Substation meter low-order defect identification method, system and equipment and storage medium

Abstract

The invention relates to the technical field of image processing, and discloses a substation meter low-order defect identification method, system and device and a storage medium. The method comprises the following steps: acquiring a dial region type, a dial region detection frame, a scale region mask and an indication region mask of a transformer substation meter image through an improved Yolov9-m meter identification model; cutting the transformer substation meter image according to the dial plate area detection frame to obtain a dial plate area image, and correcting the dial plate area image, the scale area mask and the indication area mask according to a dial plate area correction template; and for different dial plate region types, calculating the total area of the scale region based on the correction scale region mask, calculating the area of the indication region based on the correction indication region mask, judging whether the dial plate is in a low-level defect state according to the total area of the scale region and the area of the indication region, if so, giving an alarm for the low-level defect state, and if not, returning to the next step. According to the invention, the low-level defect state of the transformer station meter can be rapidly identified.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, system, device and storage medium for identifying low-level defects of transformer substation meters. Background Art

[0002] Meters such as oil level gauges, pressure gauges, and lightning arrester detectors are important instruments and equipment in substations, providing a powerful monitoring method to ensure the normal operation of power grid equipment. When the oil level gauge reading is low, the insulation performance of the transformer or other oil-immersed equipment will be reduced, the cooling efficiency will be reduced, and the aging of the equipment will be accelerated; when the pressure gauge reading is low, the insulation performance of the gas-insulated equipment will be reduced, the operating efficiency will be reduced, and the equipment risk will increase; when the lightning arrester detector reading is low, the lightning protection performance of the lightning arrester will be reduced, the power stability will be reduced, and the safety hazards will increase. The existing substation meter identification method can usually only obtain the pointer reading of the meter, and then manually determine whether the meter is in a low-level defect state. When the meter scale cannot be identified or for meters without pointers such as oil level gauges, the existing technology is often unable to determine whether the meter is in a low-level defect state. Summary of the invention

[0003] In order to solve the problem that the prior art cannot identify whether a meter with unclear scale or no pointer is in a low-level defect state, the present application provides a substation meter low-level defect identification method, system, device and storage medium.

[0004] In a first aspect, the present application provides a method for identifying low-level defects of a substation meter, comprising: Obtain a substation meter image of a substation meter to be identified, input the substation meter image into an improved Yolov9-m meter recognition model, perform dial area detection processing and instance segmentation of the scale area and the indication area on the substation meter image through the improved Yolov9-m meter recognition model, and obtain a dial area type, a dial area detection frame, a scale area mask, and an indication area mask in the substation meter image; the dial area type is any one of a rectangular dial, a circular dial, and a square dial; The substation meter image is cropped according to the dial area detection frame to obtain a dial area image, a dial area correction template of the dial area image is obtained from a plurality of dial area standard templates, and the dial area image, the scale area mask and the indication area mask are corrected according to the dial area correction template to obtain a corrected dial area image, a corrected scale area mask and a corrected indication area mask; For different dial area types, the total area of ​​the scale area is calculated based on the correction scale area mask, and the area of ​​the indication area is calculated based on the correction indication area mask. According to the total area of ​​the scale area and the area of ​​the indication area, it is judged whether the substation meter to be identified is in a low-level defect state. If so, an alarm is issued that the substation meter to be identified is in a low-level defect state.

[0005] In an optional embodiment, the improved Yolov9-m meter recognition model includes a backbone network, an improved feature pyramid network and a head network, the improved feature pyramid network includes a spatial attention mechanism module and a fusion module, and the head network includes a classification regression processing module, a region of interest alignment module, and an instance segmentation module; The method of performing dial area detection processing, scale area and indication area instance segmentation on the substation meter image by using the improved Yolov9-m meter recognition model includes: Extracting features from the substation meter image through the backbone network to obtain a plurality of initial feature maps; Inputting a plurality of the initial feature maps into the improved feature pyramid network, processing the plurality of the initial feature maps through the spatial attention mechanism module to obtain a plurality of spatial attention feature maps, and fusing the plurality of the spatial attention feature maps through the fusion module to obtain a fused feature map; The fusion feature map is classified and regressed by the classification and regression processing module to obtain the dial area type and the dial area detection frame in the substation meter image; Obtaining a region of interest feature map of a preset size according to the image area corresponding to the dial area detection frame through the region of interest alignment module; The instance segmentation module is used to perform classification, regression and instance segmentation processing on the feature map of the region of interest, thereby obtaining the scale region mask and the indication region mask respectively.

[0006] In an optional implementation, the initial feature map includes a low-level high-resolution feature map and a high-level low-resolution feature map, and processing each of the initial feature maps by the spatial attention mechanism module includes: Perform channel maximum pooling on the low-level high-resolution feature map to obtain a single-channel maximum value feature map; Perform channel average pooling on the low-level high-resolution feature map to obtain a single-channel mean feature map; Perform channel concatenation on the single-channel maximum value feature map and the single-channel mean feature map to obtain a two-channel feature map, and perform a 1x1 convolution operation on the two-channel feature map to obtain a single-channel feature map; Processing the single-channel feature map through an activation function to obtain a spatial weighted feature map; The high-level low-resolution feature map is convolved and up-sampled by 1x1 to generate an up-sampled feature map with the same resolution as the low-level high-resolution feature map; The upsampled feature map is multiplied by the spatial weighted feature map to obtain the spatial attention feature map.

