A detection method and electronic device

Abstract

The application discloses a detection method and an electronic device. The method comprises the following steps: acquiring at least one image obtained by visible light imaging of a preset point of a to-be-detected device, and parameter data of at least one preset influencing parameter, wherein the preset influencing parameter is a parameter that will affect the visible light imaging of the preset point; correcting the at least one image according to the parameter data of the at least one preset influencing parameter; and finally determining whether fluid leakage occurs at the preset point of the to-be-detected device according to the corrected at least one image. Thus, the application corrects at least one visible light imaging image of the preset point by using the parameter data of the preset influencing parameter, reduces or eliminates negative factors affecting the visible light imaging of the preset point of the to-be-detected device, and on this basis, realizes efficient and accurate fluid leakage detection of the preset point through intelligent detection of the corrected at least one visible light imaging.

Description

Technical Field

[0001] This application belongs to the field of industrial testing technology, and in particular relates to a testing method and electronic equipment. Background Technology

[0002] Oil leakage / seepage in substation oil-filled equipment can cause serious safety problems. The occurrence of oil leakage / seepage not only affects the normal operation of the oil-filled equipment and reduces its service life, but also further affects the safe and stable operation of the power grid. Therefore, oil leakage / seepage detection (e.g., online monitoring) is of great urgency and necessity for ensuring the normal operation of oil-filled equipment and the safe operation of the power grid. Summary of the Invention

[0003] Therefore, this application discloses the following technical solution:

[0004] A detection method, the method comprising:

[0005] Acquire at least one image obtained by visible light imaging of a preset point of the device to be inspected;

[0006] Obtain parameter data for at least one preset influencing parameter, wherein the preset influencing parameter is a parameter that will affect the visible light imaging of the preset point;

[0007] Based on the parameter data of the at least one preset influence parameter, the at least one image is corrected to obtain the at least one corrected image;

[0008] Based on the at least one corrected image, determine whether a fluid leak has occurred at the preset point of the device under test, and obtain a determination result of whether or not a fluid leak has occurred.

[0009] Optionally, acquiring at least one image obtained by visible light imaging of a preset point of the device to be inspected includes:

[0010] Obtain the current first time data and determine that the time represented by the first time data is the preset time;

[0011] Initiate lighting compensation for the preset point and acquire at least one image obtained by visible light imaging of the preset point under the lighting compensation.

[0012] Optionally, obtaining parameter data for at least one preset influencing parameter includes:

[0013] Acquire at least one of the following data for the device under test: micro-meteorological data, second time data, geographical location data, and configuration and size data.

[0014] Optionally, the step of correcting the at least one image based on the parameter data of the at least one preset influence parameter includes:

[0015] In response to the parameter data indicating that the meteorological conditions corresponding to the device under test meet the preset meteorological conditions, the at least one image is subjected to image detail enhancement processing related to the meteorological conditions;

[0016] And / or, in response to the parameter data characterization of the at least one preset influence parameter representing the generation of interference shadows in the location area corresponding to the preset point, the at least one image is subjected to shadow removal processing to at least reduce the interference shadows in the at least one image;

[0017] The interference shadow is distinct from the shadow cast by the device under test in the area corresponding to the preset point due to fluid leakage at the preset point.

[0018] Optionally, the process of removing shadows from the at least one image includes:

[0019] Identify the shadowed regions in the at least one image;

[0020] Based on the parameter data of the at least one preset influence parameter, a shadow prior map matching the interference shadow is constructed;

[0021] Based on the shadow prior map, the shadow regions in the at least one image are corrected to at least partially remove interfering shadows in the at least one image.

[0022] Optionally, constructing a shadow prior map matching the interfering shadow based on the parameter data of the at least one preset influence parameter includes:

[0023] Based on the parameter data of the at least one preset influence parameter, determine the shadow parameter corresponding to the interference shadow;

[0024] Based on the shadow parameters, a shadow prior map matching the interfering shadow is constructed.

