Method and apparatus for distinguishing between charged and uncharged mid-infrared and visible light images

Abstract

The application provides a charged detection mid-infrared image and visible light image distinguishing method and device, relates to the technical field of charged detection, solves the problem of low artificial judgment efficiency and possible errors caused by non-uniform distinguishing standards of infrared images and visible light images shot by different manufacturers in the field, can accurately and efficiently determine the type of the to-be-detected image, and enables the background system to accurately judge the equipment operation condition based on the accurate image type. The method comprises the following steps: acquiring a to-be-detected image of a power equipment in a running state; determining whether an association relationship matching key information of a file name is contained in a database according to the file name, the association relationship being used for associating the key information with the type of the image, the type being an infrared image or a visible light image; if the database contains the association relationship matching the key information, determining the type of the to-be-detected image according to the association relationship; otherwise, determining the type of the to-be-detected image according to pixel features of the to-be-detected image.

Description

Technical Field

[0001] The present application relates to the technical field of charge detection, and in particular to a method and device for distinguishing between infrared images and visible light images in charge detection. Background Art

[0002] Live inspection technology is a non-destructive testing method performed on operating electrical equipment. It aims to promptly detect potential equipment failures and ensure the safe and stable operation of the power system. Routine live inspection and testing of primary and secondary equipment in normal operation is a crucial component of power grid operations and maintenance. This work involves a wide variety of main equipment types, a wide range of sensor types used in operation, a large amount of data required for manual recording and export, and a high level of complexity in inspection scheduling and management.

[0003] Inspection equipment is required at sites within power systems, including power generation, transmission, and distribution systems, to collect on-site images. These images can be used to predict power system faults, for example by inputting them into fault models. To improve the accuracy and efficiency of fault prediction, different types of on-site images reflecting different site characteristics can be registered and fused. For example, image fusion can be used to combine the thermal detail information of an infrared image with the texture information of a visible light image to generate a composite image containing both temperature and structural information. Finally, image recognition is performed on this composite image to identify abnormalities such as partial discharge and mechanical failures in power equipment, enabling timely detection and resolution of potential safety hazards. Therefore, the backend system must clearly identify the image type, whether infrared or visible light, in order to accurately carry out the subsequent processing steps.

[0004] Currently, various inspection equipment manufacturers exhibit significant discrepancies in how they distinguish between infrared and visible light images, with some manufacturers even failing to differentiate between the two. Due to the lack of a unified standard for differentiation, backend systems receiving image data from inspection equipment from multiple manufacturers must rely on manual differentiation of image types. However, manual differentiation is not only inefficient but also labor-intensive and time-consuming when dealing with large volumes of inspection images. Therefore, a solution for efficiently distinguishing between infrared and visible light images is urgently needed. Summary of the Invention

[0005] The present application provides a method and device for distinguishing between infrared images and visible light images in live detection, which solves the problem in this field that inspection equipment from different manufacturers have inconsistent standards for distinguishing between infrared images and visible light images. It can accurately and efficiently determine the type of image to be detected, effectively reducing the possible misclassification that may occur during manual judgment, and helps the background system to more accurately judge the equipment operation status based on the accurate image type, timely discover potential problems, thereby effectively ensuring the safe and stable operation of the equipment.

[0006] In a first aspect, a method for distinguishing infrared images from visible light images in charge detection is provided, comprising:

[0007] Acquire images of power equipment to be inspected in an operating state;

[0008] According to the file name of the image to be detected, determine whether the database contains an association relationship that matches the key information of the file name, and the association relationship is used to associate the key information with the type of the image, which is an infrared image or a visible light image;

[0009] If the database contains an association relationship that matches the key information, the type of the image to be detected is determined based on the association relationship;

[0010] Otherwise, the type of the image to be detected is determined according to the pixel features of the image to be detected.

[0011] In a feasible design, determining the type of the image to be detected based on the pixel features of the image to be detected includes:

[0012] Obtain the target grayscale histogram of the image to be detected;

[0013] The type of the image to be detected is determined based on the skewness and / or kurtosis of the target grayscale histogram.

[0014] In a feasible design, the type of the image to be detected is determined based on the skewness and / or kurtosis of the target grayscale histogram, including:

[0015] If the skewness of the target grayscale histogram is within a predetermined first range, or the kurtosis of the target grayscale histogram is within a predetermined second range, determining that the type of the image to be detected is an infrared image;

[0016] Otherwise, it is determined that the type of the image to be detected is a visible light image.

[0017] In a feasible design, if the skewness of the target grayscale histogram is outside the first range and the kurtosis of the target grayscale histogram is outside the second range, the method further includes:

[0018] The type of the image to be detected is determined according to the green channel value of the pixel of the image to be detected.

[0019] In one possible design, the method further includes:

[0020] By traversing pixels of the visible light images in the database, a first average value is determined, where the first average value is an average value of green channel values ​​of each visible light image in the database.