[0007] In an optional implementation, for different dial area types, calculating the total area of ​​the scale area based on the corrected scale area mask, and calculating the area of ​​the indication area based on the corrected indication area mask, includes: If the dial area type is the rectangular dial, four scale area edge points are extracted according to the corrected scale area mask; and the total scale area area corresponding to the rectangular dial is calculated according to the four scale area edge points; Four indication region edge points are extracted according to the corrected indication region mask, and the indication region area is calculated according to the four indication region edge points.

[0008] In an optional implementation, for different dial area types, calculating the total area of ​​the scale area based on the corrected scale area mask, and calculating the area of ​​the indication area based on the corrected indication area mask, includes: If the dial area type is the circular dial or the square dial, extract multiple scale area edge points according to the corrected scale area mask, and determine two points with the largest gradient change among the multiple scale area edge points as the scale start point and the scale end point; A target point is selected from the remaining edge points of the scale area, and the center and radius of the circle where the correction scale area mask is located are calculated according to the target point, the scale starting point and the scale end point, wherein the remaining edge point of the scale area is the coordinate of the plurality of edge points of the scale area excluding the scale starting point and the scale end point; Calculate the total area of ​​the scale region according to the target point, the scale starting point, the scale end point, the center of the circle and the radius; Extracting a plurality of indication area edge points according to the corrected indication area mask, and calculating the distance between each of the indication area edge points and each of the scale area edge points; The shortest distance among the multiple distances is determined, the edge point of the scale area corresponding to the shortest distance is used as the pointer indication position, and the area of ​​the indication area is calculated according to the pointer indication position.

[0009] In an optional implementation, calculating the total area of ​​the scale region according to the target point, the scale starting point, the scale end point, the center of the circle and the radius includes: If the dial area type is the circular dial, the total area of ​​the scale area of ​​the circular dial is calculated according to the following formula 1; Formula 1: ; If the dial area type is the square dial, the total area of ​​the scale area of ​​the square dial is calculated according to the following formula 2; Formula 2: ; in,

[0010]

[0011] The starting point of the scale is , the end point of the scale is , the target point is , the center of the circle is , the radius is r, and the total area of ​​the scale area is The area of ​​the circle where the scale area mask of the circular dial is located is cut by the line connecting the scale starting point and the scale end point. The area of ​​the circle where the square dial scale area mask is located is cut by the line connecting the scale start point and the scale end point. ; The calculating the area of ​​the indicated region according to the position indicated by the pointer comprises: The area of ​​the indicated region is calculated according to the following formula 3 and formula 4; Formula 3:

[0012] Formula 4:

[0013] The pointer indicates the position , the indicated area is .

[0014] In an optional implementation manner, the step of acquiring a dial area correction template of the dial area image from a plurality of dial area standard templates includes: Get the standard templates of the dial area corresponding to different dial area types; Determine, by using a matching algorithm, from a plurality of the dial area standard templates, a dial area standard template having the greatest similarity to the dial area image as the dial area correction template; The correcting process of the dial area image, the scale area mask and the indication area mask according to the dial area correction template includes: Calculating a homography matrix between the dial area image and the dial area correction template; Correcting the dial area image, the scale area mask and the indication area mask respectively by using the homography matrix; The step of judging whether the substation meter to be identified is in a low-level defect state according to the total area of ​​the scale area and the area of ​​the indication area includes: Calculating the area ratio between the area of ​​the indication region and the total area of ​​the scale region; If the area ratio is greater than or equal to a preset area ratio threshold, it is determined that the substation meter to be identified is in a normal state; If the area ratio is less than the preset area ratio threshold, it is determined that the substation meter to be identified is in a low-level defect state.

[0015] In a second aspect, the present application provides a substation meter low-level defect identification system, comprising: A detection and segmentation module, used for acquiring a substation meter image of a substation meter to be identified, inputting the substation meter image into an improved Yolov9-m meter recognition model, performing dial area detection processing and instance segmentation of a scale area and an indication area on the substation meter image through the improved Yolov9-m meter recognition model, and obtaining a dial area type, a dial area detection frame, a scale area mask and an indication area mask in the substation meter image; the dial area type is any one of a rectangular dial, a circular dial and a square dial; A matching correction module, used for cropping the substation meter image according to the dial area detection frame to obtain a dial area image, obtaining a dial area correction template of the dial area image from a plurality of dial area standard templates, and performing correction processing on the dial area image, the scale area mask and the indication area mask according to the dial area correction template to obtain a corrected dial area image, a corrected scale area mask and a corrected indication area mask; The low-level defect recognition module is used to calculate the total area of ​​the scale area based on the correction scale area mask, calculate the area of ​​the indication area based on the correction indication area mask for different dial area types, and judge whether the substation meter to be identified is in a low-level defect state according to the total area of ​​the scale area and the area of ​​the indication area. If so, an alarm is issued that the substation meter to be identified is in a low-level defect state.

[0016] In a third aspect, the present application provides a computer device, comprising a processor and a memory, wherein the memory stores a computer program, and the processor is used to execute the computer program to implement the substation meter low-level defect identification method described in the first aspect.

