown.
[0095] In one embodiment of the present application, the present invention utilizes the visible light and infrared spectrum imaging conversion principle, integrates parameters such as DFOV (display field of view), equivalent focal length, aperture, focus distance, zoom factor, etc. (Table 1 shows the parameters of the visible light camera and thermal camera of the Mavic 3T drone), and constructs a drone infrared and visible light dual-channel imaging overlap mapping module.
[0096] Table 1 Parameters of UAV visible light camera and thermal imaging camera
[0097] Visible light camera Thermal imaging camera DFOV (Display Field of View) 84° 61° Equivalent focal length 24mm 40mm aperture f / 2.8 f / 1.0 Focus distance 1 meter to infinity 5 meters to infinity Optical zoom ratio 7 times Fixed focus Digital zoom ratio 56 times 28 times
[0098] Through the visible light target detection algorithm of power equipment, such as YOLO V5, Faster RCNN, Cascade RCNN and other algorithms, the power equipment is identified in the visible light image, and the identification frame is mapped by overlapping the infrared and visible light dual-channel imaging, and the visible light image coordinate position is mapped to the infrared image coordinate position to complete the temperature measurement and identification of the power equipment, such as Figure 4 shown.
[0099] In one embodiment of the present invention, the power equipment temperature measurement system for the overlap mapping analysis of the infrared and visible light dual-channel imaging of drones is composed of a hardware system and a software system. The hardware system is mainly responsible for the data acquisition function and is composed of an integrated camera with high-definition visible light and high-precision infrared image acquisition. Its structure is as follows: Figure 5The visible light sensor has effective pixels of no less than 12 million pixels, supports digital zoom or optical zoom, the infrared sensor has a sensing wavelength range of at least 7.5~13.5μm, a scene adaptation range of at least -25℃ to 135℃, and a sensitivity (NETD) better than 50mk.
[0100] The power equipment temperature measurement software system based on the overlap mapping analysis of the infrared and visible light dual-channel imaging of drones (hereinafter referred to as the temperature measurement software system) is mainly responsible for the real-time data processing function, which can be viewed by the drone handheld terminal and can also be displayed and exported by the computer terminal. Figure 6 As shown, during the image acquisition process, the shooting parameters of visible light and infrared images (focal length, zoom ratio, pan / tilt rotation angle, aperture) and other parameter information are recorded in real time, and the system's built-in algorithm is used to complete the infrared and visible light dual-channel imaging coincidence mapping analysis, i.e., power equipment temperature measurement, and the relevant results are output to form an inspection business report.
[0101] In one embodiment of the present invention, the present invention adopts a combination of software and hardware to carry out power equipment identification and temperature measurement. First, the infrared imaging module of the integrated dual-light camera is calibrated and proofread by a standard infrared blackbody, and then the imaging characteristics of visible light images and infrared images under different focal lengths, zoom factors, pan-tilt rotation angles, and aperture parameter combinations are analyzed by an infrared checkerboard calibration plate, and an infrared and visible light dual-channel imaging coincidence mapping module constrained by parameters such as focal length, zoom factor, pan-tilt rotation angle, and aperture is constructed; on this basis, the existing power equipment target detection algorithm based on visible light vision is integrated to frame and mark the power equipment in the visible light image, and it is mapped to the infrared image through the infrared and visible light dual-channel imaging coincidence mapping module to complete the thermal analysis of the power equipment.
[0102] The system as a whole is composed of an infrared and visible light dual-channel imaging coincidence mapping module, a visible light image target detection module, and an infrared thermal imaging temperature measurement and analysis module. The technical route is as follows: Figure 7 The implementation process is as follows:
[0103] (1) Calibration of infrared imaging module of integrated dual-light camera:
[0104] The infrared imaging module of the integrated dual-light camera is calibrated and corrected by a standard infrared black body. The temperature setting range of the infrared black body is greater than -15℃ to 500℃. During the calibration process, the distance between the drone and the standard black body is controlled. Referring to the inspection safety distance and imaging distance range of the drone, the calibration distance is set to 1m to 15m respectively. The calibration is performed at intervals of one meter, and the optimal imaging distance curve is set so that the temperature measurement error at each control distance is not less than ±2℃ or ±2% (whichever is larger in absolute value). Figure 8 This is the blackbody calibration experiment diagram of the infrared imaging module of the integrated dual-light camera.
