Identification method and system for illegal wiring of electric energy meter, electronic equipment and storage medium

Abstract

The invention provides a method for identifying illegal wiring of an electric energy meter. The method comprises the following steps: acquiring image information of a target electric energy meter; according to the image information, determining a wire metal layer identification area, a wire insulation layer identification area, a wire label identification area and wire key points of all wires of the target electric energy meter; determining whether the target electric energy meter has a first illegal wiring condition or not according to the wire metal layer identification area, wherein the first illegal wiring condition comprises a wire metal layer exposure risk; determining whether the target electric energy meter has a second illegal wiring condition or not according to the wire insulation layer identification area, wherein the second illegal wiring condition comprises a wire line misconnection risk; determining whether the target electric energy meter has a third illegal wiring condition according to the wire key point, wherein the third illegal wiring condition comprises a risk that the wire bending angle is not compliant; and determining whether the target electric energy meter has a fourth illegal wiring condition according to the lead label identification area, wherein the fourth illegal wiring condition comprises lead label mismatching.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular, to a method and system for identifying illegal wiring of an electric energy meter, an electronic device, and a storage medium. Background Art

[0002] The wiring of an electric energy meter is an important link in electric energy metering, and its correctness is directly related to the accuracy of electric energy metering and power consumption safety. Therefore, the detection of whether the wiring of the electric energy meter is compliant is of great significance.

[0003] Currently, some methods for identifying illegal wiring of an electric energy meter include identifying the area of the electric energy meter and the wiring area, and identifying the wiring sequence according to the detection algorithm to determine whether there is illegal wiring.

[0004] However, the inventor found that such methods for identifying illegal wiring of an electric energy meter can only determine whether there is non-compliant wiring operation by identifying the wiring sequence, and there is a problem of low recognition accuracy. Summary of the Invention

[0005] The present invention provides a method and system for identifying illegal wiring of an electric energy meter, an electronic device, and a storage medium, which are used to solve the problem of low recognition accuracy existing in the current methods for identifying illegal wiring of an electric energy meter.

[0006] According to one aspect of the present invention, there is provided a method for identifying illegal wiring of an electric energy meter, including: obtaining image information of a target electric energy meter; determining, according to the image information, the identification regions of the wire metal layer, the wire insulation layer, the wire label, and the wire key points of all wires of the target electric energy meter; determining whether the target electric energy meter has a first illegal wiring situation according to the identification region of the wire metal layer, where the first illegal wiring situation includes the risk of exposure of the wire metal layer; determining whether the target electric energy meter has a second illegal wiring situation according to the identification region of the wire insulation layer, where the second illegal wiring situation includes the risk of incorrect connection of the wire circuit; determining whether the target electric energy meter has a third illegal wiring situation according to the wire key points, where the third illegal wiring situation includes the risk of non-compliant bending angle of the wire; determining whether the target electric energy meter has a fourth illegal wiring situation according to the identification region of the wire label, where the fourth illegal wiring situation includes non-matching of the wire label.

[0007] According to some embodiments of the present invention, determining whether there is a first illegal wiring situation in the target electricity meter based on the wire metal layer identification area includes: determining the circumscribed rectangle of the metal layer of the wire metal layer identification area; determining the pixel width and pixel height of the circumscribed rectangle of the metal layer; determining whether the pixel width and pixel height of the circumscribed rectangle of the metal layer meet a first preset condition; if so, determining the pixel ratio of the wire metal layer identification area to the sum of the wire metal layer identification area and the wire insulation layer identification area; and determining that there is a first illegal wiring situation when the pixel ratio meets a second preset condition.

[0008] According to some embodiments of the present invention, determining whether there is a second illegal wiring situation in the target electricity meter based on the wire insulation layer identification area includes: determining the circumscribed rectangle of the insulation layer of the wire insulation layer identification area; determining the color sequence of all wire insulation layers in the circumscribed rectangle of the insulation layer; and determining that there is a second illegal wiring situation when the color sequence is inconsistent with the theoretical color sequence of the target electricity meter.