[0017] In a fourth aspect, the present application provides a computer storage medium storing a computer program, which, when executed on a processor, implements the method for identifying low-level defects of a substation meter according to the first aspect.

[0018] The embodiments of the present application have the following beneficial effects: The method for identifying low-level defects of substation meters provided in the present application detects and instance-segments the substation meter image to be identified through the improved Yolov9-m meter identification model, obtains the dial area type, dial area detection frame, scale area mask and indication area mask, then crops the substation meter image to obtain the dial area image, and matches and corrects the dial area image, scale area mask and indication area mask through the matching algorithm and correction algorithm to obtain the corrected dial area image, corrected scale area mask and corrected indication area mask, then calculates the total area of ​​the scale area and the area of ​​the indication area, determines whether the substation meter is in a low-level defect state according to the total area of ​​the scale area and the area of ​​the indication area, and alarms if the substation meter to be identified is in a low-level defect state. The present application can quickly identify the low-level defect state of substation meters and eliminate safety hazards in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present application and should not be regarded as limiting the scope of protection of the present application. For ordinary technicians in this field, other related drawings can also be obtained based on these drawings without creative work.

[0020] Figure 1 A schematic diagram of a flow chart of a method for identifying low-level defects of a substation meter provided in this embodiment is shown; Figure 2 A schematic diagram of the structure of an improved Yolov9-m recognition model provided in this embodiment is shown; Figure 3 A schematic diagram of the structure of a spatial attention mechanism module provided in this embodiment is shown; Figure 4 A schematic diagram of the structure of a rectangular dial provided by this embodiment is shown; Figure 5 A schematic diagram of the structure of a circular dial provided by this embodiment is shown; Figure 6 A schematic structural diagram of a square dial provided in this embodiment is shown; Figure 7 A schematic diagram of the framework structure of a substation meter low-level defect identification system provided by this embodiment is shown. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0022] The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0023] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present application, are intended only to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing items or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations of the foregoing items.

[0024] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0025] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.

[0026] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0027] Reference Figure 1 , Figure 1 A schematic flow chart of a method for identifying low-level defects of a substation meter provided in this embodiment, the method can quickly identify the meter and determine the current state of the meter, the method comprising: S101. Obtain a substation meter image of a substation meter to be identified, input the substation meter image into an improved Yolov9-m meter recognition model, and perform dial area detection processing and instance segmentation of the scale area and the indication area on the substation meter image through the improved Yolov9-m meter recognition model to obtain a dial area type, a dial area detection frame, a scale area mask, and an indication area mask in the substation meter image; the dial area type is any one of a rectangular dial, a circular dial, and a square dial.

[0028] In scenes such as substations, oil level gauges, pressure gauges, and lightning arrester detectors are usually installed at higher positions and are often unable to be inspected through normal observation methods. Therefore, drone aerial photography is usually used to obtain images of various meters in the meter station. After obtaining the images of each meter, the existing technology needs to process the image if the image is not clear enough. After the processing is completed, it is manually determined whether the meter reading is normal or in a low-level defect state. The whole process is very cumbersome. Moreover, some meters, such as rectangular oil level gauges, usually have no pointers, only oil level displays. Existing pointer recognition methods often cannot recognize this type of meter. For meters with pointers, if the scale is blurred, it is difficult for existing technologies to recognize the accurate reading of the meter, and it is also impossible to determine whether the meter is in a low-level defect state.

[0029] In order to improve the recognition efficiency of meters, this embodiment provides a method for identifying low-level defects of substation meters. After acquiring images of each meter, a series of processes of meter image processing and meter low-level defect recognition are completed through a meter recognition model.

[0030] The meter recognition model can select the improved Yolov9-m recognition model. In order to make the model more suitable for meter recognition, the target detection module and the instance segmentation module can be embedded in the model to simultaneously perform dual-type tasks of target detection and instance segmentation.

[0031] For example, the acquired images of the substation meters to be identified usually include other irrelevant factors, such as external environmental factors and images of equipment such as oil tanks and lightning arresters. These factors may interfere with the identification of the meters. Therefore, the dial area type can be first determined through the target detection module. The dial area types usually include circular dials, square dials and rectangular dials, as well as dial area detection frames corresponding to the dial area types. The dial area detection frames are used to crop the meter images in the substation meters to be identified to obtain the dial area images.

[0032] Then, the dial area image can be input into the instance segmentation module, and other dial area features can be obtained through the instance segmentation module, such as the scale area type and the scale area mask. The scale area type generally includes arc and rectangular shapes, as well as the indication area type and the indication area mask. The indication area type generally includes a pointer and an oil body.

[0033] S102. Crop the substation meter image according to the dial area detection frame to obtain a dial area image, obtain a dial area correction template of the dial area image from multiple dial area standard templates, and perform correction processing on the dial area image, the scale area mask and the indication area mask according to the dial area correction template to obtain a corrected dial area image, a corrected scale area mask and a corrected indication area mask.

[0034] The dial area image is obtained by cropping the substation meter image through the dial area detection frame. Since the image may be distorted during the aerial photography process, the dial area image needs to be corrected after it is obtained. Usually, multiple standard templates can be prepared for each type of dial, and then a similarity algorithm is used to select one of the standard templates as the dial area correction template to correct the dial area image.