[0025] Optionally, determining whether a fluid leak has occurred at the preset point of the device under test based on the at least one corrected image includes:

[0026] The at least one corrected image is compared with a reference image of the preset point, and the fluid leakage at the preset point is determined based on the comparison result; the reference image is an image obtained by visible light imaging of the preset point when no fluid leakage has occurred.

[0027] Alternatively, shadow detection can be performed on at least one of the corrected images, and the detection results can be used to determine whether a fluid leak has occurred at the preset point of the device under test.

[0028] Optionally, determining whether a fluid leak has occurred at the preset point of the device under test based on the at least one corrected image includes:

[0029] The at least one corrected image is compared with the reference image of the preset point to obtain a comparison result; the reference image is the image obtained by visible light imaging of the preset point when no fluid leakage has occurred.

[0030] Shadow detection is performed on at least one of the corrected images to obtain detection results;

[0031] Based on the comparison results and the detection results, it is determined whether a fluid leak has occurred at the preset point of the device to be tested.

[0032] Optionally, the above method also includes:

[0033] In response to the satisfaction of preset update conditions, the reference image of the preset point is updated.

[0034] An electronic device, comprising:

[0035] Memory is used to store computer instruction sets;

[0036] A processor for implementing the detection method described in any of the preceding descriptions by executing a set of instructions stored in memory.

[0037] This application also discloses a storage medium storing at least one set of computer instructions, which, when invoked and executed, are used to implement any of the detection methods disclosed above.

[0038] In summary, the detection method and electronic device disclosed in this application acquire at least one image obtained by visible light imaging of a preset point on the device under test, and parameter data of at least one preset influencing parameter. The preset influencing parameter is a parameter that affects the visible light imaging of the preset point. The at least one image is corrected based on the parameter data of the at least one preset influencing parameter, and finally, the presence or absence of fluid leakage at the preset point on the device under test is determined based on the corrected at least one image. Therefore, this application reduces / eliminates negative factors affecting the visible light imaging of the preset point on the device under test by using the parameter data of the preset influencing parameter. Based on this, through intelligent detection of the corrected at least one visible light imaging image, efficient and accurate detection of fluid leakage at the preset point is achieved. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0040] Figure 1 This is a flowchart illustrating one of the detection methods provided in this application;

[0041] Figure 2 This is the overall detection logic diagram for detecting oil leakage in substation oil-filled equipment provided in this application;

[0042] Figure 3 This is a schematic diagram illustrating the effect of parameters such as latitude and longitude, date / time provided in this application on ground shadows;

[0043] Figure 4 This is an example of a visible light imaging image corresponding to a preset transformer location provided in this application;

[0044] Figure 5 This is the flowchart of the shadow removal process provided in this application;

[0045] Figure 6 This is another flowchart illustrating the detection method provided in this application;

[0046] Figure 7 This is a structural diagram of the electronic device provided in this application. Detailed Implementation

[0047] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0048] This application discloses a detection method and electronic device for detecting fluid leaks / leakage in industrial testing and other fields. The fluid can be a liquid, gas, colloid, or other substance with flow characteristics. Typically, the embodiments of this application mainly use oil leakage detection (such as oil leakage detection in substation oil-filled equipment) as an example for scheme description. The detection method disclosed in this application can be applied to electronic devices. The electronic devices using the method of this application can be, but are not limited to, devices in a variety of general or special computing device environments or configurations, such as: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor devices, etc.

[0049] See Figure 1 The provided flowchart illustrates the detection method of this application, which includes the following processing steps:

[0050] Step 101: Obtain at least one image obtained by visible light imaging of a preset point of the device to be tested.

[0051] Preset points can be one or more potential leak / leak points of the equipment to be tested that may have fluid leakage / leakage, such as the corresponding points on the bushing of the oil-filled equipment in the substation, or the points corresponding to other potential leak / leak points of the oil-filled equipment.