[0105] (2) Visible light image object detection module:
[0106] At present, the target detection algorithm for power equipment is relatively mature. The present invention adopts the target detection algorithm for power equipment based on the YOLO v5 algorithm. Through multi-level feature extraction and fusion, it can fully capture the subtle features of power equipment in visible light images. It has a fast detection speed and can process a large amount of image data in real time to meet the real-time requirements of power inspection scenarios. At the same time, the algorithm is easy to carry out lightweight compression and can be deployed on the remote control end of the drone or the front-end of the drone, so as to facilitate target recognition while executing the inspection flight mission. Its recognition effect is as follows: Fig. 9 In addition, when identifying targets on the back end such as a server, the present invention can also deploy algorithms including but not limited to Faster RCNN, Cascade RCNN, etc. to carry out visible light target detection, which has good algorithm scalability.
[0107] The visible light power equipment target detection algorithm is encapsulated. By inputting a visible light image, it can mark the identification boxes of power equipment including transformers, tension clamps, parallel trench clamps, pole-mounted disconnectors, insulators, lightning arresters, etc.
[0108] (3) Infrared and visible light dual-channel imaging coincidence mapping module:
[0109] The drone moves or temporarily hovers to shoot the target power equipment in daily inspection applications. To adapt to this scenario, the infrared calibration chessboard (such as Fig.10 As shown in the figure, the camera performs stable translation and rotation in three-dimensional space, and adjusts the aperture, focal length, zoom factor and other parameters respectively, takes multiple sets of images, and solves the internal and external parameters of the visible light imaging module and the infrared imaging module respectively according to the quantitative acquisition of moving image information and camera setting parameters, namely M k and M h Matrix, inversion to solve the visible light and infrared image pixel conversion mapping matrix T .
[0110] According to the transformation mapping matrix T The module is encapsulated to form an overlapping mapping module, which inputs visible light and infrared images and adapts to the mapping of the common parts of visible light images and infrared images at various zoom magnifications. The position of the box mark on the visible light image can be accurately mapped to the infrared image. Because it is converted and encapsulated according to the imaging principle, it is different from the traditional mapping (affine) method based on reinforcement learning or feature fitting. This module has the characteristics of small size and can be deployed on both the front and back ends.
[0111] (4) Infrared thermal imaging temperature measurement and analysis module:
[0112] According to the power equipment marking frame of the infrared image mapped by the infrared and visible light dual-channel imaging coincidence mapping module, the maximum temperature and average temperature in the marking frame are calculated, such as Fig.11 As shown, according to the power industry standard "Infrared Diagnosis Specifications for Energized Equipment", the normal operating temperature range of the equipment in the current environment is set, and the equipment is judged whether it is hot based on this temperature range, and there are hidden defects.
[0113] In one embodiment of the present invention, according to each system module proposed in the present invention, a temperature measurement method for power equipment based on infrared and visible light dual-channel imaging coincidence mapping analysis is proposed to meet the algorithm characteristics and field application requirements. The specific acceptance operation flow chart is as follows: Fig.12 shown.
[0114] Before the operation begins, the drone with visible light and infrared dual-channel imaging capabilities needs to be self-checked, and the overlap mapping analysis and temperature measurement system needs to be debugged to ensure that the drone and the dual-channel imaging overlap mapping analysis and temperature measurement system can work normally. After debugging, operate the drone to fly near the tower, station area or equipment facilities to be tested, adjust the parameters of the visible light camera and infrared camera to ensure that the equipment to be tested is unobstructed and the image is clear. After adjustment, complete the synchronous acquisition of visible light images and infrared images, that is, the spatial positions such as the drone position and the gimbal angle are consistent during imaging, and accurately record the imaging parameters such as focal length, zoom factor, gimbal rotation angle, aperture, etc. during shooting. The operation diagram is shown as follows Fig.13 shown.
[0115] After the image information is collected, you can select the visible light image target detection module and the infrared and visible light dual-channel imaging coincidence mapping module installed on the front end, or you can choose to process the visible light image, infrared image, imaging parameters during shooting and other data through the back-end server. First, the visible light image target detection module performs target detection on the power equipment in the visible light image, including but not limited to transformers, tension clamps, parallel groove clamps, pole disconnectors, insulators, lightning arresters and other equipment, and marks the location of the power equipment. Then, the infrared and visible light dual-channel imaging coincidence mapping module maps the power equipment marked by the visible light image target detection module to the infrared image, and the infrared thermal imaging temperature measurement analysis module extracts and analyzes the infrared thermal data in the marked box on the mapped infrared image, and calculates the average temperature and the highest temperature in the box.