[0009] According to some embodiments of the present invention, determining whether there is a third illegal wiring situation in the target electricity meter based on the wire key points includes: determining the target wire key points in the wire insulation layer identification area according to the wire key points; determining the included angle between adjacent wires in the wire insulation layer identification area according to the target wire key points; and determining that there is a third illegal wiring situation when there is at least one included angle between adjacent wires that meets a third preset condition.

[0010] On the other hand, the present invention provides a recognition system for illegal wiring of an electricity meter, including: an image processing module that acquires image information of a target electricity meter and determines the wire metal layer identification area, the wire insulation layer identification area, the wire label identification area, and the wire key points of all wires of the target electricity meter according to the image information; and an information processing module that determines whether there is a first illegal wiring situation in the target electricity meter based on the wire metal layer identification area, where the first illegal wiring situation includes the risk of wire metal layer exposure, determines whether there is a second illegal wiring situation in the target electricity meter based on the wire insulation layer identification area, where the second illegal wiring situation includes the risk of incorrect wire connection, determines whether there is a third illegal wiring situation in the target electricity meter based on the wire key points, where the third illegal wiring situation includes the risk of non-compliant wire bending angle, and determines whether there is a fourth illegal wiring situation in the target electricity meter based on the wire label identification area, where the fourth illegal wiring situation includes wire label mismatch.

[0011] According to some embodiments of the present invention, the information processing module determines the circumscribed rectangle of the metal layer of the wire metal layer identification region; the information processing module determines the pixel width and pixel height of the circumscribed rectangle of the metal layer; the information processing module determines whether the pixel width and pixel height of the circumscribed rectangle of the metal layer meet the first preset condition; if so, the information processing module determines the pixel ratio of the wire metal layer identification region to the sum of the wire metal layer identification region and the wire insulation layer identification region; the information processing module determines that there is a first illegal wiring situation when the pixel ratio meets the second preset condition.

[0012] According to some embodiments of the present invention, the information processing module determines the circumscribed rectangle of the insulation layer of the wire insulation layer identification region; the information processing module determines the color sequence of all wire insulation layers in the circumscribed rectangle of the insulation layer; the information processing module determines that there is a second illegal wiring situation when the color sequence is inconsistent with the theoretical color sequence of the target electricity meter.

[0013] According to some embodiments of the present invention, the information processing module determines the target wire key points in the wire insulation layer identification region according to the wire key points; the information processing module determines the included angle between adjacent wires in the wire insulation layer identification region according to the target wire key points; the information processing module determines that there is a third illegal wiring situation when there is at least one included angle between adjacent wires that meets the third preset condition.

[0014] According to another aspect of the present invention, the present invention also provides an electronic device. The electronic device includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors can implement the identification method as described above.

[0015] According to another aspect of the present invention, the present invention also provides a non-volatile computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by a processor, it can implement the identification method as described above.

[0016] According to another aspect of the present invention, the present invention also provides a computer program product. The computer program product includes: a computer program stored on a computer-readable storage medium; the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the identification method as described above.

[0017] Beneficial effects

[0018] The present invention determines the wire metal layer identification region, wire insulation layer identification region, wire label identification region, and wire key points of all wires of the target electricity meter by obtaining the image information of the target electricity meter. Further, the present invention can determine whether there is a first illegal wiring situation of the target electricity meter based on the wire metal layer identification region, determine whether there is a second illegal wiring situation of the target electricity meter based on the wire insulation layer identification region, determine whether there is a third illegal wiring situation of the target electricity meter based on the wire key points, and determine whether there is a fourth illegal wiring situation of the target electricity meter based on the wire label identification region.

[0019] The present invention can identify the illegal wiring of the electricity meter simultaneously from multiple aspects (such as exposed wire metal layer, wrong wire connection, wire bending, and mismatched wire labels), so as to more comprehensively and accurately identify whether there is an illegal wiring operation for the target electricity meter. Furthermore, it can avoid the safety risks caused by the illegal wiring of the electricity meter during the electricity metering process. Brief Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 A flowchart showing the identification method according to an embodiment of the present invention;

[0022] Figure 2 Another flowchart showing the identification method according to an embodiment of the present invention;

[0023] Figure 3 Another flowchart showing the identification method according to an embodiment of the present invention;

[0024] Figure 4 Another flowchart showing the identification method according to an embodiment of the present invention;

[0025] Figure 5 Another flowchart showing the identification method according to an embodiment of the present invention;

[0026] Figure 6 A structural diagram showing the identification system according to an embodiment of the present invention.