[0021] In a feasible design, determining the type of the image to be detected according to the green channel value of the pixel of the image to be detected includes:

[0022] Determine a second average value by traversing pixels of the image to be detected, where the second average value is an average value of each green channel value of the image to be detected;

[0023] comparing the second mean with the first mean;

[0024] If the second average value is less than the first average value, determining that the type of the image to be detected is an infrared image;

[0025] Otherwise, the type of the image to be detected is determined to be a visible light image, or the type of the image to be detected is determined according to the file size of the image to be detected.

[0026] In a feasible design, the type of the image to be detected is determined based on the file size of the image to be detected, including:

[0027] Acquire another image to be detected corresponding to the image to be detected, wherein the other image to be detected and the image to be detected form a pair of visible light images and infrared images for image registration processing;

[0028] Comparing the file size of the image to be detected with the file size of another image to be detected;

[0029] If the file size of the image to be detected is larger than the file size of another image to be detected, determining that the type of the image to be detected is an infrared image;

[0030] Otherwise, it is determined that the type of the image to be detected is a visible light image.

[0031] In a feasible design, the method further includes: when the image to be detected is one of a pair of an infrared image and a visible light image, if the type of the image to be detected is an infrared image, determining that the type of the other image to be detected is a visible light image;

[0032] If the type of the image to be detected is a visible light image, it is determined that the type of the other image to be detected is an infrared image.

[0033] In a feasible design, the key information is a character or code in the main file name for indicating the type of the image, or the key information is an extension name, according to the file name of the image to be detected, it is determined whether the database contains an association relationship matching the key information of the file name, if the database contains the association relationship matching the key information, the type of the image to be detected is determined according to the association relationship, comprising:

[0034] The main file name of the image to be detected is matched with the characters or codes in the database used by each manufacturer according to the type of the image;

[0035] If the main file name of the image to be detected contains the characters or codes in the database, the association relationship in the database matching the characters or codes contained in the main file name is determined according to the characters or codes contained in the main file name, and the type of the image to be detected is determined according to the association relationship;

[0036] If the main file name of the image to be detected does not contain the characters or codes in the database, and the file name of the image to be detected contains the extension name, it is determined whether the database contains an association relationship matching the extension name of the image to be detected;

[0037] If the database contains the association relationship matching the extension name of the image to be detected, the type of the image to be detected is determined according to the association relationship.

[0038] In a second aspect, an apparatus for distinguishing infrared images from visible light images in live detection is provided, comprising:

[0039] An image acquisition module is configured to acquire an image to be detected of a power device in a running state;

[0040] An image type identification module is configured to determine, according to a file name of the image to be detected, whether a database contains an association relationship matching key information of the file name, the association relationship being used to associate the key information with a type of the image, the type being an infrared image or a visible light image;

[0041] The image type identification module is further configured to determine, if the database contains the association relationship matching the key information, the type of the image to be detected according to the association relationship;

[0042] Otherwise, the image type identification module is further configured to determine the type of the image to be detected according to a pixel feature of the image to be detected.

[0043] The database of the embodiments of the present application includes a large number of infrared images and visible light images taken by inspection equipment of existing manufacturers, which are widely sourced and cover various practical application scenarios and device models. Therefore, the database of the present application has high representativeness and comprehensiveness. On this basis, according to the file name of the to-be-detected image, the corresponding association in the database can basically be found, so as to accurately and efficiently determine whether the to-be-detected image is an infrared image or a visible light image. In the rare case that the type of the image cannot be determined through the file name of the image and the database, the present application also provides a scheme for determining the type of the to-be-detected image according to the pixel characteristics of the to-be-detected image. Therefore, no matter how complex the way of distinguishing image types of the inspection equipment is or even if it is not distinguished, the present application scheme can automatically adapt and accurately identify the type of the image. It can be seen that, compared with the traditional manual judgment method, the present application has excellent adaptive ability and can accurately distinguish the type of the image without human intervention. This feature greatly improves the data processing efficiency, significantly saves manpower and time cost, and enables the detection work to be more efficient and smooth, thereby providing strong support for large-scale detection work.

[0044] In actual live detection scenarios, when the present application scheme is applied to a handheld live detection mobile terminal, after obtaining the infrared image and the visible light image, the present application scheme is used to quickly and accurately distinguish and process the images, and the type of the image is displayed in the file name using a specific field according to a preset rule. Then, the distinguished image is accurately uploaded to the background system through the live detection function. The background system can accurately determine the type of the image according to the preset rule, and efficiently process and analyze the image, so as to realize accurate circulation and effective utilization of image data in the entire live detection work process. The live detection mobile terminal applying the present application can help power grid operation and maintenance team members in routine inspection to realize real-time processing and uploading of maintenance and experimental data in a digital and wireless manner, which not only reduces the heavy workload of the staff, but also greatly improves the timeliness and accuracy of the data.

[0045] In summary, the present application scheme effectively reduces the error classification that may occur in the manual judgment process, accurately identifies the type of the image, and provides more reliable data basis for equipment state evaluation; helps the background system to more accurately judge the equipment operation condition based on the accurate image type, timely discovers potential problems, thereby effectively guarantees the safe and stable operation of the equipment, improves the quality and reliability of the detection work, and reduces the risk of equipment failure. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, for those skilled in the art, other drawings can also be obtained based on these drawings without any creative effort.