[0052] This application embodiment detects whether a fluid leak / leak has occurred at a preset point of the device to be tested by performing visible light imaging on a preset point and detecting whether a shadow is generated in the area corresponding to the preset point (such as a ground area) based on the obtained visible light imaging image (a fluid leak / leak at the preset point will cause a shadow to be generated in the area corresponding to the preset point). Accordingly, for one or more preset points of the device to be tested, an imaging device for visible light imaging, such as an RGB (Red-Green-Blue) camera, is pre-set.

[0053] The shooting equipment used can be fixed or mobile, such as drones or robots, and there are no restrictions. Specifically, the fixed / mobile shooting equipment will be used to take photos or record videos to image the corresponding locations and their surrounding environment (such as the ground environment corresponding to the preset locations) using visible light.

[0054] When it is necessary to detect fluid leakage / seepage at preset points of the equipment to be tested, at least one image is first obtained by using an imaging device to perform visible light imaging at the preset points of the equipment to be tested, as the data basis for fluid leakage / seepage detection.

[0055] Optionally, in practical applications, visible light imaging images can be acquired at a custom time frequency, such as once every 5 seconds, for one or more preset points (i.e., potential fluid leaks / leaks) of the device to be tested, and the fluid leaks / leaks can be monitored based on the acquired images.

[0056] Step 102: Obtain parameter data for at least one preset influence parameter, wherein the preset influence parameter is a parameter that will affect the visible light imaging of the preset point.

[0057] The applicant's research found that methods for detecting fluid leaks / leakage based on images obtained from visible light imaging are easily affected by external factors, mainly in the following ways:

[0058] 11) If rain, fog, haze, or other conditions occur, the visibility of the visible light shooting equipment and the clarity of the captured image will be affected, resulting in a blurry image, which in turn reduces the accuracy of the image recognition algorithm that relies on pixels.

[0059] 12) When it rains, the surface water and oil stains are similar to the fluids waiting to be detected, which can easily lead to detection errors and cause false alarms or missed alarms for fluid leakage / seepage.

[0060] 13) The shadows on the ground can be easily confused with the shadows cast by oil stains and other fluids waiting to be detected, which can reduce the accuracy of detection and cause false alarms or missed alarms.

[0061] Based on the applicant's above-mentioned research findings, this application embodiment predetermines and sets at least one influencing parameter that will affect the visible light imaging of preset points of the device to be tested.

[0062] Among them, the preset influencing parameters include, but are not limited to, at least one of the following: micro-meteorological data, second time data, geographical location data, configuration and size data, etc., corresponding to the device under test.

[0063] Furthermore, micro-meteorological data includes, but is not limited to, the time of fluid leak detection, wind, cloud, rain, fog, haze, frost, and ice data corresponding to the equipment under test; second time data includes, but is not limited to, non-precise time data such as the season, date, and solar term (e.g., spring equinox / autumn equinox / winter solstice / summer solstice) corresponding to the detection time; geographical location data includes, but is not limited to, the latitude and longitude information corresponding to the location of the equipment under test; and configuration and size data includes, but is not limited to, the shape, size, and connection relationship / structure between different components of the equipment under test, as well as the shape and size of the overall equipment composed of the components.

[0064] During implementation, access configurations for various types of data that affect visible light imaging can be pre-executed. Taking oil leakage detection of oil-filled equipment in substations as an example, this includes, but is not limited to, access configurations for micro-meteorological data, oil-filled equipment configuration / size data, substation latitude and longitude location data, and time data.

[0065] When it is necessary to detect fluid leakage / seepage at a preset point of the device to be tested, in addition to acquiring at least one image obtained by visible light imaging of the preset point, the parameter data of at least one preset influencing parameter corresponding to the device to be tested is also acquired according to the access configuration information of various types of data that affect visible light imaging. Based on the parameter data of these influencing parameters, at least one image corresponding to the preset point is corrected, thereby eliminating factors that may interfere with fluid leakage detection.

[0066] The order in which at least one image corresponding to a preset point is obtained and at least one preset influence parameter data is obtained can be arbitrary and unrestricted. That is, one type of data information can be obtained first and then the other type, or the two types of data information can be obtained simultaneously in a parallel manner.