[0035] After selecting the dial area correction template, the dial area image, the scale area mask and the indication area mask are corrected respectively by the corresponding correction algorithm to obtain the corrected dial area image, the corrected scale area mask and the corrected indication area mask to reduce the error of meter recognition.

[0036] S103. For different dial area types, the total area of ​​the scale area is calculated based on the correction scale area mask, and the area of ​​the indication area is calculated based on the correction indication area mask. According to the total area of ​​the scale area and the area of ​​the indication area, it is judged whether the substation meter to be identified is in a low-level defect state. If so, an alarm is issued that the substation meter to be identified is in a low-level defect state.

[0037] Since there are many types of dial areas, it is necessary to select different calculation methods to calculate the total area of ​​the scale area and the area of ​​the indication area according to different dial area types, and then judge whether the substation meter to be identified is in a low-level defect state based on the total area of ​​the scale area and the area of ​​the indication area, and alarm if the substation meter to be identified is in a low-level defect state.

[0038] This embodiment detects and instance-segments the substation meter image to be identified through an improved Yolov9-m meter recognition model, obtains the dial area type, dial area detection frame, scale area mask and indication area mask, then crops the substation meter image to obtain the dial area image, and matches and corrects the dial area image, scale area mask and indication area mask through a matching algorithm and a correction algorithm to obtain a corrected dial area image, a corrected scale area mask and a corrected indication area mask, then calculates the total area of ​​the scale area and the area of ​​the indication area, determines whether the substation meter is in a low-level defect state based on the total area of ​​the scale area and the area of ​​the indication area, and alarms if the substation meter to be identified is in a low-level defect state. This application can quickly identify the low-level defect state of substation meters and eliminate safety hazards in a timely manner.

[0039] In one embodiment, the improved Yolov9-m meter recognition model includes a backbone network, an improved feature pyramid network and a head network, wherein the improved feature pyramid network includes a spatial attention mechanism module and a fusion module, and the head network includes a classification regression processing module, an area of ​​interest alignment module, and an instance segmentation module; The method of performing dial area detection processing, scale area and indication area instance segmentation on the substation meter image by using the improved Yolov9-m meter recognition model includes: Extracting features from the substation meter image through the backbone network to obtain a plurality of initial feature maps; Inputting a plurality of the initial feature maps into the improved feature pyramid network, processing the plurality of the initial feature maps through the spatial attention mechanism module to obtain a plurality of spatial attention feature maps, and fusing the plurality of the spatial attention feature maps through the fusion module to obtain a fused feature map; The fusion feature map is classified and regressed by the classification and regression processing module to obtain the dial area type and the dial area detection frame in the substation meter image; Obtaining a region of interest feature map of a preset size according to the image area corresponding to the dial area detection frame through the region of interest alignment module; The instance segmentation module is used to perform classification, regression and instance segmentation processing on the feature map of the region of interest, thereby obtaining the scale region mask and the indication region mask respectively.

[0040] Reference Figure 2 , Figure 2 A schematic diagram of the structure of an improved Yolov9-m recognition model provided in this embodiment.

[0041] Generally speaking, substation meter identification usually starts with dial area identification, cropping the dial area, and then further identifying the scale area and pointer area based on the dial area image.

[0042] In order to quickly obtain the dial area, meter scale area and pointer area, this embodiment embeds strategies such as dial area recognition and scale area and pointer area recognition into the Yolov9-m algorithm network structure, and introduces a spatial attention mechanism module (SAM), which can accurately and quickly extract the dial area type and rectangular frame, scale area type and scale area mask, and indicator area type and scale area mask.

[0043] First, the substation meter image passes through the backbone network constructed by the RepNSCPELAN4 module. The backbone network includes three backbone network layers (Conv3 ~Conv5), and three layers of initial feature maps (F3~F5) are obtained and input into the improved feature pyramid network PA-SAM-FPN. Then, the initial feature map F5 and the initial feature map F4 are connected through the spatial attention mechanism module (SAM) to generate the spatial attention feature map SAF4, and the spatial attention feature map SAF4 is cascaded with the initial feature map F4 to generate the initial fusion feature map ~P4; the initial fusion feature map ~P4 and the initial feature map F3 are connected through the spatial attention mechanism module to generate the spatial attention feature map SAF3, and the spatial attention feature map SAF3 is cascaded with the initial feature map F3 to generate the fusion feature map P3. The fused feature map P3 is passed through the convolution layer to generate a convolution feature map PAF4 with the same resolution as the fused feature map P4; the convolution feature map PAF4 is cascaded with the initial fused feature map ~P4 to generate a fused feature map P4; the fused feature map P4 is passed through the convolution layer to generate a convolution feature map PAF5 with the same resolution as F5; the convolution feature map PAF5 is cascaded with F5 to generate a fused feature map P5, thus obtaining a feature map fusion process from top to bottom and bottom to top (P3~P5). Finally, the fused feature maps P3~P5 are classified and regressed respectively through the decoupling head to obtain the region of interest detection result (the region of interest detection result includes the dial type and the dial area detection frame, and the dial area detection frame can be a rectangular frame); the region of interest feature map is obtained using the region of interest rectangular frame, and the region of interest feature map of a preset size is obtained according to the image area corresponding to the dial area detection frame through the region of interest alignment module. The region of interest alignment module can be a ROI Align operator, which generates a ROI Align feature map of uniform size; the ROI Align feature map is classified, regressed, and segmented through a decoupling head to complete instance segmentation of the scale area and the indicator area, thereby obtaining the scale area type and the scale area mask, and the indicator area type and the scale area mask.