[0116] After completing the temperature analysis of all marked boxes on the infrared image, the normal operating temperature range of the equipment in the current environment is set according to the field operation experience, and the temperature range is used to determine whether the equipment is hot and has potential defects. The line (equipment) information of the defective infrared image is output to form an inspection defect thermal analysis report.
[0117] According to the on-site ambient temperature, the maximum temperature difference between the average temperature of the calculated equipment and the on-site ambient temperature is within 5 degrees, which is considered normal. At the same time, the maximum temperature of other equipment on site is compared. If it is not higher than 30% of the maximum temperature of the same type of equipment, the temperature is considered normal.
[0118] In one embodiment of the present invention, taking the inspection of overhead line equipment in the distribution network as an example, on-site testing and application of overhead distribution lines are carried out according to the present invention, which has a good recognition effect and can accurately identify and measure the temperature of equipment such as transformers, tension clamps, parallel groove clamps, pole-mounted disconnectors, insulators, and lightning arresters.
[0119] In summary: (1) The present invention proposes a method for identifying and measuring temperature by using infrared and visible light dual-channel overlap mapping for power equipment drones, which fully utilizes the advantages of rich information in visible light images and the characteristics of infrared images that can be used to conduct thermal analysis of equipment, reduces the interference of complex backgrounds on the thermal analysis of power equipment, and has good environmental adaptability. (2) Based on the imaging principle, the present invention integrates parameters such as aperture, DFOV (display field of view), focal length, and zoom factor to construct an infrared and visible light dual-channel imaging overlap mapping module, and realizes the conversion mapping of all pixel points in the overlap area of visible light images and infrared images. (3) The intelligent temperature measurement and recognition method of public area full map mapping by UAV dual-channel joint image comparison proposed in the present invention includes but is not limited to YOLOv5, Faster RCNN, Cascade RCNN and other target recognition algorithms for the target positioning process of power equipment in visible light, realizes infrared temperature measurement and recognition of power equipment including but not limited to transformers, tension clamps, parallel groove clamps, pole-mounted disconnectors, insulators, lightning arresters, etc., realizes the recognition of multiple types of electrical equipment, has good scalability of temperature measurement and recognition types, can be expanded to carry out visible light defect recognition, etc., and realizes integrated diagnosis of dual-light defects.
[0120] Therefore, the present invention proposes a system and method for temperature measurement based on the imaging principle of an infrared and visible light dual-channel overlap mapping recognition of an electric power equipment drone. By mapping the entire area of overlap between the visible light image and the infrared image, a visible light image and infrared image mapping recognition module based on the imaging principle is constructed, which improves the accuracy of the infrared thermal analysis algorithm while reducing the complexity of the algorithm, providing an accurate diagnostic means for thermal analysis of electric power equipment. The present invention proposes a method for temperature measurement based on the imaging principle of an infrared and visible light dual-channel overlap mapping recognition of an electric power equipment drone. By combining infrared and visible light multi-spectral analysis, the interference of complex background on the thermal analysis effect of electric power equipment is reduced, the impact of complex background is effectively reduced, the standardization requirements for infrared photography of drones are reduced, and the complexity of on-site operations is simplified. Using drones as the carrying platform makes the temperature measurement system more flexible and adaptable. Combined with intelligent target detection and thermal analysis, the efficiency of operations and data analysis is improved, providing an effective means for fault diagnosis and preventive maintenance.
[0121] Exemplary Devices
[0122] Fig.14 FIG. 1 is a schematic diagram of a temperature measuring device for electric power equipment provided by an exemplary embodiment of the present invention. Fig.14 As shown, the apparatus 1400 includes:
[0123] The acquisition module 1410 is used to acquire the visible light image and the infrared image of the temperature measurement device through the pre-calibrated dual-light camera on the drone, and record the camera imaging parameters of the dual-light camera, wherein the dual-light camera includes a visible light camera and an infrared camera, which are calibrated by a standard infrared black body;
[0124] The detection module 1420 is used to detect targets on the visible light image using a target detection algorithm and mark target devices, wherein the target devices include: transformers, tension clamps, parallel trench clamps, pole disconnectors, insulators, and lightning arresters;
[0125] A mapping module 1430 is used to map the marked target device onto the infrared image according to a predetermined conversion mapping matrix of the visible light camera and the infrared camera and camera imaging parameters, and obtain a marked infrared image with the mark of the target device;
[0126] The analysis module 1440 is used to extract and analyze the infrared thermal data of the target device from the marked infrared image to determine the temperature information of the target device; wherein,
[0127] The transformation mapping matrix is:
[0128]
[0129] in, u k , v k Represents the position of the object in the pixel coordinate system of the visible light image, u h , v h Represents the position of the object in the pixel coordinate system of the infrared image, T It is a mapping matrix for converting the position of an object in the pixel coordinate system of a visible light image to the position of an object in the pixel coordinate system of an infrared image.