[0067] Step 103: Correct the at least one image according to the parameter data of the at least one preset influence parameter to obtain the at least one corrected image.

[0068] Specifically, based on at least one of the following data obtained from the current micro-meteorological data, second time data, geographical location data, and configuration and size data of the device under test, at least one of the above-mentioned images corresponding to the preset points of the device under test is corrected.

[0069] Reference Figure 2 The overall detection logic provided, taking the oil leakage detection of oil-filled equipment in Sino-Israeli substations as an example, includes correction processing performed on at least one of the above-mentioned images corresponding to preset points of the equipment to be detected, including but not limited to any one or more of the following:

[0070] 21) In response to the parameter data indicating that the meteorological conditions corresponding to the device under test meet the preset meteorological conditions, at least one image of the preset point of the device under test is subjected to image detail information enhancement processing related to the meteorological conditions.

[0071] The preset weather conditions can be set to, but are not limited to, weather conditions such as rain, fog, and / or haze that affect the visibility of the shooting equipment and the clarity of the captured images.

[0072] Accordingly, based on the acquired micro-meteorological data, the current meteorological conditions of the device under test can be determined, and then it can be determined whether the current meteorological environment of the device under test is experiencing rain, fog and / or haze, which affect the visibility of the shooting device and the clarity of the acquired image. If so, the meteorological conditions are met, and image detail enhancement processing is performed on at least one image of the preset point of the device under test. If not, the meteorological conditions are not met, and there is no need to perform image detail enhancement processing on at least one image of the preset point.

[0073] The image detail enhancement processing performed on at least one image of the preset point of the device under test is a processing related to the current weather conditions of the device under test. Specifically, it may be, but is not limited to, one or more of the following: defogging, deraining, and haze removal processing of the at least one image, depending on the actual weather conditions corresponding to the device under test. By performing deraining / fogging / haze processing on the image, the effect of enhancing image detail and improving image clarity is achieved. This improves the image blurring caused by the impact of rain / fog / haze on the visibility of the shooting device and the clarity of the acquired image in the area where the device under test is located, thereby minimizing or eliminating the interference of these meteorological factors on the visible light imaging of the preset point of the device under test.

[0074] Specifically, rain / fog / haze removal algorithms can be used to process at least one image at a preset location of the detection device, such as defogging based on image enhancement or image restoration algorithms, to improve the clarity of at least one image at the preset location.

[0075] 22) In response to the parameter data characterization of at least one preset influence parameter, an interference shadow is generated in the location area corresponding to the preset point. At least one image of the preset point of the device to be detected is subjected to shadow removal processing to at least reduce the interference shadow in the at least one image.

[0076] The aforementioned interference shadow is distinct from the shadow cast by the device under test in the area corresponding to the preset point due to fluid leakage / seepage at that preset point.

[0077] When detecting fluid leaks at preset locations by performing shadow detection on images obtained from visible light imaging, interfering shadows have a significant impact on the judgment of oil stains and other fluids to be detected, and are easily confused with shadows caused by fluid seepage in image recognition.

[0078] Interference shadows include, but are not limited to, shadows cast by rainwater accumulation in the area corresponding to the preset point of the device under test (such as the corresponding ground area), and shadows cast by light, such as equipment shadows, ground environment shadows, and cloud shadows, which are different from shadows cast by fluid leakage / seepage in the area corresponding to the preset point.

[0079] Specifically, based on prior knowledge of the influence of at least one of the above-mentioned influencing parameters on ground shadows, and based on one or more of the following data: the micro-meteorological data, second time data, geographical location data, and equipment configuration / size data corresponding to the device under test, and also in combination with image information from at least one image of a preset point, it can be determined whether an interfering shadow is generated in the location area corresponding to the preset point, so as to further determine whether the at least one image of the preset point needs to be subjected to deshading processing.

[0080] refer to Figure 3 This provides a schematic diagram illustrating the impact of parameters such as latitude and longitude, date / time, and their influence on ground shadows. Based on prior knowledge of the influence of at least one parameter on ground shadows, the following example provides a simple calculation of interference shadows using data such as the latitude and longitude of the substation and date / time.