[0044] Based on the target detection in the dial area, this embodiment generates a feature map of the region of interest with uniform size through the region of interest alignment module, thereby quickly completing the instance segmentation of the scale area and the indicator area.

[0045] Reference Figure 3 , Figure 3 A schematic diagram of the structure of a spatial attention mechanism module provided for this embodiment.

[0046] The initial feature map includes a low-level high-resolution feature map and a high-level low-resolution feature map. First, the low-level high-resolution feature map is subjected to channel maximum pooling and channel average pooling respectively to obtain a single-channel maximum feature map and a single-channel mean feature map respectively; then, the single-channel maximum feature map and the single-channel mean feature map are concatenated through channels to obtain a two-channel feature map, which is then subjected to a 1x1 convolution operation to obtain a single-channel feature map, which is then subjected to an activation function to obtain a spatial weighted feature map; then, the high-level low-resolution feature map is subjected to a 1x1 convolution and up-sampled to generate an up-sampled feature map with the same resolution as the low-level high-resolution feature map; finally, the up-sampled feature map is multiplied by the spatial weighted feature map to obtain a spatial attention feature map.

[0047] This embodiment improves the Yolov9-m algorithm network and uses the spatial attention mechanism module to help the model focus on the key areas in the image, giving the high-level feature map detailed attention to the low-level feature map, and also integrating the detail information of the low-level feature map, thereby improving the overall feature representation capability, thereby effectively improving the accuracy of substation meter target detection and instance segmentation.

[0048] In one embodiment, when the dial area detection and the instance segmentation of the scale area and the indication area are performed by the improved Yolov9-m meter recognition model, if the dial area target is not detected, the next image is recognized, and the meter result storage module is called to record that the image has no dial area. If there is a dial area target, no scale area mask, and no indication area mask, the next image is recognized, and the meter result storage module is called to record the dial type and rectangular frame coordinates of the image.

[0049] If there is a dial area target, a scale area mask, and no indication area mask, the next image is identified, and the meter result storage module is called to record the dial type and rectangular frame coordinates, scale area type, and scale area mask image of the image. If there is a dial area target, no scale area mask, and an indication area mask, the next image is identified, and the meter result storage module is called to record the dial type and rectangular frame coordinates, indication area type, and mask image of the image.

[0050] If there is a dial area target, a scale area mask, and an indication area mask, the dial area matching link is entered, and the meter result storage module is called to record the dial type and rectangular frame coordinates, the scale area type and scale area mask, and the indication area type and indication area mask of the image.

[0051] In this embodiment, when the dial area detection and scale area and indication area instance segmentation are performed on the meter image to be identified through the improved Yolov9-m meter recognition model, when one of the meter images to be identified does not contain all the features to be identified at the same time, the detection and segmentation results of multiple images can be combined to obtain accurate results, thereby improving the accuracy of meter recognition.

[0052] In one embodiment, the step of acquiring a dial area correction template of the dial area image from a plurality of dial area standard templates includes: Get the standard templates of the dial area corresponding to different dial area types; Determine, by using a matching algorithm, from a plurality of the dial area standard templates, a dial area standard template having the greatest similarity to the dial area image as the dial area correction template; The correcting process of the dial area image, the scale area mask and the indication area mask according to the dial area correction template includes: Calculating a homography matrix between the dial area image and the dial area correction template; The dial area image, the scale area mask and the indication area mask are corrected respectively by the homography matrix.

[0053] According to the dial area type, the corresponding standard template is selected. For example, if the dial area type is circular, the standard template of the circle is used to traverse and calculate the similarity between the standard template of the corresponding dial area type and the dial area image, and the standard template of the dial area type with the greatest similarity is found as the correction template of the dial area. The matching algorithm can be a Perceptual Hash algorithm, i.e., a phash algorithm. The phash algorithm is a method for calculating similar images and can be used to detect the repetitiveness of images. If the contents of two images are similar, their Perceptual Hash values ​​will also be similar.

[0054] After determining the dial area correction template with the greatest similarity to the dial area image, the ORB key points of the dial area image and the ORB key points of the dial area correction template are calculated respectively using the ORB key point algorithm based on the dial area image and the dial area correction template, and the homography matrix between the ORB key points of the dial area image and the ORB key points of the dial area correction template is further calculated.

[0055] Finally, the corrected dial area image is obtained by multiplying the homography matrix with the dial area image. At the same time, the corrected scale area mask and the corrected indication area mask are obtained by multiplying the homography matrix with the scale area mask and the indication area mask.

[0056] After obtaining the dial area image, dial area type, correction scale area mask and correction indication area mask, the total scale area area and indication area area can be calculated. Since the calculation methods corresponding to different dial area types are different, this application is classified as follows according to different dial area types.