[0047] Figure 1 is a schematic flow chart of a method for distinguishing infrared images and visible light images in live-line detection according to an example embodiment of the present application;

[0048] Figure 2 is a schematic flow chart of another method for distinguishing infrared images and visible light images in live-line detection according to an example embodiment of the present application;

[0049] Figure 3 is a schematic diagram of a device for distinguishing infrared images and visible light images in live-line detection according to an example embodiment of the present application. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort fall within the scope of protection of the present application.

[0051] An infrared image refers to an image reflecting the temperature distribution of an object surface acquired by infrared thermal imaging technology, usually representing different temperature regions in specific colors or gray scales. A visible light image refers to an image presenting the real color and appearance of an object acquired by shooting in the visible light band. Infrared images and visible light images have different characteristics, such as resolution, viewing angle, field of view, etc. Identifying the image type helps the background system to adopt a suitable registration algorithm. After identifying the image type, the background system can effectively fuse the thermal detail information of the infrared image and the texture information of the visible light image.

[0052] It can be seen that distinguishing infrared images and visible light images is a necessary condition for the smooth progress of the processing flow of the inspection device to the background system. From the uploading of the image by the inspection device to a series of image processing operations by the background system, each link depends on the accurate image type judgment. If this link is wrong, the subsequent image registration, fusion and recognition operations cannot be correctly executed, and the entire live-line detection system cannot effectively find and handle the safety hazards in the power equipment.

[0053] However, at present, after the image data obtained by the inspection equipment is uploaded to the background system, due to the lack of unified distinguishing criteria, the type of the picture can only be distinguished by manual operation in the background system. This method is not only extremely inefficient, but also consumes a large amount of manpower and time cost when facing a large number of detection pictures. Moreover, human judgment has strong subjectivity and is prone to cause false classification. For example, the infrared spectrum is incorrectly judged as a visible light picture, which may cause an incorrect assessment of the heating condition of the equipment, thereby affecting the accuracy of the equipment maintenance decision and endangering the safe operation of the equipment. If the background system cannot accurately identify the type of the image, the entire data processing process will be stalled, seriously damaging the continuity and accuracy of the live detection work.

[0054] Based on the above problems, as shown in the Figure 1 The present application provides a method for distinguishing infrared images and visible light images in live detection, comprising:

[0055] S110, obtaining a to-be-detected image of a power equipment in a running state.

[0056] It should be noted that in the live detection process, the to-be-detected image of the power equipment in the running state can be obtained by the inspection equipment. Generally, the infrared image and the visible light image containing the image of the power equipment photographed by the inspection equipment appear in pairs. After the to-be-detected images photographed by multiple inspection equipment are collected to the live detection mobile terminal, the images are processed for type distinguishing, and then uploaded to the background system. It can be understood that the to-be-detected images photographed by multiple inspection equipment can also be directly uploaded to the background system, and the background system first processes the images for type distinguishing and then determines the running state of the power equipment through calculation.

[0057] The inspection equipment can be a drone moving in the air and a patrol robot moving on the ground, such as a patrol robot or a drone equipped with multi-modal (visible light image and infrared image) sensors.

[0058] It should be understood that the scheme of the present application can be applied not only to the live detection mobile terminal, but also to the live detection background system. When applied to the live detection mobile terminal, the distinguishing and processing can be directly performed on site; when the live detection mobile terminal is equipped with a background system, fault diagnosis and maintenance can be performed in real time on site based on the distinguished infrared image and visible light image, thereby improving the inspection efficiency.

[0059] The charged detection mobile terminal is a special device for charged detection, and a detection personnel can complete daily inspection, operation and maintenance of the power equipment by operating the charged detection mobile terminal. In actual application, a plurality of inspection devices can capture a pair of infrared images and visible light images of the same power equipment in a running state, and then upload the images to the charged detection mobile terminal. The charged detection mobile terminal obtains the infrared images and the visible light images, and uploads the images to the background system. The background system needs to perform image processing such as image registration, image fusion and image recognition on the infrared images and the visible light images. The image registration is a key prerequisite for subsequent image processing, and the purpose is to match and superimpose a plurality of images with different resolutions, different angles of view and different fields of view in the same scene. The background system aligns the infrared images and the visible light images through the image registration processing, and then fuses the thermal detail information of the infrared images and the texture information of the visible light images through the image fusion processing to generate a comprehensive image containing temperature and structure information. Finally, image recognition is performed on the basis of the comprehensive image to identify abnormal conditions such as partial discharge and mechanical failure in the power equipment, so that potential safety hazards can be found and handled in time.

[0060] Since the images collected to the charged detection mobile terminal are often from infrared cameras or visible light cameras of inspection devices of different manufacturers, and lack a unified image type distinguishing standard, the charged detection mobile terminal applies the scheme for distinguishing the image type of the to-be-detected image to improve the work efficiency of the power grid operation and maintenance inspection team members, and the accuracy of image type distinguishing, thereby improving the ability of the background system to identify abnormal conditions such as partial discharge and mechanical failure in the power equipment.

[0061] In S120, whether the database contains an association relationship matching the key information of the file name is determined according to the file name of the to-be-detected image.