[0081] cos h sin A=-cos δ sin H…(1)

[0082]

[0083]

[0084] In the above formulas, A represents the azimuth angle, δ represents the declination, H represents the hour angle, and the longitude λ of the location area is needed when calculating the hour angle H. h represents the solar altitude angle, and φ represents the latitude of the location area of ​​the substation oil filling equipment. The length of the interference shadow is the height of the object that produces the shadow × cot h. The azimuth angle of the shadow is the solar azimuth angle plus 180°.

[0085] The solar altitude angle, a geographical term, refers to the angle between the direction of sunlight incident at a given location on Earth and the horizontal plane. More professionally, it refers to the angle between the sunlight at a given location and a section of the Earth's surface connecting that location to the Earth's center. Solar radiation intensity is greatest when the solar altitude angle is 90°; the greater the degree of sun's oblique incidence on the ground (i.e., the smaller the solar altitude angle), the lower the solar radiation intensity.

[0086] After obtaining the length and azimuth of the interference shadow, information such as the area of ​​the interference shadow can be further calculated based on the length and azimuth of the interference shadow.

[0087] By calculating the relevant parameters of the interference shadow, such as shadow area and shadow length / azimuth, based on the parameter data of at least one of the preset influence parameters, it is determined whether an interference shadow is generated in the location area corresponding to the preset point of the device to be tested.

[0088] If interfering shadows are generated, further reference is made to parameters such as the area, length / azimuth of the interfering shadows, etc., and corresponding deshading processing is performed on at least one image corresponding to the preset point of the detection device to at least reduce the interfering shadows in the at least one image.

[0089] By performing the aforementioned image detail enhancement processing (removal of rain / fog / haze) and / or shadow removal (interference shadow) processing on at least one image corresponding to a preset point of the device to be inspected, the correction of at least one image corresponding to a preset point of the device to be inspected is achieved.

[0090] Step 104: Based on at least one corrected image, determine whether a fluid leak has occurred at a preset point of the device to be tested, and obtain a determination result of whether or not a fluid leak has occurred.

[0091] When determining whether a fluid leak has occurred at a preset point of the device to be tested based on at least one corrected image, optionally, in one embodiment, the at least one corrected image can be compared with a reference image of the preset point, and the fluid leak at the preset point can be determined based on the comparison result.

[0092] The reference image of the preset point is an image obtained by visible light imaging of the preset point under the condition that no fluid leakage / seepage has occurred.

[0093] In this implementation, the preparation of reference images for preset points can be carried out in advance. For each point of the device to be tested that may have fluid leakage / seepage, i.e. each preset point, visible light images are sampled in advance by a fixed or mobile imaging device under the condition that no fluid leakage / seepage has occurred (including image information of the preset point and its location area, such as the ground area). Several (one or more) sampled images of each preset point without fluid leakage / seepage are stored as the reference image of the preset point.

[0094] The collected and stored reference images of preset points do not include interference shadows such as equipment shadows and cloud shadows.

[0095] Subsequently, when detecting fluid leaks at preset points, at least one corrected image of the preset point is compared with a reference image of the preset point. Shadow detection is performed on the corrected image, such as ground shadow detection based on the difference in pixel values ​​of corresponding pixels. This is to detect whether there are ground shadows or other shadows caused by fluid leaks in the corrected image of the preset point. If they are present, it is determined that a fluid leak has occurred at the preset point of the equipment under test, such as an oil leak at the corresponding point of the oil pipeline at the substation. Otherwise, if they are not present, it is determined that no fluid leak has occurred at the preset point of the equipment under test.

[0096] In addition, in other embodiments, without using a reference image, shadow detection can be performed directly on at least one corrected image corresponding to a preset point based on a corresponding shadow detection algorithm (such as a corresponding machine learning algorithm for ground shadow detection), and the fluid leakage at the preset point of the device to be detected can be determined based on the detection result. If a shadow is detected in the at least one image based on the shadow detection algorithm, it is determined that a fluid leakage has occurred at the preset point; otherwise, if no shadow is detected in the at least one image, it is determined that no fluid leakage has occurred at the preset point.