[0057] This embodiment provides schematic structural diagrams of three different dials.

[0058] Figure 4 A schematic structural diagram of a rectangular dial provided in this embodiment.

[0059] Figure 5 This is a schematic structural diagram of a circular dial provided in this embodiment.

[0060] Figure 6 This is a schematic structural diagram of a square dial provided in this embodiment.

[0061] Generally speaking, there are two types of meters in substations. The first type of meter is a meter without a pointer, such as Figure 4 The oil level gauge shown in Figure 2 shows only the oil level. Figure 5 and Figure 6 As shown, it is a meter that includes a pointer, such as a pressure gauge, lightning arrester detector, etc.

[0062] for Figure 4 For a rectangular dial without a pointer, the coordinates of the four edge points (A, B, C, and D) of the scale area are extracted according to the scale area mask, and the scale area area between the start and end points of the scale line is is the scale area mask area, and its formula is:

[0063] for Figure 5 and Figure 6 For a circular or square dial with a pointer, extract the coordinates of the edge points of the scale area according to the scale area mask, and perform gradient calculation (difference operation) on the coordinates of the edge points, remove the edge points with very small coordinate gradient changes, and obtain the effective scale area edge points. In this way, the two points with the largest coordinate gradient changes among the edge points of the effective scale area are the starting points of the scale lines. With the end point , and then select any target point on the circle , you can find the center of the circle The radius of the circle ,in, Except for the starting point of the tick mark With the end point Any point other than .

[0064] like Figure 5 or Figure 6 As shown, the scale area is a sector area, which is a part of a circle. According to the characteristics of the circle and the center of the circle, the distance from the center of the circle to any point on the circle is the same. Therefore, according to the three points on the circle , and , the position of the center of the circle can be calculated The radius of the circle .

[0065] Therefore, the area of ​​the scale area from the start point to the end point of the scale line It is the sector area from the start point to the end point of the scale line in the clockwise direction, that is:

[0066]

[0067]

[0068]

[0069] Among them, the total area of ​​the scale area is The area of ​​the circle where the scale area mask of the circular dial is located is cut by the line connecting the scale start point and the scale end point. , the area of ​​the circle where the square dial scale area mask is located is cut by the line connecting the scale start point and the scale end point. .

[0070] Secondly, based on the corrected indication area mask, the coordinates of the edge points of the indication area are extracted to determine the indication position corresponding to the scale area, and then the area of ​​the indication area between the scale line starting point and the indication position is calculated. .

[0071] for Figure 4 The rectangular dial in the figure is extracted according to the oil body indication area mask, and the coordinates of the edge points of the oil body indication area (points A, F, E, and D) and the indication area area between the starting point of the scale line and the indication position are extracted. To indicate the area, the formula is:

[0072] for Figure 5 The round dial or Figure 6 The square dial in the pointer indication area is extracted according to the pointer indication area mask, and the distance between the pointer indication area edge point and the effective scale area edge point is calculated. The effective scale area edge point corresponding to the shortest distance is selected as the pointer indication position. , the area of ​​the indication area between the starting point of the scale area and the position indicated by the pointer It is the sector area from the starting point of the scale line to the position indicated by the pointer in the clockwise direction, that is:

[0073]

[0074] This embodiment selects different area calculation methods according to different types of dials, and can be applied to meters in various scenarios, so that the meter recognition result is more accurate.

[0075] In one embodiment, judging whether the substation meter to be identified is in a low-level defect state based on the total area of ​​the scale area and the area of ​​the indication area includes: Calculating the area ratio between the area of ​​the indication region and the total area of ​​the scale region; If the area ratio is greater than or equal to a preset area ratio threshold, it is determined that the substation meter to be identified is in a normal state; If the area ratio is less than the preset area ratio threshold, it is determined that the substation meter to be identified is in a low-level defect state.

[0076] By presetting the area ratio threshold, i.e., the meter low threshold, which is generally 20%, it is determined whether the meter reading is in a low defect state. Specifically, if the area ratio is greater than or equal to the meter low threshold, the meter reading is in a normal state; if the area ratio is less than the meter low threshold, the meter reading is in a low defect state and a hidden danger check needs to be carried out in a timely manner.

[0077] In order to realize low-level alarm for different meters, it is possible to determine whether the meter is an oil level gauge, a pressure gauge, a lightning arrester detector, etc. according to the meter type or the meter image, and then generate different alarm modes according to different meters, such as voice broadcast, so that the staff can quickly determine the meter in a low-level defect state according to the alarm.

[0078] Reference Figure 7 This embodiment also provides a substation meter low-level defect identification system 700, including: The detection and segmentation module 701 is used to obtain a substation meter image of a substation meter to be identified, input the substation meter image into an improved Yolov9-m meter recognition model, and perform dial area detection processing, scale area and indication area instance segmentation on the substation meter image through the improved Yolov9-m meter recognition model to obtain a dial area type, a dial area detection frame, a scale area mask and an indication area mask in the substation meter image; the dial area type is any one of a rectangular dial, a circular dial and a square dial; A matching correction module 702 is used to crop the substation meter image according to the dial area detection frame to obtain a dial area image, obtain a dial area correction template of the dial area image from multiple dial area standard templates, and perform correction processing on the dial area image, the scale area mask and the indication area mask according to the dial area correction template to obtain a corrected dial area image, a corrected scale area mask and a corrected indication area mask; The low-level defect recognition module 703 is used to calculate the total area of ​​the scale area based on the correction scale area mask, calculate the area of ​​the indication area based on the correction indication area mask for different dial area types, and judge whether the substation meter to be identified is in a low-level defect state according to the total area of ​​the scale area and the area of ​​the indication area. If so, an alarm is issued that the substation meter to be identified is in a low-level defect state.