[0062] The association relationship is used to associate the key information and the type of the image, and the type is an infrared image or a visible light image.

[0063] The database is constructed by the following methods in the present application.

[0064] Firstly, a large number of infrared images and visible light images captured by inspection devices of a plurality of existing common manufacturers are collected and stored in the database; then, the images are systematically sorted and analyzed, and the key information related to distinguishing the infrared images and the visible light images is extracted and saved, for example, characters or codes used by manufacturers when naming the images according to the type of the images, or specific format suffixes (i.e. extensions) for distinguishing the type of the images; finally, a plurality of association relationships for associating the key information and the type of the image are created and saved in the database.

[0065] The images in the database are from a wide range of sources, covering various practical application scenarios and device models, thereby ensuring that the database is highly representative and comprehensive. The database will serve as a solid foundation for the subsequent type identification of images, providing rich reference for the algorithm.

[0066] In S130, if the database contains an association relationship matching the key information, the type of the image to be detected is determined according to the association relationship.

[0067] In a feasible design, the type of the image can be quickly determined by using the file name of the image, which includes the main file name and can also include the extension name. In this case, the key information is the character or code in the main file name indicating the type of the image, or the key information is the extension name. Correspondingly, the association relationship is used to associate the character in the main file name with the type of the image, or the association relationship is used to associate the code in the main file name with the type of the image, or the association relationship is used to associate the extension name with the type of the image. In this case, the type of the image to be detected is determined according to the file name of the image to be detected in the following way: whether the database contains an association relationship matching the file name of the image to be detected, and if the database contains an association relationship matching the file name of the image to be detected, the type of the image to be detected is determined according to the association relationship.

[0068] The main file name of the image to be detected is matched with the characters or codes used by each manufacturer according to the type of the image in the database.

[0069] If the main file name of the image to be detected contains the characters or codes in the database, the association relationship in the database matching the characters or codes contained in the main file name is determined according to the characters or codes contained in the main file name, and the type of the image to be detected is determined according to the association relationship.

[0070] If the main file name of the image to be detected does not contain the characters or codes in the database, and the file name of the image to be detected contains the extension name, it is determined whether the database contains an association relationship matching the extension name of the image to be detected.

[0071] If the database contains an association relationship matching the extension name of the image to be detected, the type of the image to be detected is determined according to the association relationship.

[0072] The above example first matches the main file name of the image to be detected with the characters or codes in the database. If the main file name of the image to be detected contains the characters or codes in the database, it means that the database contains the association relationship matching the characters or codes in the main file name. The type of the image to be detected is directly determined according to the association relationship. For example, if the file name contains the word “infrared” or a specific infrared-related code, it is determined to be an infrared image; if it contains the word “visible light” or the corresponding code, it is determined to be a visible light image. If the main file name of the image to be detected does not contain the characters or codes in the database, it means that the main file name does not contain characters or codes indicating the type of the image, or the database does not save the characters or codes in the main file name and the corresponding association relationship. The matching association relationship can be further determined to determine the type of the image to be detected. For example, if the extension of the image is “.IR.jpg”, “.ir.jpg”, “.irp.jpg”, then the type of the image is an infrared image, and if the extension of the image is “.DC.jpg”, “.vi.jpg”, then the type of the image is a visible light image. The example first determines the type of the image through the main file name, and then determines the type of the image through the extension, realizing multi-dimensional determination of the type of the image and increasing the accuracy of determining the type of the image.

[0073] In addition, in practice, the information related to the type of the image in the main file name is more obvious, and the extension that indicates the type of the image has more types. For example, the main file name of an infrared image contains “infrared” related words, and the extension of an infrared image can be “.IR.jpg”, “.ir.jpg”, “.irp.jpg”, etc. Therefore, this way of determining the type of the image through the main file name first and then through the extension can reduce unnecessary subsequent judgment steps as much as possible and improve the overall work efficiency.

[0074] It should be understood that if the file name of the image to be detected does not contain an extension, or if the file name of the image to be detected contains an extension, but the database does not contain an association relationship matching the extension of the image to be detected, a subsequent step of determining the type of the image according to the pixel characteristics of the image needs to be performed.

[0075] It should be noted that due to the possibility of different characters or suffixes in the file name but the same manufacturer, the association relationship of the above example has the case that the same manufacturer is associated with multiple characters or codes.

[0076] In practical application, there can be a case that characters associated by different manufacturers are the same. Since the image type corresponding to a character is related to the semantics of the character, in this case, the image type defined by different manufacturers for the same character is the same. Based on this, if there are multiple association relations matching the same character in the database, the type of the image to be detected can be determined according to any one of the association relations corresponding to the character.

[0077] There can also be a case that codes associated by different manufacturers are the same. Since the image type corresponding to a code defined by a manufacturer is random, for the same code, the image type defined by different manufacturers can be different. Based on this, if there are multiple association relations matching the same code in the database, it is determined whether the image types corresponding to the codes in the multiple association relations are the same; if so, the image types in the multiple association relations are determined as the type of the image to be detected; if not, subsequent steps of determining the type of the image according to the pixel features of the image need to be performed.