[0097] See Figure 4 The provided visible light imaging image (image after removing interference shadows) corresponding to the preset points of the transformer can be used to detect whether there are shadows in the image by any of the above methods. Based on the detection result that there are shadows, it can be determined that there is oil leakage at the preset points of the transformer. In the case of oil leakage, alarm processing can be further performed.

[0098] In practical applications, the two implementation methods described above can be combined to improve the accuracy and reliability of fluid leakage detection results. In this implementation method, the fluid leakage detection process can be specifically implemented as follows: comparing at least one corrected image corresponding to a preset point with a reference image of the preset point to obtain a comparison result; performing shadow detection on at least one corrected image to obtain a detection result; and determining whether a fluid leak has occurred at the preset point of the device to be tested based on the comparison result and the detection result.

[0099] Specifically, the first probability value of whether a shadow is generated / whether a fluid leak occurs, as represented by the comparison result, can be weighted and calculated with the second probability value of whether a shadow is generated / whether a fluid leak occurs, as represented by the detection result, to obtain the comprehensive probability of whether a shadow is generated / whether a fluid leak occurs at the preset point of the device under test. Based on the comprehensive probability and the preset probability threshold, it can be determined whether a fluid leak occurs at the preset point of the device under test.

[0100] In summary, the method of this application acquires at least one image obtained by visible light imaging of a preset point of the device under test, and parameter data of at least one preset influencing parameter. The preset influencing parameter is a parameter that affects the visible light imaging of the preset point. The at least one image is then corrected based on the parameter data of the at least one preset influencing parameter. Finally, the method determines whether a fluid leak has occurred at the preset point of the device under test based on the corrected at least one image. Therefore, this application reduces / eliminates negative factors affecting the visible light imaging of the preset point of the device under test by using the parameter data of the preset influencing parameter. Based on this, through intelligent detection of the corrected at least one visible light imaging image, efficient and accurate detection of fluid leaks at the preset point is achieved.

[0101] Optionally, in one embodiment, see [link to relevant documentation]. Figure 5 The provided shadow removal flowchart, which describes the process of removing shadows from at least one image corresponding to a preset point on the device to be inspected, can be further implemented as follows:

[0102] Step 501: Identify the shadowed area in at least one image corresponding to the preset point of the device to be detected.

[0103] Specifically, shadow detection can be performed on at least one corrected image corresponding to a preset point of the detection device based on a corresponding shadow detection algorithm, such as a corresponding machine learning algorithm for ground shadow detection, in order to identify the shadow area in the at least one image.

[0104] The shadow areas identified by the shadow detection algorithm here include at least the shadow areas formed by interfering shadows (such as shadows caused by rainwater accumulation, cloud shadows, equipment shadows, etc.).

[0105] Step 502: Based on the parameter data of at least one preset influence parameter, construct a shadow prior map that matches the interference shadow.

[0106] When constructing a priori shadow map that matches the interference shadow, the shadow parameters corresponding to the interference shadow are first determined based on the parameter data of at least one preset influence parameter. Specifically, the shadow parameters such as the length, azimuth, and area of ​​the interference shadow can be determined based on one or more of the following data: micro-meteorological data, second time data, geographical location data, equipment configuration / size data, etc.

[0107] Then, based on the shadow parameters of the interfering shadow, a shadow prior map matching the interfering shadow is constructed.

[0108] The shadow prior map that matches the interfering shadow is the shadow map corresponding to the interfering shadow in at least one of the above images at the preset points.

[0109] Step 503: Based on the constructed shadow prior map, correct the shadow regions in at least one of the above images to at least partially remove interfering shadows in the at least one image.