[0079] It can be understood that the substation meter low-level defect identification system of this embodiment corresponds to the substation meter low-level defect identification method of the above embodiment, and the options in the above embodiment are also applicable to this embodiment, so they will not be repeated here.

[0080] The present application also provides a computer device. Exemplarily, the computer device includes a processor and a memory, wherein the memory stores a computer program, and the processor runs the computer program to enable the computer device to execute the functions of each module in the above-mentioned substation meter low-level defect identification method or the above-mentioned substation meter low-level defect identification system.

[0081] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or at least one of other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application.

[0082] The memory may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electric erasable programmable read-only memory (EEPROM), etc. The memory is used to store a computer program, and the processor may execute the computer program accordingly after receiving an execution instruction.

[0083] The present application also provides a computer storage medium for storing the computer program used in the above-mentioned computer device. The computer storage medium may be a readable storage medium, or a non-volatile storage medium or a volatile storage medium. For example, the computer storage medium may include but is not limited to: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0084] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow diagram, and the combination of boxes in the structure diagram and / or the flow diagram, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0085] In addition, the functional modules or units in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0086] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0087] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for identifying low-level defects of substation meters, characterized in that: include: Obtain a substation meter image of a substation meter to be identified, input the substation meter image into an improved Yolov9-m meter recognition model, perform dial area detection processing and instance segmentation of the scale area and the indication area on the substation meter image through the improved Yolov9-m meter recognition model, and obtain a dial area type, a dial area detection frame, a scale area mask, and an indication area mask in the substation meter image; the dial area type is any one of a rectangular dial, a circular dial, and a square dial; The substation meter image is cropped according to the dial area detection frame to obtain a dial area image, a dial area correction template of the dial area image is obtained from a plurality of dial area standard templates, and the dial area image, the scale area mask and the indication area mask are corrected according to the dial area correction template to obtain a corrected dial area image, a corrected scale area mask and a corrected indication area mask; For different dial area types, the total area of ​​the scale area is calculated based on the correction scale area mask, and the area of ​​the indication area is calculated based on the correction indication area mask. According to the total area of ​​the scale area and the area of ​​the indication area, it is judged whether the substation meter to be identified is in a low-level defect state. If so, an alarm is issued that the substation meter to be identified is in a low-level defect state.

2. The method for identifying low-level defects of substation meters according to claim 1, characterized in that: The improved Yolov9-m meter recognition model includes a backbone network, an improved feature pyramid network and a head network, wherein the improved feature pyramid network includes a spatial attention mechanism module and a fusion module, and the head network includes a classification regression processing module, an area of ​​interest alignment module, and an instance segmentation module; The method of performing dial area detection processing, scale area and indication area instance segmentation on the substation meter image by using the improved Yolov9-m meter recognition model includes: Extracting features from the substation meter image through the backbone network to obtain a plurality of initial feature maps; Inputting a plurality of the initial feature maps into the improved feature pyramid network, processing the plurality of the initial feature maps through the spatial attention mechanism module to obtain a plurality of spatial attention feature maps, and fusing the plurality of the spatial attention feature maps through the fusion module to obtain a fused feature map; The fusion feature map is classified and regressed by the classification and regression processing module to obtain the dial area type and the dial area detection frame in the substation meter image; Obtaining a region of interest feature map of a preset size according to the image area corresponding to the dial area detection frame through the region of interest alignment module; The instance segmentation module is used to perform classification, regression and instance segmentation processing on the feature map of the region of interest, thereby obtaining the scale region mask and the indication region mask respectively.

3. The method for identifying low-level defects of substation meters according to claim 2, characterized in that: The initial feature map includes a low-level high-resolution feature map and a high-level low-resolution feature map, and the processing of each of the initial feature maps by the spatial attention mechanism module includes: Performing channel maximum pooling on the low-level high-resolution feature map to obtain a single-channel maximum value feature map, and performing channel average pooling on the low-level high-resolution feature map to obtain a single-channel mean feature map; Perform channel concatenation on the single-channel maximum value feature map and the single-channel mean feature map to obtain a two-channel feature map, and perform a 1x1 convolution operation on the two-channel feature map to obtain a single-channel feature map; Processing the single-channel feature map through an activation function to obtain a spatial weighted feature map; The high-level low-resolution feature map is convolved and up-sampled by 1x1 to generate an up-sampled feature map with the same resolution as the low-level high-resolution feature map; The upsampled feature map is multiplied by the spatial weighted feature map to obtain the spatial attention feature map.

