Vehicle-mounted pantograph-catenary temperature detection method and device

Abstract

The invention provides a vehicle-mounted pantograph-catenary temperature detection method and device, and the method comprises the steps: collecting an initial infrared image set containing a target train related pantograph-catenary through an infrared imaging device disposed at the roof of a target train; screening the initial infrared images contained in the initial infrared image set based on a pre-trained definition recognition model to obtain a to-be-processed infrared image set; based on a pre-trained noisy point elimination model, processing the to-be-processed infrared images contained in the to-be-processed infrared image set to obtain a target infrared image set; and according to the target infrared image set, determining the pantograph-catenary temperature associated with the target train. Automatic pantograph-catenary temperature monitoring is achieved, and the influence on the temperature monitoring process caused by the problems of image blurring, quality reduction, isolated pulse noise points and the like due to train movement is avoided.

Description

Technical Field

[0001] The present application relates to the field of rail transportation technology, and in particular to a vehicle-mounted pantograph-catenary temperature detection method. The present application also relates to a vehicle-mounted pantograph-catenary temperature detection device, a computing device, and a computer-readable storage medium. Background Art

[0002] On-board pantograph-catenary contact status testing typically includes monitoring for hard points, hard force, temperature, arcing, and anomalies. Conventional technology typically uses non-contact infrared thermal imaging to monitor pantograph-catenary contact temperature. This method is commonly used to monitor the temperature of abnormal heat sources such as power equipment and high-temperature friction. Compared to traditional contact temperature measurement methods, it offers advantages such as high accuracy, fast measurement speed, wide measurement range, no time constraints, and the ability to measure the temperature of small targets.

[0003] However, when it comes to detecting moving or dynamic targets, the main problems facing current infrared detection technology are: first, the sampling frame rate of industrial infrared cameras is limited, resulting in a small number of thermal images acquired per unit time; second, the effective range of the target's field of view changes with the movement of the target itself, which can cause local image tailing and affect image quality. Summary of the Invention

[0004] In view of this, the present invention provides a vehicle-mounted pantograph-catenary temperature detection method to address the technical deficiencies in the prior art. The present invention also provides a vehicle-mounted pantograph-catenary temperature detection device, a computing device, and a computer-readable storage medium.

[0005] According to a first aspect of an embodiment of the present application, a vehicle-mounted pantograph-catenary temperature detection method is provided, comprising:

[0006] An infrared imaging device arranged on the roof of a target train is used to collect an initial infrared image set containing the pantograph and catenary associated with the target train;

[0007] Based on a pre-trained clarity recognition model, the initial infrared images contained in the initial infrared image set are screened to obtain an infrared image set to be processed;

[0008] Based on the pre-trained noise removal model, the infrared images to be processed contained in the infrared image set to be processed are processed to obtain a target infrared image set;

[0009] The pantograph-catenary temperature associated with the target train is determined based on the target infrared image set.

[0010] Optionally, the pre-trained clarity recognition model is used to screen the initial infrared images contained in the initial infrared image set to obtain the infrared image set to be processed, including:

[0011] Using the initial infrared image as input of the clarity recognition model, wherein the model algorithm of the clarity recognition model includes Gaussian blur, binarization, Laplace operator and saturation operation;

[0012] The initial infrared images contained in the initial infrared image set are screened according to the output result of the clarity recognition model to obtain the infrared image set to be processed.

[0013] Optionally, the process of processing the initial infrared image by the clarity recognition model includes:

[0014] Performing Gaussian blur on the initial infrared image to obtain a first image;

[0015] Binarizing the first image to obtain a second image;

[0016] performing image enhancement on the second image using a Pilates operator to obtain a third image;

[0017] Processing the third image using a preset saturation operation formula to obtain a fourth image;

[0018] The variance of all pixels in the fourth image is calculated, and the fourth image having a variance smaller than a preset variance threshold is eliminated.

[0019] Optionally, the processing the third image using a preset saturation operation formula to obtain the fourth image includes:

[0020] All pixels included in the third image are processed according to the saturation operation formula, wherein the saturation operation formula is:

[0021] output = saturate(|α*input+β|),

[0022] The input is the grayscale value of the pixel in the third image, the output is the grayscale value of the pixel in the fourth image, and α and β are adjustable parameters determined by the training process of the clarity recognition model.