[0130] Optionally, the calibration process of the bifocal camera is:
[0131] Control the calibration distance between the drone and the standard infrared black body to obtain the temperature measurement results at different calibration distances, where the calibration distance is set to 1m to 24m and calibrated at intervals of one meter;
[0132] According to the temperature measurement results at different calibration distances and the actual temperature data of the standard infrared black body, the compensation values at different calibration distances are determined;
[0133] According to the compensation values at different calibration distances, the calibrated distance compensation curve is determined.
[0134] Optionally, the camera imaging parameters include focal length, focal length multiple, gimbal rotation angle, and aperture, and the process of determining the conversion mapping matrix includes:
[0135] By controlling the infrared calibration chessboard as a three-dimensional customer-provided component to stably translate and rotate, and adjusting the camera imaging parameters at the same time, multiple sets of infrared chessboard images and visible light chessboard images are collected;
[0136] According to multiple sets of infrared chessboard images, visible light chessboard images and corresponding camera imaging parameters, the visible light coordinate mapping matrix and the infrared coordinate mapping matrix are solved respectively;
[0137] The conversion mapping matrix is solved according to the visible light coordinate mapping matrix and the infrared coordinate mapping matrix.
[0138] Optionally, solving a conversion mapping matrix according to the visible light coordinate mapping matrix and the infrared coordinate mapping matrix includes:
[0139] Determine the visible light coordinate mapping matrix between the visible light coordinate system and the world coordinate system:
[0140]
[0141] Determine the infrared coordinate mapping matrix between the infrared coordinate system and the world coordinate system:
[0142]
[0143] According to the visible light coordinate mapping matrix and the infrared coordinate mapping matrix, solve the conversion mapping matrix:
[0144]
[0145] in, ,get:
[0146]
[0147] In the formula, M k is the visible light coordinate mapping matrix between objects and pixels in the world coordinate system in visible light imaging, M h is the infrared coordinate mapping matrix between objects and pixels in the world coordinate system in infrared imaging, x w , y w, z w is the coordinate position of the object in the world coordinate system.
[0148] Optionally, extracting and analyzing infrared thermal data of the target device from the marked infrared image to determine temperature information of the target device includes:
[0149] The infrared thermal data of the target device is extracted and analyzed from the marked infrared image to determine the maximum temperature and average temperature of the target device.
[0150] Optionally, the apparatus 1400 further includes:
[0151] comparing the average temperature of the target device with the ambient temperature of the target device to determine a first temperature difference;
[0152] Compare the maximum temperature of the target device with the maximum temperature of the same type of device in the same scene as the target device to determine a second temperature difference;
[0153] When the first temperature difference satisfies the first preset condition and the second temperature difference satisfies the second preset condition, it is determined that the temperature of the target device is normal; otherwise, it is determined that the temperature of the target device is abnormal.
[0154] Optionally, the visible light sensor of the visible light camera has effective pixels of not less than 12 million pixels and supports digital zoom or optical zoom mode, and the infrared sensor of the infrared camera has a sensing wavelength range of 7.5~13.5μm, a scene adaptation range of -25℃ to 135℃, and a sensitivity higher than 50mk.
[0155] Exemplary Electronic Devices
[0156] Fig.15 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. Fig.15 As shown, the electronic device 150 includes one or more processors 151 and a memory 152 .
[0157] The processor 151 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.
[0158] The memory 152 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 151 may run the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above and / or other desired functions. In one example, the electronic device may also include: an input device 153 and an output device 154, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown).
[0159] In addition, the input device 153 may also include, for example, a keyboard, a mouse, and the like.
[0160] The output device 154 can output various information to the outside, and can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto.
[0161] Of course, to simplify, Fig.15 Only some of the components related to the present invention in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device may further include any other appropriate components according to specific application conditions.
[0162] Exemplary computer program products and computer-readable storage media
[0163] In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above-mentioned "Exemplary Method" section of this specification.
[0164] The computer program product may be written in any combination of one or more programming languages to write program code for performing the operations of the embodiments of the present invention, including object-oriented programming languages such as Java, C++, etc., and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.