[0078] S140, otherwise, the type of the image to be detected is determined according to the pixel features of the image to be detected.

[0079] The database also includes a large number of images containing images of power equipment in a running state, and the type of the image is an infrared image or a visible light image. In this case, the present application analyzes the gray level histograms of a large number of infrared images and visible light images in the database, finds that the gray level histograms of different types of images have differences in gray level distribution, and can further determine the type of the image according to the differences. Specifically, it includes the following steps:

[0080] According to the gray level histograms of each infrared image and the gray level histograms of each visible light image in the database, it is determined that the skewness of the image gray level histogram belongs to a first range, and the kurtosis belongs to a second range.

[0081] The inventors found through analysis of the gray level histograms of a large number of images of the two types in the database that infrared images usually have a higher gray level value in the high temperature region, and their gray level histograms can have obvious peak values at higher gray levels or be biased towards higher gray levels; while the gray level distribution of visible light images is relatively uniform, and their gray level histogram shape is relatively flat or has a relatively uniform distribution in a wider gray level range. Therefore, by way of example, the first range is [0.5, +∞), and the second range is (3, +∞). Correspondingly, when the skewness of an image belongs to the first range or the kurtosis belongs to the second range, the image can be determined as an infrared image; when the skewness is outside the first range and the kurtosis is also outside the second range, the image is a visible light image.

[0082] Therefore, for the to-be-detected image whose type cannot be determined according to the file name, in a feasible design, the type of the to-be-detected image is determined according to the pixel features of the to-be-detected image by the following method:

[0083] A target gray histogram of the to-be-detected image is obtained.

[0084] The type of the to-be-detected image is determined according to the skewness and / or kurtosis of the target gray histogram.

[0085] Considering that the infrared image and the visible light image have differences in the gray distribution, in the case where the type of the image cannot be directly determined according to the file name, the type of the to-be-detected image can be further accurately determined according to the skewness and / or kurtosis of the target gray histogram in the above example.

[0086] In a feasible design, the type of the to-be-detected image is determined according to the skewness and / or kurtosis of the target gray histogram by the following method:

[0087] If the skewness of the target gray histogram is located in a first predetermined range, or the kurtosis of the target gray histogram is located in a second predetermined range, the type of the to-be-detected image is determined as an infrared image.

[0088] Otherwise, the type of the to-be-detected image is determined as a visible light image.

[0089] In the above example, if the skewness of the target gray histogram is not located in the first range, and the kurtosis is not located in the second range, the type of the to-be-detected image can be directly determined as a visible light image.

[0090] The present application finds that, among the red, green and blue colors, the green channel value of the infrared image is relatively low because the infrared light filters the green color most. Therefore, under the condition that the computing resources are allowed or according to actual needs, in order to further accurately determine the type of the to-be-detected image, if the skewness of the target gray histogram is located outside the first range, and the kurtosis of the target gray histogram is located outside the second range, the type of the to-be-detected image can be further accurately determined according to the green channel value of the pixel of the to-be-detected image.

[0091] The present application determines the average value of the green channel value of the visible light image by analyzing the channel value features of the pixels of a large number of infrared images and visible light images in a database, so as to facilitate subsequent determination of the type of the to-be-detected image according to the average value. The specific steps include:

[0092] The first average value is determined by traversing the pixels of the visible light images in the database, and the first average value is the average value of the green channel values of the visible light images in the database.

[0093] For example, in determining the first average value, an average value of the green channel value of each pixel of each visible light image in the database is determined first, and then an average of the average values is obtained to obtain the first average value.

[0094] Therefore, the type of the image to be detected can be determined according to the green channel value of the pixel of the image to be detected in the following manner:

[0095] The second average value is determined by traversing the pixels of the image to be detected, and the second average value is an average of the green channel values of the image to be detected.

[0096] The second average value is compared with the first average value.

[0097] If the second average value is less than the first average value, it is determined that the type of the image to be detected is an infrared image.

[0098] Otherwise, it is determined that the type of the image to be detected is a visible light image; or, the type of the image to be detected is determined according to the file size of the image to be detected.

[0099] In the above example, if the second average value is greater than the first average value, the type of the image to be detected can be directly determined as a visible light image. It is found through analysis of a large amount of image data collected that, in the live detection process, the images are always a pair of infrared images and visible light images, and the file size of the infrared image is basically larger than that of the visible light image.

[0100] Therefore, under the condition that the computing resources are allowed or according to actual needs, the type of the image to be detected can be further accurately determined according to the file size of the image to be detected. In a feasible design, the type of the image to be detected is determined according to the file size of the image to be detected in the following manner:

[0101] Another image to be detected corresponding to the image to be detected is obtained, and the other image to be detected and the image to be detected form a pair of visible light image and infrared image for image registration processing.

[0102] The file size of the image to be detected is compared with the file size of the other image to be detected.

[0103] If the file size of the image to be detected is greater than the file size of the other image to be detected, it is determined that the type of the image to be detected is an infrared image.

[0104] Otherwise, it is determined that the type of the image to be detected is a visible light image.

[0105] The file size is used to indicate the number of bytes of image data.