[0023] Optionally, calculating the variance of all pixels in the fourth image and eliminating fourth images whose variance is less than a preset variance threshold includes:

[0024] Determine the average value and standard deviation of all pixels in the fourth image;

[0025] Calculating the variance based on the mean and the standard deviation;

[0026] The fourth image whose variance is less than a preset variance threshold is eliminated, wherein the variance threshold is determined by the training process of the clarity recognition model.

[0027] Optionally, the noise removal model processes the infrared image to be processed, including:

[0028] Binarizing the infrared image to be processed, and constructing a grayscale value matrix according to the binarization result;

[0029] determining a grayscale threshold associated with the grayscale value matrix;

[0030] Constructing a target topology matrix based on the gray value matrix and the gray value matrix;

[0031] The initial infrared image to be processed is adjusted according to the target topology matrix to obtain a target infrared image.

[0032] Optionally, determining a grayscale threshold associated with the grayscale value matrix includes:

[0033] The maximum value of the grayscale values ​​of the pixels in the grayscale value matrix is ​​determined, and the maximum value is used as the grayscale threshold.

[0034] Optionally, constructing a target topology matrix based on the gray value matrix and the gray value matrix includes:

[0035] Comparing the pixel points in the gray value matrix with the gray value threshold, and marking the pixel points that are greater than or equal to the gray value threshold as 1, to obtain a topological matrix;

[0036] The identity matrix contained in the topology matrix is ​​queried, and the matrix elements located at the identity matrix position in the topology matrix are assigned a value of 1, and the matrix elements at other positions are assigned a value of 0, to obtain a target topology matrix.

[0037] According to a second aspect of an embodiment of the present application, a vehicle-mounted pantograph-catenary temperature detection device is provided, comprising:

[0038] an acquisition module configured to acquire an initial infrared image set containing the pantograph-catenary associated with the target train through an infrared imaging device arranged on the roof of the target train;

[0039] a screening module configured to screen the initial infrared images contained in the initial infrared image set based on a pre-trained clarity recognition model to obtain an infrared image set to be processed;

[0040] a noise removal module configured to process the infrared images to be processed contained in the infrared image set to be processed based on a pre-trained noise removal model to obtain a target infrared image set;

[0041] The temperature determination module is configured to determine the pantograph-catenary temperature associated with the target train based on the target infrared image set.

[0042] According to a third aspect of an embodiment of the present application, a computing device is provided, including:

[0043] memory and processor;

[0044] The memory is used to store computer-executable instructions, and the processor implements the steps of the vehicle-mounted pantograph-catenary temperature detection method when executing the computer-executable instructions.

[0045] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores computer-executable instructions. When the instructions are executed by a processor, the steps of the vehicle-mounted bow-catenary temperature detection method are implemented.

[0046] According to a fifth aspect of an embodiment of the present application, a chip is provided, which stores a computer program. When the computer program is executed by the chip, the steps of the vehicle-mounted bow-catenary temperature detection method are implemented.

[0047] The vehicle-mounted bow-net temperature detection method provided by the present application collects an initial infrared image set containing the bow-net associated with the target train by means of an infrared imaging device arranged on the roof of the target train; based on a pre-trained clarity recognition model, the initial infrared images contained in the initial infrared image set are screened to obtain a set of infrared images to be processed; based on a pre-trained noise removal model, the infrared images to be processed contained in the set of infrared images to be processed are processed to obtain a set of target infrared images; and based on the target infrared image set, the bow-net temperature associated with the target train is determined. Automated bow-net temperature monitoring is achieved, and the effects of image blur and quality degradation caused by train movement, as well as isolated pulse noise points, on the temperature monitoring process are avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 This is a flow chart of a vehicle-mounted pantograph-catenary temperature detection method provided in one embodiment of the present application;

[0050] Figure 2 This is a noise elimination flow chart of a vehicle-mounted pantograph-catenary temperature detection method provided in one embodiment of the present application;

[0051] Figure 3 This is a structural diagram of a vehicle-mounted pantograph-catenary temperature detection device provided in one embodiment of the present application;

[0052] Figure 4 This is a structural block diagram of a computing device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0053] The following description sets forth many specific details to facilitate a thorough understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of the present application. Therefore, the present application is not limited to the specific implementations disclosed below.