4. The method for identifying low-level defects of substation meters according to claim 1, characterized in that: For different dial area types, the total area of ​​the scale area is calculated based on the corrected scale area mask, and the area of ​​the indication area is calculated based on the corrected indication area mask, including: If the dial area type is the rectangular dial, four scale area edge points are extracted according to the corrected scale area mask; and the total scale area area corresponding to the rectangular dial is calculated according to the four scale area edge points; Four indication region edge points are extracted according to the corrected indication region mask, and the indication region area is calculated according to the four indication region edge points.

5. The method for identifying low-level defects of substation meters according to claim 1, characterized in that: For different dial area types, the total area of ​​the scale area is calculated based on the corrected scale area mask, and the area of ​​the indication area is calculated based on the corrected indication area mask, including: If the dial area type is the circular dial or the square dial, extract multiple scale area edge points according to the corrected scale area mask, and determine two points with the largest gradient change among the multiple scale area edge points as the scale start point and the scale end point; A target point is selected from the remaining edge points of the scale area, and the center and radius of the circle where the correction scale area mask is located are calculated according to the target point, the scale starting point and the scale end point, wherein the remaining edge point of the scale area is the coordinate of the plurality of edge points of the scale area excluding the scale starting point and the scale end point; Calculate the total area of ​​the scale region according to the target point, the scale starting point, the scale end point, the center of the circle and the radius; Extracting a plurality of indication area edge points according to the corrected indication area mask, and calculating the distance between each of the indication area edge points and each of the scale area edge points; The shortest distance among the multiple distances is determined, the edge point of the scale area corresponding to the shortest distance is used as the pointer indication position, and the area of ​​the indication area is calculated according to the pointer indication position.

6. The method for identifying low-level defects of substation meters according to claim 5, characterized in that: Calculating the total area of ​​the scale region according to the target point, the scale starting point, the scale end point, the center of the circle and the radius includes: If the dial area type is the circular dial, the total area of ​​the scale area of ​​the circular dial is calculated according to the following formula 1; Formula 1: ; If the dial area type is the square dial, the total area of ​​the scale area of ​​the square dial is calculated according to the following formula 2; Formula 2: ; in, The starting point of the scale is , the end point of the scale is , the target point is , the center of the circle is , the radius is r, and the total area of ​​the scale area is The area of ​​the circle where the scale area mask of the circular dial is located is cut by the line connecting the scale starting point and the scale end point. The area of ​​the circle where the scale area mask of the square dial is located is cut by the line connecting the scale starting point and the scale end point. ; The calculating the area of ​​the indicated region according to the position indicated by the pointer comprises: The area of ​​the indicated region is calculated according to the following formula 3 and formula 4; Formula 3: Formula 4: The pointer indicates the position , the indicated area is .

7. The method for identifying low-level defects of a substation meter according to any one of claims 1 to 6, characterized in that: The step of acquiring a dial area correction template of the dial area image from a plurality of dial area standard templates comprises: Get the standard templates of the dial area corresponding to different dial area types; Determine, by using a matching algorithm, from the plurality of standard dial area templates, a standard dial area template having the greatest similarity to the dial area image as the dial area correction template; The correcting process of the dial area image, the scale area mask and the indication area mask according to the dial area correction template includes: Calculating a homography matrix between the dial area image and the dial area correction template; Correcting the dial area image, the scale area mask and the indication area mask respectively by using the homography matrix; The step of judging whether the substation meter to be identified is in a low-level defect state according to the total area of ​​the scale area and the area of ​​the indication area includes: Calculating the area ratio between the area of ​​the indication region and the total area of ​​the scale region; If the area ratio is greater than or equal to a preset area ratio threshold, it is determined that the substation meter to be identified is in a normal state; If the area ratio is less than the preset area ratio threshold, it is determined that the substation meter to be identified is in a low-level defect state.

8. Substation meter low-level defect identification system, characterized by: include: A detection and segmentation module, used for acquiring a substation meter image of a substation meter to be identified, inputting the substation meter image into an improved Yolov9-m meter recognition model, performing dial area detection processing and instance segmentation of a scale area and an indication area on the substation meter image through the improved Yolov9-m meter recognition model, and obtaining a dial area type, a dial area detection frame, a scale area mask and an indication area mask in the substation meter image; the dial area type is any one of a rectangular dial, a circular dial and a square dial; A matching correction module, used for cropping the substation meter image according to the dial area detection frame to obtain a dial area image, obtaining a dial area correction template of the dial area image from a plurality of dial area standard templates, and performing correction processing on the dial area image, the scale area mask and the indication area mask according to the dial area correction template to obtain a corrected dial area image, a corrected scale area mask and a corrected indication area mask; The low-level defect recognition module is used to calculate the total area of ​​the scale area based on the correction scale area mask, calculate the area of ​​the indication area based on the correction indication area mask for different dial area types, and judge whether the substation meter to be identified is in a low-level defect state according to the total area of ​​the scale area and the area of ​​the indication area. If so, an alarm is issued that the substation meter to be identified is in a low-level defect state.

9. A computer device, characterized in that: The computer device comprises a processor and a memory, wherein the memory stores a computer program, and the processor is used to execute the computer program to implement the substation meter low-level defect identification method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer program is stored therein, and when the computer program is executed on a processor, the method for identifying low-level defects of a substation meter according to any one of claims 1 to 7 is implemented.

Images