[0106] Based on the rule that the images taken in the electrification detection process are a pair of infrared images and visible light images, another image to be detected in a pair of visible light images and infrared images can also be determined quickly and efficiently in the following way:

[0107] When the image to be detected is one of the paired infrared image and visible light image, if the type of the image to be detected is an infrared image, the type of the other image to be detected is determined to be a visible light image;

[0108] If the type of the image to be detected is a visible light image, the type of the other image to be detected is determined to be an infrared image.

[0109] Exemplarily, in order to adapt to the new manufacturer's way of distinguishing image types or the change of the original manufacturer's way of distinguishing image types, a new way of distinguishing image types can also be updated by cloud or manually imported, and a new association relationship can be constructed according to the new distinguishing way. Thus, the database is constantly expanded and improved, and it is ensured that the scheme can always accurately identify the image types of different manufacturers, and the ability of the scheme to automatically adapt to the complex distinguishing ways of different manufacturers is further improved.

[0110] Further, when the newly added images in the database reach a certain number, the first average value of the green channel value of the visible light image and the first range to which the skewness of the gray histogram of the infrared image belongs and the second range to which the kurtosis belongs are determined again, so as to further improve the accuracy of determining the image type.

[0111] Based on the above embodiments, as shown in Figure 2 The present application also provides an example of a method for distinguishing infrared images and visible light images, as shown in the following steps:

[0112] Step a, determine whether the main filename of the image to be detected contains the word "infrared", if yes, execute step b, otherwise, execute step c;

[0113] Step b, determine that the type of the image to be detected is an infrared image and output the result;

[0114] Step c, determine whether the extension of the image to be detected matches the extension of the infrared image stored in the database, if yes, execute step b, otherwise, execute step d;

[0115] Step d, determine the gray histogram of the image to be detected, if the skewness of the gray histogram is greater than or equal to 0.5, or the kurtosis is greater than 3, execute step b, otherwise, execute step e;

[0116] Step e, traverse the pixels of the image to be detected, calculate the second average value of the green channel value of the image to be detected, and determine whether the second average value is lower than the first average value of the green channel value of the visible light image in the database, if yes, execute step b, otherwise, execute step f;

[0117] Step f, obtaining another to-be-detected image corresponding to the to-be-detected image, determining whether the file size of the to-be-detected image is greater than the file size of the another to-be-detected image, if yes, executing step b, otherwise, executing step g;

[0118] Step g, determining that the type of the to-be-detected image is visible light and outputting the result.

[0119] The above example synthesizes the results of the primary file name matching judgment, the extension name matching judgment and the pixel feature analysis (gray histogram, color information, picture size) after completing each analysis, and performs the final comprehensive judgment. By weighing the reliability and consistency of each judgment basis, the accurate type of each image is determined. Finally, the judgment result is output, providing accurate image classification information for the subsequent processing flow.

[0120] The database of the embodiments of the present application includes a large number of infrared images and visible light images taken by the inspection equipment of existing manufacturers, which are widely sourced and cover various practical application scenarios and device models. Therefore, the database of the present application has high representativeness and comprehensiveness. On this basis, according to the file name of the to-be-detected image, the corresponding association in the database can be basically found, so as to accurately and efficiently determine whether the to-be-detected image is an infrared image or a visible light image. In the rare case that the type of the image cannot be determined through the file name of the image and the database, the present application also provides a scheme for determining the type of the to-be-detected image according to the pixel features of the to-be-detected image. Therefore, no matter how complex the way of distinguishing the image type of the inspection equipment is or even if it is not distinguished, the present application scheme can automatically adapt and accurately identify the type of the image. It can be seen that, compared with the traditional manual judgment method, the present scheme has excellent adaptive ability and can realize accurate differentiation of the image type without human intervention. This feature greatly improves the data processing efficiency, significantly saves the labor and time cost, and enables the detection work to be more efficient and smooth, thereby providing strong support for large-scale detection work.

[0121] The present application scheme has excellent integrability and can be easily integrated into various inspection equipment, live-line detection mobile terminals and background systems, and can be compatible with different operating systems and hardware platforms to ensure that the scheme can stably run on various common inspection equipment, terminals or systems, and seamlessly cooperate with other live-line detection function modules without affecting the overall performance of the inspection equipment, terminal or system and the normal progress of the detection work. This enables the field detection personnel to conveniently use the scheme to distinguish the type of the to-be-detected image in actual work, optimizes the entire live-line detection work flow, enhances the convenience and reliability of the work, improves the efficiency and quality of the field detection work, and provides great convenience for the detection personnel.

[0122] In an actual live detection scenario, when the solution of the present application is applied to a handheld live detection mobile terminal, after acquiring the infrared image and the visible light image, the solution of the present application is used to quickly and accurately distinguish and process the images, and the type of the image is displayed in the file name using a specific field according to the preset rules. Then, the distinguished image is accurately uploaded to the background system through the live detection function. The background system can accurately determine the type of image based on the preset rules, and efficiently process and analyze the image, so as to achieve accurate flow and effective utilization of image data in the entire live detection workflow. The live detection mobile terminal using this solution can help the members of the power grid operation and maintenance team to realize the real-time processing and uploading of maintenance and experimental data in a digital and wireless manner during routine inspections, which not only reduces the workload of the staff, but also greatly improves the timeliness and accuracy of the data.