[0054] The terms used in one or more embodiments of the present application are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of the present application. The singular forms "a", "the" and "the" used in one or more embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of the present application refers to and includes any or all possible combinations of one or more associated listed items.

[0055] It should be understood that although the terms "first," "second," and the like may be used to describe various information in one or more embodiments of the present application, such information should not be limited to these terms. These terms are merely used to distinguish information of the same type from one another. For example, "first" may also be referred to as "second," and similarly, "second" may also be referred to as "first," without departing from the scope of one or more embodiments of the present application.

[0056] This application provides a vehicle-mounted pantograph-catenary temperature detection method. This application also relates to a vehicle-mounted pantograph-catenary temperature detection device, a computing device, and a computer-readable storage medium, which are described in detail in the following embodiments.

[0057] Figure 1 A flow chart of a vehicle-mounted pantograph-catenary temperature detection method according to an embodiment of the present application is shown, which specifically includes the following steps:

[0058] Step S102: using an infrared imaging device placed on the roof of the target train, collecting an initial infrared image set containing the pantograph-catenary associated with the target train;

[0059] Step S104: screening the initial infrared images contained in the initial infrared image set based on the pre-trained clarity recognition model to obtain an infrared image set to be processed;

[0060] Step S106: processing the infrared images to be processed contained in the infrared image set to be processed based on the pre-trained noise removal model to obtain a target infrared image set;

[0061] Step S108: Determine the pantograph-catenary temperature associated with the target train based on the target infrared image set.

[0062] Among them, for the target train in motion, the collected image data will have problems such as blurring and tailing. The clarity recognition model is used to measure the degree of image blurring to avoid or reduce problems such as image blurring and quality degradation caused by the movement of the target object; infrared thermal imaging usually has various isolated pulse noise points, which are specifically manifested as local maximum and minimum pixel values. In the process of extracting the predetermined grayscale value, it is very likely to be mistakenly judged as an overheating point. Therefore, the noise removal model is used to eliminate or modify the isolated pulse noise points.

[0063] Based on this, to process blurred images in image detection, the first step is to find an indicator that can measure the degree of image blur. This embodiment achieves this by calculating the variance of the image, and the clarity recognition model uses the YOLO framework to identify and detect the target object to improve the overall image quality, thereby effectively improving the accuracy of automatic recognition and positioning.

[0064] Specifically, the infrared imaging device can use an infrared thermal imager, which is mounted on the roof of the target train. The collected image data is sent to the image processing equipment installed in the carriage. The image is processed by the clarity recognition model and noise removal model arranged therein to obtain a target infrared image set for temperature detection.

[0065] Furthermore, in step S104, the initial infrared images contained in the initial infrared image set are screened based on the pre-trained clarity recognition model to obtain the infrared image set to be processed. In this embodiment, the specific implementation is as follows:

[0066] The initial infrared image is used as the input of the clarity recognition model, wherein the model algorithm of the clarity recognition model includes Gaussian blur, binarization, Laplace operator and saturation operation; according to the output result of the clarity recognition model, the initial infrared images contained in the initial infrared image set are screened to obtain the infrared image set to be processed.

[0067] Furthermore, the processing of the initial infrared image by the above definition recognition model is specifically implemented as follows in this embodiment:

[0068] Gaussian blur is performed on the initial infrared image to obtain a first image; the first image is binarized to obtain a second image; the second image is enhanced by a Pilates operator to obtain a third image; the third image is processed by a preset saturation operation formula to obtain a fourth image; the variance of all pixels in the fourth image is calculated, and the fourth image whose variance is less than a preset variance threshold is eliminated.

[0069] Furthermore, the process of processing the third image using the preset saturation operation formula to obtain the fourth image is specifically implemented as follows in this embodiment:

[0070] According to the saturation operation formula, all pixels contained in the third image are processed, wherein the saturation operation formula is, output = saturate(|α*input+β|), wherein the input is the grayscale value of the pixel in the third image, the output is the grayscale value of the pixel in the fourth image, α and β are adjustable parameters determined by the training process of the clarity recognition model.