[0165] In addition, an embodiment of the present invention may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above “Exemplary Method” section of this specification.
[0166] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, system or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.
[0167] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details disclosed above are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.
[0168] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0169] The block diagrams of the devices, systems, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, systems, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The word "such as" used here refers to the phrase "such as but not limited to", and can be used interchangeably with it.
[0170] The method and system of the present invention may be implemented in many ways. For example, the method and system of the present invention may be implemented by software, hardware, firmware or any combination of software, hardware, firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present invention are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present invention may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.
[0171] It should also be noted that in the system, device and method of the present invention, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present invention. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined here can be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown here, but in accordance with the widest range consistent with the principles and novel features disclosed here.
[0172] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.
Claims
1. A temperature measurement method for electric power equipment, It is characterized in that include: The visible light image and infrared image of the temperature measurement device are collected by a pre-calibrated dual-light camera on the drone, and the camera imaging parameters of the dual-light camera are recorded, wherein the dual-light camera includes a visible light camera and an infrared camera, which are calibrated by a standard infrared black body, the visible light sensor of the visible light camera has an effective pixel of not less than 12 million pixels, supports digital zoom or optical zoom mode, and the infrared sensor of the infrared camera has a sensing wavelength range of 7.5 to 13.5 μm, a scene adaptation range of -25°C to 135°C, and a sensitivity higher than 50mk; Using a target detection algorithm to perform target detection on the visible light image, and marking target equipment, wherein the target equipment includes: a transformer, a tension clamp, a parallel groove clamp, a pole disconnector, an insulator and a lightning arrester; According to the predetermined conversion mapping matrix of the visible light camera and the infrared camera and the camera imaging parameters, the marked target device is mapped onto the infrared image to obtain a marked infrared image with the mark of the target device; Extract and analyze the infrared thermal data of the target device from the marked infrared image to determine the temperature information of the target device; wherein, The conversion mapping matrix is: in, u k , v k Represents the position of the object in the pixel coordinate system of the visible light image, u h , v h Represents the position of the object in the pixel coordinate system of the infrared image, T A mapping matrix for converting the position of an object in the pixel coordinate system of a visible light image to the position of an object in the pixel coordinate system of an infrared image; The calibration process of the bi-optical camera is as follows: Controlling the calibration distance between the UAV and the standard infrared black body to obtain temperature measurement results at different calibration distances, wherein the calibration distance is set to be 1m to 15m and calibrated at intervals of one meter; Determine compensation values at different calibration distances according to temperature measurement results at different calibration distances and actual temperature data of the standard infrared black body; According to the compensation values at different calibration distances, a calibrated distance compensation curve is determined, and the camera imaging parameters include focal length, focal length multiple, pan / tilt rotation angle and aperture; the camera parameters of the dual-light camera carried by the UAV are: the display field of view of the visible light camera is 84°, the equivalent focal length is 24mm, the aperture is f / 2.8, the focus distance is 1 meter to infinity, the optical zoom multiple is 7 times, and the digital zoom multiple is 56 times; the display field of the infrared camera is 61°, the equivalent focal length is 40mm, the aperture is f / 1.0, the focus distance is 5 meters to infinity, the optical zoom multiple is fixed focus, and the digital zoom multiple is 28 times; The process of determining the conversion mapping matrix includes: By controlling the infrared calibration chessboard as a three-dimensional customer-provided component to stably translate and rotate, and adjusting the camera imaging parameters at the same time, multiple sets of infrared chessboard images and visible light chessboard images are collected; Solving a visible light coordinate mapping matrix and an infrared coordinate mapping matrix respectively according to the plurality of groups of infrared chessboard images, the visible light chessboard images and corresponding camera imaging parameters; Solving the conversion mapping matrix according to the visible light coordinate mapping matrix and the infrared coordinate mapping matrix; Extracting and analyzing the infrared thermal data of the target device from the marked infrared image to determine the temperature information of the target device includes: Extracting and analyzing the infrared thermal data of the target device from the marked infrared image to determine the maximum temperature and average temperature of the target device; The temperature measurement method also includes: Comparing the average temperature of the target device with the ambient temperature of the target device to determine a first temperature difference; Comparing the maximum temperature of the target device with the maximum temperature of other devices of the same type in the same scene as the target device to determine a second temperature difference; When the first temperature difference satisfies a first preset condition and the second temperature difference satisfies a second preset condition, the temperature of the target device is determined to be normal; otherwise, the temperature of the target device is determined to be abnormal. The first preset condition is that the first temperature difference is less than 5 degrees, and the second preset condition is that the second temperature difference is not higher than 30% of the highest temperature of other devices of the same type in the same scene.