[0123] In summary, this application solution effectively reduces the potential for misclassification during manual judgment, efficiently and accurately identifies image types, and provides a more reliable data basis for equipment status assessment. This helps the backend system more accurately judge the equipment's operating status based on the accurate image type and promptly identify potential problems, thereby effectively ensuring the safe and stable operation of the equipment, improving the quality and reliability of detection work, and reducing the risk of equipment failure.

[0124] like Figure 3 As shown, the present application also provides a device for distinguishing infrared images from visible light images during charge detection, comprising:

[0125] An image acquisition module is used to acquire images of the power equipment to be tested in an operating state;

[0126] An image type recognition module is used to determine, based on the file name of the image to be detected, whether the database contains an association relationship that matches the key information of the file name. The association relationship is used to associate the key information with the type of the image, which can be an infrared image or a visible light image.

[0127] The image type recognition module is further configured to, if the database contains an association relationship that matches the key information, determine the type of the image to be detected based on the association relationship;

[0128] Otherwise, the image type recognition module is further configured to determine the type of the image to be detected according to pixel features of the image to be detected.

[0129] In a feasible design, the image type recognition module includes an irregular recognition submodule, which is implemented in the following manner to determine the type of the image to be detected based on the pixel features of the image to be detected:

[0130] Obtain the target grayscale histogram of the image to be detected;

[0131] The type of the image to be detected is determined based on the skewness and / or kurtosis of the target grayscale histogram.

[0132] In a feasible design, the irregularity recognition submodule is implemented in the following manner to determine the type of the image to be detected based on the skewness and / or kurtosis of the target grayscale histogram:

[0133] If the skewness of the target grayscale histogram is within a predetermined first range, or the kurtosis of the target grayscale histogram is within a predetermined second range, determining that the type of the image to be detected is an infrared image;

[0134] Otherwise, it is determined that the type of the image to be detected is a visible light image.

[0135] In a feasible design, if the skewness of the target grayscale histogram is outside the first range and the kurtosis of the target grayscale histogram is outside the second range, the irregular recognition submodule is further used to determine the type of the image to be detected based on the green channel value of the pixel of the image to be detected.

[0136] In a feasible design, the image data statistical analysis module is further configured to determine a first average value by traversing pixels of visible light images in the database, where the first average value is an average value of green channel values ​​of each visible light image in the database.

[0137] In a feasible design, the irregularity recognition submodule is implemented in the following manner to determine the type of the image to be detected based on the green channel value of the pixel of the image to be detected:

[0138] Determine a second average value by traversing pixels of the image to be detected, where the second average value is an average value of each green channel value of the image to be detected;

[0139] comparing the second mean with the first mean;

[0140] If the second average value is less than the first average value, determining that the type of the image to be detected is an infrared image;

[0141] Otherwise, the type of the image to be detected is determined to be a visible light image, or the type of the image to be detected is determined according to the file size of the image to be detected.

[0142] In a feasible design, the irregular recognition submodule is implemented in the following manner to determine the type of the image to be detected based on the file size of the image to be detected:

[0143] Acquire another image to be detected corresponding to the image to be detected, wherein the other image to be detected and the image to be detected form a pair of visible light images and infrared images for image registration processing;

[0144] Comparing the file size of the image to be detected with the file size of another image to be detected;

[0145] If the file size of the image to be detected is larger than the file size of another image to be detected, determining that the type of the image to be detected is an infrared image;

[0146] Otherwise, it is determined that the type of the image to be detected is a visible light image.

[0147] In a feasible design, when the image to be detected is one of a pair of infrared image and visible light image, the irregular recognition submodule is further configured to:

[0148] If the type of the image to be detected is an infrared image, determining that the type of the other image to be detected is a visible light image;

[0149] If the type of the image to be detected is a visible light image, it is determined that the type of the other image to be detected is an infrared image.

[0150] In a feasible design, the image type identification module further includes a file name identification submodule and an extension identification submodule. When the key information is a character or code in the main file name that indicates the type of the image, or when the key information is an extension:

[0151] The file name recognition submodule is used to match the main file name of the image to be detected with the characters or codes used by each manufacturer according to the type of image in the database; if the main file name of the image to be detected contains characters or codes in the database, based on the characters or codes contained in the main file name, determine the association relationship in the database that matches the characters or codes contained in the main file name, and determine the type of the image to be detected based on the association relationship;

[0152] The extension recognition submodule is used to determine whether the database contains an association relationship that matches the extension of the image to be detected if the main file name of the image to be detected does not contain characters or codes in the database and the file name of the image to be detected contains an extension; if the database contains an association relationship that matches the extension of the image to be detected, determine the type of the image to be detected based on the association relationship.

[0153] For other implementations and effects of the above-mentioned device, please refer to the description in the embodiment of the method for distinguishing infrared images from visible light images, which will not be repeated here.

[0154] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this application are merely illustrative and not restrictive, and it should not be assumed that these advantages, strengths, and effects are required of each embodiment of this application. In addition, the specific details disclosed above are merely illustrative and facilitating understanding, and are not restrictive. The above details do not limit this application to necessarily being implemented using the above specific details.