[0110] See also Figure 2 The processing flow of the shadow removal algorithm in the fluid leakage sorting and detection logic is as follows: after obtaining the shadow prior map that matches the interference shadow, the shadow area can be further marked in at least one image corresponding to the preset point of the device to be detected according to the constructed shadow prior map. Then, based on the marking results, the shadow area in the at least one image is pixel corrected to obtain at least one corrected image corresponding to the preset point.

[0111] This embodiment removes shadows from at least one image corresponding to a preset point of the device to be tested, effectively eliminating interference from a series of shadows such as device shadows, ground environment shadows, cloud shadows, and water shadows on fluid leak detection, making the subsequent fluid leak detection results more accurate and reliable.

[0112] Optionally, in one embodiment, see [link to relevant documentation]. Figure 6 The provided flowchart of the detection method Figure 1 Step 101 of the method shown, which involves obtaining at least one image from a preset point of the device to be inspected using visible light imaging, can be further implemented as follows:

[0113] Step 1011: Obtain the current first-time data;

[0114] Step 1012: Determine whether the time represented by the first time data is the preset time. If so, proceed to step 1013.

[0115] Step 1013: Start the light compensation for the preset point and acquire at least one image of the preset point obtained by visible light imaging under the light compensation.

[0116] In this embodiment, when it is necessary to obtain at least one image of a preset point of the device under test by visible light imaging, the current first time data is first obtained, and it is determined whether the time represented by the first time data is a preset time. If it is a preset time, then the light compensation of the preset point of the device under test is activated, and at least one image of the preset point is obtained by visible light imaging under the light compensation. Otherwise, if the time represented by the first time data is not a preset time, then the light compensation of the preset point of the device under test is not activated, and at least one image of the preset point of the device under test is directly obtained by visible light imaging.

[0117] The first-time data specifically refers to the current hour / minute / second and other fine-grained time data. The preset time can be a pre-set period of insufficient light or low illumination (such as the corresponding period of night or early morning), or a period of time determined by combining meteorological information, weather forecast information, etc., in which rain / fog / haze will affect the visibility of the shooting equipment and the clarity of the captured images.

[0118] This embodiment determines whether to activate supplementary lighting based on first-time data and performs light compensation on the visible light imaging of the shooting device for a preset time, so as to minimize the impact of low light or special weather conditions such as rain / fog / haze on the visible light imaging of the shooting device.

[0119] Optionally, in an embodiment where fluid leakage at a preset point is determined by comparing at least one corrected image corresponding to a preset point of the device under test with a reference image of the preset point, the following processing may also be included:

[0120] In response to the satisfaction of preset update conditions, the reference image of the preset point is updated.

[0121] The preset update conditions can be set to any one or more of the following:

[0122] Condition 1: The time elapsed since the last update of the reference image of the preset point of the device to be tested reaches the set time.

[0123] Condition 2: The change in the environment at the location of the device under test reaches the change threshold.

[0124] For example, the change in the ground environment where the equipment to be tested is located due to plant growth, withering and / or the addition or reduction of pebbles reaches the change threshold.

[0125] During implementation, timing and / or image detection and recognition methods can be used to determine whether the reference image of the preset point of the device under test meets the corresponding update conditions mentioned above. If it does, the reference image of the preset point of the device under test is updated. Specifically, visible light imaging images of the preset point of the device under test are re-acquired under the condition that no fluid leakage has occurred, and the reference image of the preset point is updated with the re-acquired image.

[0126] This embodiment determines whether the reference image of the preset point of the device to be tested meets the update conditions, and updates the reference image of the preset point in a timely manner when the update conditions are met. This ensures that the image information of the reference image is consistent with the environmental information of the area corresponding to the preset point of the device to be tested, thereby ensuring the effectiveness of the subsequent fluid leakage detection results based on the reference image.

[0127] This application also discloses an electronic device, which may be, but is not limited to, a device in a variety of general or special computing device environments or configurations, such as: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor devices, etc.

[0128] The composition and structure of electronic devices, such as Figure 7 As shown, it includes at least:

[0129] Memory 10 is used to store the computer instruction set;

[0130] Computer instruction sets can be implemented in the form of computer programs.