2. The temperature measurement method according to claim 1, It is characterized in that Solving the conversion mapping matrix according to the visible light coordinate mapping matrix and the infrared coordinate mapping matrix includes: Determine the visible light coordinate mapping matrix between the visible light coordinate system and the world coordinate system: Determine the infrared coordinate mapping matrix between the infrared coordinate system and the world coordinate system: According to the visible light coordinate mapping matrix and the infrared coordinate mapping matrix, the conversion mapping matrix is solved: in, ,get: In the formula, M k is the visible light coordinate mapping matrix between objects and pixels in the world coordinate system in visible light imaging, M h is the infrared coordinate mapping matrix between objects and pixels in the world coordinate system in infrared imaging, x w , y w , z w is the coordinate position of the object in the world coordinate system.
3. A temperature measuring device for electric power equipment, It is characterized in that include: The acquisition module is used to acquire visible light images and infrared images of the temperature-measured equipment through a pre-calibrated dual-light camera on the drone, and record the camera imaging parameters of the dual-light camera, wherein the dual-light camera includes a visible light camera and an infrared camera, which are calibrated by a standard infrared black body. The visible light sensor of the visible light camera has an effective pixel of not less than 12 million pixels and supports digital zoom or optical zoom mode. The infrared sensor of the infrared camera has a sensing wavelength range of 7.5 to 13.5 μm, a scene adaptation range of -25°C to 135°C, and a sensitivity higher than 50mk. A detection module, used to perform target detection on the visible light image using a target detection algorithm and mark target equipment, wherein the target equipment includes: a transformer, a tension clamp, a parallel groove clamp, a pole disconnector, an insulator and a lightning arrester; A mapping module, used to map the marked target device onto the infrared image according to a predetermined conversion mapping matrix of the visible light camera and the infrared camera and the camera imaging parameters, and obtain a marked infrared image with the mark of the target device; An analysis module is used to extract and analyze the infrared thermal data of the target device from the marked infrared image to determine the temperature information of the target device; wherein, The conversion mapping matrix is: in, u k , v k Represents the position of the object in the pixel coordinate system of the visible light image, u h , v h Represents the position of the object in the pixel coordinate system of the infrared image, T A mapping matrix for converting the position of an object in the pixel coordinate system of a visible light image to the position of an object in the pixel coordinate system of an infrared image; The calibration process of the bi-optical camera is as follows: Controlling the calibration distance between the UAV and the standard infrared black body to obtain temperature measurement results at different calibration distances, wherein the calibration distance is set to be 1m to 15m and calibrated at intervals of one meter; Determine compensation values at different calibration distances according to temperature measurement results at different calibration distances and actual temperature data of the standard infrared black body; Determining a calibrated distance compensation curve according to the compensation values at different calibration distances; The camera imaging parameters include focal length, focal length multiple, pan / tilt rotation angle and aperture, and the determination process of the conversion mapping matrix includes: By controlling the infrared calibration chessboard as a three-dimensional customer-provided component to stably translate and rotate, and adjusting the camera imaging parameters at the same time, multiple sets of infrared chessboard images and visible light chessboard images are collected; Solving a visible light coordinate mapping matrix and an infrared coordinate mapping matrix respectively according to the plurality of groups of infrared chessboard images, the visible light chessboard images and corresponding camera imaging parameters; Solving the conversion mapping matrix according to the visible light coordinate mapping matrix and the infrared coordinate mapping matrix; Extracting and analyzing the infrared thermal data of the target device from the marked infrared image to determine the temperature information of the target device includes: Extracting and analyzing the infrared thermal data of the target device from the marked infrared image to determine the maximum temperature and average temperature of the target device; Comparing the average temperature of the target device with the ambient temperature of the target device to determine a first temperature difference; Comparing the maximum temperature of the target device with the maximum temperature of other devices of the same type in the same scene as the target device to determine a second temperature difference; When the first temperature difference satisfies a first preset condition and the second temperature difference satisfies a second preset condition, the temperature of the target device is determined to be normal; otherwise, the temperature of the target device is determined to be abnormal. The first preset condition is that the first temperature difference is less than 5 degrees, and the second preset condition is that the second temperature difference is not higher than 30% of the highest temperature of other devices of the same type in the same scene.
4. A computer-readable storage medium, It is characterized in that The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 2.
5. An electronic device, It is characterized in that The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1-2 above.