[0155] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0156] The block diagrams of the devices, devices, equipment, and systems involved in this application are intended only as illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0157] It should also be noted that in the apparatus, device, and method of the present application, each component or each step can be decomposed and / or recombined, and such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0158] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0159] The above description has been provided for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application 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, alterations, additions, and sub-combinations thereof.

Claims

1. A method for distinguishing infrared images from visible light images in charge detection, characterized in that: include: Acquire an image to be detected of the power equipment in an operating state, wherein the image to be detected corresponds to another image to be detected, and the other image to be detected and the image to be detected form a pair of visible light images and infrared images for image registration processing; Determine, based on the file name of the image to be detected, whether a database contains an association relationship that matches key information of the file name, wherein the association relationship is used to associate the key information with the type of the image, the type being an infrared image or a visible light image; If the database contains an association relationship that matches the key information, determining the type of the image to be detected based on the association relationship; wherein the key information is a character or code in the main file name of the file name that indicates the type of the image, or the key information is an extension of the file name, and determining whether the database contains an association relationship that matches the key information of the file name based on the file name of the image to be detected, and if the database contains an association relationship that matches the key information, determining the type of the image to be detected based on the association relationship, includes: Matching the main file name of the image to be detected with the characters or codes used by each manufacturer according to the type of image in the database; If the main file name of the image to be detected contains characters or codes in the database, determining, based on the characters or codes contained in the main file name, an association relationship in the database that matches the characters or codes contained in the main file name, and determining the type of the image to be detected based on the association relationship; If the main file name of the image to be detected does not contain the characters or codes in the database, and the file name of the image to be detected contains an extension, determining whether the database contains an association relationship that matches the extension of the image to be detected; If the database contains an association relationship that matches the extension of the image to be detected, determining the type of the image to be detected according to the association relationship; If the database does not contain an association relationship matching the key information, obtaining a target grayscale histogram of the image to be detected; If the skewness of the target grayscale histogram is within a predetermined first range, or the kurtosis of the target grayscale histogram is within a predetermined second range, determining that the type of the image to be detected is an infrared image; If the skewness of the target grayscale histogram is outside a predetermined first range, and the kurtosis of the target grayscale histogram is outside a predetermined second range, the type of the image to be detected is determined according to the file size of the image to be detected.

2. The method according to claim 1, characterized in that The determining the type of the image to be detected according to the file size of the image to be detected includes: Acquire another image to be detected corresponding to the image to be detected; Comparing the file size of the image to be detected with the file size of another image to be detected; If the file size of the image to be detected is larger than the file size of the other image to be detected, determining that the type of the image to be detected is an infrared image; Otherwise, it is determined that the type of the image to be detected is a visible light image.

3. The method according to claim 1, characterized in that The method further includes: if the type of the image to be detected is an infrared image, determining that the type of another image to be detected is a visible light image; If the type of the image to be detected is a visible light image, it is determined that the type of another image to be detected is an infrared image.

4. A device for distinguishing infrared images from visible light images in charge detection, characterized in that: include: An image acquisition module is used to acquire an image to be detected of the power equipment in an operating state, wherein the image to be detected corresponds to another image to be detected, and the other image to be detected and the image to be detected form a pair of visible light images and infrared images for image registration processing; An image type recognition module is used to determine, based on the file name of the image to be detected, whether a database contains an association relationship that matches the key information of the file name, wherein the association relationship is used to associate the key information with the type of the image, and the type is an infrared image or a visible light image; The image type recognition module is further configured to, if the database contains an association relationship that matches the key information, determine the type of the image to be detected based on the association relationship; wherein the key information is a character or code in the main file name of the file name that indicates the type of the image, or the key information is an extension of the file name, and determining, based on the file name of the image to be detected, whether the database contains an association relationship that matches the key information of the file name, and if the database contains an association relationship that matches the key information, determining the type of the image to be detected based on the association relationship, includes: Matching the main file name of the image to be detected with the characters or codes used by each manufacturer according to the type of image in the database; If the main file name of the image to be detected contains characters or codes in the database, determining, based on the characters or codes contained in the main file name, an association relationship in the database that matches the characters or codes contained in the main file name, and determining the type of the image to be detected based on the association relationship; If the main file name of the image to be detected does not contain the characters or codes in the database, and the file name of the image to be detected contains an extension, determining whether the database contains an association relationship that matches the extension of the image to be detected; If the database contains an association relationship that matches the extension of the image to be detected, determining the type of the image to be detected according to the association relationship; If the database does not contain an association relationship matching the key information, the image type recognition module is further configured to obtain a target grayscale histogram of the image to be detected; If the skewness of the target grayscale histogram is within a predetermined first range, or the kurtosis of the target grayscale histogram is within a predetermined second range, determining that the type of the image to be detected is an infrared image; If the skewness of the target grayscale histogram is outside a predetermined first range, and the kurtosis of the target grayscale histogram is outside a predetermined second range, the type of the image to be detected is determined according to the file size of the image to be detected.

Images