[0071] Furthermore, the above process of calculating the variance of all pixels in the fourth image and eliminating the fourth image whose variance is less than a preset variance threshold is specifically implemented as follows in this embodiment:

[0072] Determine the average value and standard deviation of all pixels in the fourth image; calculate the variance based on the average value and the standard deviation; and eliminate the fourth image whose variance is less than a preset variance threshold, wherein the variance threshold is determined by the training process of the clarity recognition model.

[0073] Among them, the process of performing Gaussian blur processing on the initial infrared image is to assign weights through the normal distribution on the two-dimensional image, obtain the weight matrix, and calculate the Gaussian blur value, and then perform Gaussian blur operation on the values ​​of all RGB channels on the entire initial infrared image to obtain the first image.

[0074] Subsequently, the first image is grayscaled, or binarized, to obtain a grayscale image, which serves as the second image. The Laplace operator is then used to enhance the grayscale image, or the second image, thereby enhancing areas with significant grayscale changes while reducing grayscale changes in areas with less significant changes. Convolution of the image with the Laplace operator reveals changes in image edge features. While the Laplace operator can enhance grayscale trends, it is also highly sensitive to noise. Therefore, image smoothing, specifically Gaussian smoothing, is performed before Laplace processing. The second image enhanced with the Laplace operator serves as the third image.

[0075] Next, the third image is processed using a saturation calculation formula. Specifically, a pixel in the third image is used as the input for the saturation calculation formula output = saturate(|α*input + β|), and the output is used as the grayscale value of the pixel at the corresponding position in the fourth image. Furthermore, the adjustable parameters in the saturation calculation formula are determined during the training process of the clarity recognition model. Specifically, a sample image in the sample data is input into the clarity recognition model, and the output result is used together with the standard data in the sample data to construct a loss function. The clarity recognition model is adjusted using the loss function, and after the adjustment is completed, the determined values ​​of α and β are obtained.

[0076] Finally, the average and standard deviation of the grayscale values ​​of all pixels in the fourth image are called, and the variance of all pixels in the fourth image is calculated using a variance function. Since the calculated pixel variance in a blurred infrared image is generally small, by setting this calculation indicator and reasonably setting the variance threshold, blurred images are identified and preprocessed, successfully eliminating such images and preventing them from participating in the subsequent bownet temperature detection process. It should be noted that the setting of the variance threshold is also determined by the training process of the clarity recognition model. The specific process is similar to the determination process of α and β described above, and will not be repeated in this embodiment.

[0077] Furthermore, in step S106, the noise removal model processes the infrared image to be processed. In this embodiment, the specific implementation is as follows:

[0078] Binarize the infrared image to be processed and construct a gray value matrix based on the binarization result; determine a gray threshold associated with the gray value matrix; construct a target topology matrix based on the gray value matrix and the gray value matrix; adjust the initial infrared image to be processed according to the target topology matrix to obtain a target infrared image.

[0079] Furthermore, in this embodiment, the above process of determining the grayscale threshold associated with the grayscale value matrix is ​​specifically implemented as follows:

[0080] The maximum value of the grayscale values ​​of the pixels in the grayscale value matrix is ​​determined, and the maximum value is used as the grayscale threshold.

[0081] Furthermore, the above process of constructing a target topology matrix based on the gray value matrix and the gray value matrix is ​​specifically implemented as follows in this embodiment:

[0082] The pixel points in the gray value matrix are compared with the gray value threshold, and the pixel points greater than or equal to the gray value threshold are marked as 1 to obtain a topological matrix; the unit matrix contained in the topological matrix is ​​queried, and the matrix elements located at the unit matrix position in the topological matrix are assigned a value of 1, and the matrix elements at other positions are assigned a value of 0 to obtain a target topological matrix.

[0083] The fourth image to be eliminated is determined, and the initial infrared images corresponding to the fourth image to be eliminated are determined, and these initial infrared images are eliminated from the initial infrared image set to obtain the infrared image set to be processed.

[0084] Based on this, Figure 2 As shown in the noise removal flow chart of a vehicle-mounted bow-net temperature detection method, first, the original infrared thermal image, that is, the infrared image to be processed in the infrared image set to be processed, is input, and then converted into a grayscale value matrix. Specifically, the infrared image to be processed is converted into a grayscale image through binarization processing, and a grayscale value matrix is ​​constructed according to the grayscale value of each pixel in the grayscale image, and p(x,y) represents the grayscale value of the pixel in the image.