[0131] The processor 20 is configured to implement the detection method disclosed in any of the above method embodiments by executing a set of computer instructions.

[0132] The processor 20 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices.

[0133] Electronic devices have a display device and / or have a display interface and can connect to an external display device.

[0134] Optionally, the electronic device may also include a camera assembly, and / or be connected to an external camera assembly.

[0135] In addition to these components, electronic devices may also include communication interfaces, communication buses, and other parts. Memory, processor, and communication interface communicate with each other through the communication bus.

[0136] Communication interfaces are used for communication between electronic devices and other devices. Communication buses can be Peripheral Component Interconnect (PCI) buses or Extended Industry Standard Architecture (EISA) buses, and can be categorized into address buses, data buses, control buses, etc.

[0137] In addition, this application also discloses a storage medium storing at least one set of computer instructions, which, when invoked and executed, are used to implement the detection method disclosed in any of the above embodiments.

[0138] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0139] For ease of description, the above systems or devices are described separately as various modules or units based on their functions. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware components.

[0140] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0141] Finally, it should be noted that in this document, relational terms such as first, second, third, and fourth are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0142] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A detection method, the method comprising: Acquire at least one image obtained by visible light imaging of a preset point of the device to be inspected; Obtain parameter data of preset influencing parameters, which are parameters that will affect the visible light imaging of the preset point. The preset influencing parameters include: micro-meteorological data, second time data, geographical location data, and configuration and size data corresponding to the device to be tested. Based on the parameter data of the preset influence parameters, at least one image is corrected to obtain at least one corrected image; this includes: responding to the parameter data of the preset influence parameters indicating that the meteorological conditions corresponding to the device under test meet preset meteorological conditions, performing image detail enhancement processing on the at least one image related to the meteorological conditions; calculating interference shadow-related parameters based on the parameter data of the preset influence parameters to determine whether interference shadows are generated in the location area corresponding to the preset point of the device under test; if interference shadows are generated, referring to the parameter data of the interference shadows, performing shadow removal processing on at least one image after image detail enhancement processing to at least reduce interference shadows in at least one image; wherein, the interference shadows are different from the shadows generated in the location area corresponding to the preset point by the device under test due to fluid leakage at the preset point; The at least one corrected image is compared with a reference image of the preset point to obtain a comparison result; the reference image is a visible light image obtained by imaging the preset point when no fluid leakage has occurred; shadow detection is performed on the at least one corrected image to detect whether there is a shadow caused by fluid leakage in the at least one corrected image of the preset point, and a detection result is obtained; based on the comparison result and the detection result, it is determined whether fluid leakage has occurred at the preset point of the device to be tested, and a determination result of whether fluid leakage has occurred is obtained.

2. The method according to claim 1, wherein acquiring at least one image obtained by visible light imaging of a preset point of the device to be inspected comprises: Obtain the current first time data and determine that the time represented by the first time data is the preset time; Initiate lighting compensation for the preset point and acquire at least one image obtained by visible light imaging of the preset point under the lighting compensation.

3. The method according to claim 1, wherein the shadow removal processing of at least one image after image detail enhancement processing includes: Identify shadow regions in at least one image after image detail enhancement processing; Based on the parameter data of the at least one preset influence parameter, a shadow prior map matching the interference shadow is constructed; Based on the shadow prior map, the shadow regions in at least one image after image detail enhancement are corrected to at least partially remove interfering shadows in at least one image after image detail enhancement.

4. The method according to claim 3, wherein constructing a shadow prior map matching the interfering shadow based on the parameter data of the at least one preset influence parameter includes: Based on the parameter data of the at least one preset influence parameter, determine the shadow parameter corresponding to the interference shadow; Based on the shadow parameters, a shadow prior map matching the interfering shadow is constructed.

5. The method according to claim 1, further comprising: In response to the satisfaction of preset update conditions, the reference image of the preset point is updated.

6. An electronic device, comprising: Memory is used to store computer instruction sets; A processor for implementing the detection method as described in any one of claims 1-5 by executing a set of instructions stored in memory.

Images