[0085] Furthermore, Mi×j represents the grayscale value matrix composed of grayscale values, which is an i×j-order matrix. The maximum grayscale value is determined to be Maxi×j, and the grayscale threshold is set to Th. Let Th = Maxi×j. When p(x,y) ≥ Th, the original image is marked as 1, and when p(x,y) < Th, the original image is marked as 0. This generates a topological matrix, which is an i×j-order matrix. Next, the unit matrix is ​​searched and assigned values. Specifically, all pixels in the Pi×j matrix are searched to find the unit matrix. The corresponding position of the unit matrix in the i×j-order matrix Pi×'j, whose element values ​​are all zero, is assigned to 1. The other elements of the matrix Pi×'j are assigned to 0, generating a new topological matrix, i.e., the target topological matrix. Finally, the initial infrared image to be processed is adjusted according to the target topological matrix to obtain the target infrared image. Based on the target infrared image set, the pantograph-catenary temperature associated with the target train can be determined.

[0086] In summary, after topology matrix optimization and variance threshold elimination optimization in this embodiment, both detection accuracy and detection rate are significantly improved. The improved YOLOv5 model eliminates blurry images that are difficult to distinguish before recognition, and only recognizes images that can be correctly identified, greatly improving detection accuracy. The addition of pre-screening of overheated areas before recognition also greatly increases detection rate.

[0087] Corresponding to the above method embodiment, the present application also provides an embodiment of a vehicle-mounted pantograph-catenary temperature detection device, Figure 3FIG1 shows a schematic structural diagram of a vehicle-mounted pantograph-catenary temperature detection device provided by an embodiment of the present application. Figure 3 As shown, the device includes:

[0088] The acquisition module 302 is configured to acquire an initial infrared image set containing the pantograph-catenary associated with the target train by using an infrared imaging device arranged on the roof of the target train;

[0089] The screening module 304 is configured to screen the initial infrared images contained in the initial infrared image set based on a pre-trained clarity recognition model to obtain an infrared image set to be processed;

[0090] The noise removal module 306 is configured to process the infrared images to be processed contained in the infrared image set to be processed based on a pre-trained noise removal model to obtain a target infrared image set;

[0091] The temperature determination module 308 is configured to determine the pantograph-catenary temperature associated with the target train based on the target infrared image set.

[0092] In an optional embodiment, the screening module 304 is further configured to:

[0093] The initial infrared image is used as the input of the clarity recognition model, wherein the model algorithm of the clarity recognition model includes Gaussian blur, binarization, Laplace operator and saturation operation; according to the output result of the clarity recognition model, the initial infrared images contained in the initial infrared image set are screened to obtain the infrared image set to be processed.

[0094] In an optional embodiment, the screening module 304 is further configured to:

[0095] Gaussian blur is performed on the initial infrared image to obtain a first image; the first image is binarized to obtain a second image; the second image is enhanced by a Pilates operator to obtain a third image; the third image is processed by a preset saturation operation formula to obtain a fourth image; the variance of all pixels in the fourth image is calculated, and the fourth image whose variance is less than a preset variance threshold is eliminated.

[0096] In an optional embodiment, the screening module 304 is further configured to:

[0097] According to the saturation operation formula, all pixels contained in the third image are processed, wherein the saturation operation formula is, output = saturate(|α*input+β|), wherein the input is the grayscale value of the pixel in the third image, the output is the grayscale value of the pixel in the fourth image, α and β are adjustable parameters determined by the training process of the clarity recognition model.

[0098] In an optional embodiment, the screening module 304 is further configured to:

[0099] Determine the average value and standard deviation of all pixels in the fourth image; calculate the variance based on the average value and the standard deviation; and eliminate the fourth image whose variance is less than a preset variance threshold, wherein the variance threshold is determined by the training process of the clarity recognition model.

[0100] In an optional embodiment, the noise removal module 306 is further configured to:

[0101] Binarize the infrared image to be processed and construct a gray value matrix based on the binarization result; determine a gray threshold associated with the gray value matrix; construct a target topology matrix based on the gray value matrix and the gray value matrix; adjust the initial infrared image to be processed according to the target topology matrix to obtain a target infrared image.

[0102] In an optional embodiment, the noise removal module 306 is further configured to:

[0103] The maximum value of the grayscale values ​​of the pixels in the grayscale value matrix is ​​determined, and the maximum value is used as the grayscale threshold.

[0104] In an optional embodiment, the noise removal module 306 is further configured to:

[0105] The pixel points in the gray value matrix are compared with the gray value threshold, and the pixel points greater than or equal to the gray value threshold are marked as 1 to obtain a topological matrix; the unit matrix contained in the topological matrix is ​​queried, and the matrix elements located at the unit matrix position in the topological matrix are assigned a value of 1, and the matrix elements at other positions are assigned a value of 0 to obtain a target topological matrix.

[0106] The vehicle-mounted bow-net temperature detection device provided by the present application collects an initial infrared image set containing the bow-net associated with the target train through an infrared imaging device arranged on the roof of the target train; based on a pre-trained clarity recognition model, the initial infrared images contained in the initial infrared image set are screened to obtain a set of infrared images to be processed; based on a pre-trained noise rejection model, the infrared images to be processed contained in the set of infrared images to be processed are processed to obtain a set of target infrared images; based on the target infrared image set, the bow-net temperature associated with the target train is determined. Automated bow-net temperature monitoring is achieved, and the effects of image blur and quality degradation caused by train movement, as well as isolated pulse noise points, on the temperature monitoring process are avoided.

[0107] The above is a schematic scheme of a vehicle-mounted bow-net temperature detection device of this embodiment. It should be noted that the technical solution of the vehicle-mounted bow-net temperature detection device and the technical solution of the above-mentioned vehicle-mounted bow-net temperature detection method belong to the same concept. For details that are not described in detail in the technical solution of the vehicle-mounted bow-net temperature detection device, please refer to the description of the technical solution of the above-mentioned vehicle-mounted bow-net temperature detection method. In addition, the various components in the device embodiment should be understood as functional modules that must be established to implement each step of the program flow or each step of the method, and each functional module is not an actual functional division or separation definition. The device claim defined by such a group of functional modules should be understood as a functional module architecture that mainly implements the solution through the computer program recorded in the specification, and should not be understood as a physical device that mainly implements the solution through hardware.

[0108] Figure 4 4 shows a block diagram of a computing device 400 according to an embodiment of the present application. Components of the computing device 400 include, but are not limited to, a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and a database 450 is used to store data.

[0109] The computing device 400 also includes an access device 440 that enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 440 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0110] In one embodiment of the present application, the above components of the computing device 400 and Figure 4 Other components not shown in the figure may also be connected to each other, for example, via a bus. Figure 4 The computing device structure block diagram shown is for illustrative purposes only and is not intended to limit the scope of the present application. Those skilled in the art may add or replace other components as needed.

[0111] Computing device 400 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 400 can also be a mobile or stationary server.

[0112] Among them, the processor 420 is used to execute computer executable instructions of each step of the vehicle-mounted pantograph-catenary temperature detection method.

[0113] The above is a schematic diagram of a computing device according to this embodiment. It should be noted that the technical solution of the computing device and the technical solution of the vehicle-mounted pantograph-catenary temperature detection method are of the same concept. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the vehicle-mounted pantograph-catenary temperature detection method.

[0114] An embodiment of the present application further provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, are used to execute the various steps of the vehicle-mounted pantograph-catenary temperature detection method.

[0115] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of this storage medium and the technical scheme of the above-mentioned vehicle-mounted pantograph-catenary temperature detection method are of the same concept. For details not described in detail in the technical scheme of the storage medium, please refer to the description of the technical scheme of the above-mentioned vehicle-mounted pantograph-catenary temperature detection method.

[0116] An embodiment of the present application further provides a chip storing a computer program, which implements the steps of the vehicle-mounted bow-net temperature detection method when executed by the chip.

[0117] The foregoing description describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0118] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0119] It should be noted that for the aforementioned method embodiments, for ease of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0120] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0121] The preferred embodiments of the present application disclosed above are intended only to help illustrate the present application. The optional embodiments do not describe all details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of this application. This application selects and describes these embodiments in detail in order to better explain the principles and practical applications of this application, so that those skilled in the art can better understand and utilize this application. This application is limited only by the claims and their full scope and equivalents.

Claims

1. A vehicle-mounted pantograph-catenary temperature detection method, characterized in that: include: An infrared imaging device arranged on the roof of a target train is used to collect an initial infrared image set containing the pantograph and catenary associated with the target train; Based on a pre-trained clarity recognition model, the initial infrared images contained in the initial infrared image set are screened to obtain an infrared image set to be processed; Based on the pre-trained noise removal model, the infrared images to be processed contained in the infrared image set to be processed are processed to obtain a target infrared image set; The pantograph-catenary temperature associated with the target train is determined based on the target infrared image set.

2. The method according to claim 1, characterized in that The pre-trained definition recognition model is used to screen the initial infrared images contained in the initial infrared image set to obtain the infrared image set to be processed, including: Using the initial infrared image as input of the clarity recognition model, wherein the model algorithm of the clarity recognition model includes Gaussian blur, binarization, Laplace operator and saturation operation; The initial infrared images contained in the initial infrared image set are screened according to the output result of the clarity recognition model to obtain the infrared image set to be processed.

3. The method according to claim 2, characterized in that The process of processing the initial infrared image by the clarity recognition model includes: Performing Gaussian blur on the initial infrared image to obtain a first image; Binarizing the first image to obtain a second image; performing image enhancement on the second image using a Pilates operator to obtain a third image; Processing the third image using a preset saturation operation formula to obtain a fourth image; The variance of all pixels in the fourth image is calculated, and the fourth image having a variance smaller than a preset variance threshold is eliminated.

4. The method according to claim 3, characterized in that The processing of the third image by a preset saturation operation formula to obtain a fourth image includes: All pixels included in the third image are processed according to the saturation operation formula, wherein the saturation operation formula is: output = saturate(|α*input+β|), The input is the grayscale value of the pixel in the third image, the output is the grayscale value of the pixel in the fourth image, and α and β are adjustable parameters determined by the training process of the clarity recognition model.

5. The method according to claim 3, characterized in that The calculating the variance of all pixels in the fourth image and eliminating the fourth image having a variance less than a preset variance threshold includes: Determine the average value and standard deviation of all pixels in the fourth image; Calculating the variance based on the mean and the standard deviation; The fourth image whose variance is less than a preset variance threshold is eliminated, wherein the variance threshold is determined by the training process of the clarity recognition model.

6. The method according to claim 1, characterized in that The noise removal model processes the infrared image to be processed, including: Binarizing the infrared image to be processed, and constructing a grayscale value matrix according to the binarization result; determining a grayscale threshold associated with the grayscale value matrix; Constructing a target topology matrix based on the gray value matrix and the gray value matrix; The initial infrared image to be processed is adjusted according to the target topology matrix to obtain a target infrared image.

7. The method according to claim 6, characterized in that The determining of a grayscale threshold value associated with the grayscale value matrix comprises: The maximum value of the grayscale values ​​of the pixels in the grayscale value matrix is ​​determined, and the maximum value is used as the grayscale threshold.

8. The method according to claim 6, characterized in that The constructing a target topology matrix based on the gray value matrix and the gray value matrix includes: Comparing the pixel points in the gray value matrix with the gray value threshold, and marking the pixel points that are greater than or equal to the gray value threshold as 1, to obtain a topological matrix; The identity matrix contained in the topology matrix is ​​queried, and the matrix elements located at the identity matrix position in the topology matrix are assigned a value of 1, and the matrix elements at other positions are assigned a value of 0, to obtain a target topology matrix.

9. A vehicle-mounted pantograph-catenary temperature detection device, characterized in that: include: an acquisition module configured to acquire an initial infrared image set containing the pantograph-catenary associated with the target train through an infrared imaging device arranged on the roof of the target train; a screening module configured to screen the initial infrared images contained in the initial infrared image set based on a pre-trained clarity recognition model to obtain an infrared image set to be processed; a noise removal module configured to process the infrared images to be processed contained in the infrared image set to be processed based on a pre-trained noise removal model to obtain a target infrared image set; The temperature determination module is configured to determine the pantograph-catenary temperature associated with the target train based on the target infrared image set.

Images