[0027] Description of the Reference Numerals:

[0028] Identification system 1; Image processing module 10; Information processing module 20. Detailed Embodiments

[0029] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. Like reference numerals in the figures denote like or similar parts, and thus their repetitive description will be omitted.

[0030] The features, structures, or characteristics described may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of the present disclosure. However, those skilled in the art will realize that the technical solutions of the present disclosure can be practiced without one or more of these specific details, or other means, components, materials, devices, etc. may be used. In these cases, well-known structures, methods, devices, implementations, materials, or operations will not be shown or described in detail.

[0031] Furthermore, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0032] The terms "first", "second", etc. in the description and claims of the present invention and in the above drawings are used to distinguish different objects, rather than to describe a specific order.

[0033] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0034] The full names and Chinese interpretations of the English abbreviations involved in the present invention are as follows:

[0035] SSD: Single Shot MultiBox Detector, a deep learning-based object detection algorithm;

[0036] YOLO: You Only Look Once, a real-time object detection algorithm based on deep learning;

[0037] RetinaNet: a single-stage object detection model;

[0038] RT-DETR: Real-Time Detection Transformer, a real-time end-to-end object detection model;

[0039] OpenCV, Open Source Computer Vision Library, an open-source computer vision and machine learning software library.

[0040] According to one aspect of the present invention, the present invention provides a method for identifying illegal wiring of an electric energy meter. Figure 1 A flowchart showing the identification method of an embodiment of the present invention is as follows Figure 1 As shown, the identification method may include steps S100 - S600.

[0041] Exemplarily, the identification method may be executed by an identification system for illegal wiring of an electric energy meter with computing capabilities.

[0042] According to an exemplary embodiment, in step S100, the identification system acquires image information of the target electric energy meter.

[0043] For example, the target electric energy meter may be an electric energy meter for which it is necessary to determine whether there is an illegal wiring operation. The image information may include image data and type data of the target electric energy meter.

[0044] The user may collect image data of the target electric energy meter through an image acquisition device and send the image data of the target electric energy meter and the type data of the target electric energy meter (such as the type data may be the model number of the target electric energy meter, etc.) to the identification system through the image acquisition device.

[0045] Exemplarily, the image acquisition device includes but is not limited to a mobile terminal configured with a camera such as a mobile phone, a tablet, or a laptop computer, and the present invention is not limited thereto.

[0046] In step S200, the identification system determines the wire metal layer identification region, wire insulation layer identification region, wire label identification region, and wire key points of all wires of the target electric energy meter according to the image information.

[0047] For example, the identification system may perform wire metal layer segmentation, wire insulation layer segmentation, and wire label segmentation respectively based on image segmentation recognition technology according to the image data of the target electric energy meter to obtain the wire metal layer identification region, wire insulation layer identification region, and wire label identification region corresponding to each wire of the target electric energy meter respectively.

[0048] Exemplarily, the image segmentation recognition technology includes but is not limited to SSD, YOLO, RetinaNet, or RT-DETR, etc., and the present invention does not limit this.

[0049] In addition, the recognition system can detect the key points of the wire based on the key point detection technology according to the image data of the target electric energy meter, so as to obtain the key points of the wire. The key points of the wire can be customized according to user needs.

[0050] For example, the key point of the wire can be the inflection point of the wire.

[0051] As an exemplary embodiment, when the target electric energy meter is a single-phase electric energy meter, the target electric energy meter includes two wires. The colors of the two wires are red and black in sequence from the left side to the right side of the single-phase electric energy meter.

[0052] As another exemplary embodiment, when the target electric energy meter is a three-phase four-wire electric energy meter, the target electric energy meter includes four wires. The colors of the four wires are yellow, green, red, and black in sequence from the left side to the right side of the three-phase four-wire electric energy meter.

[0053] As another exemplary embodiment, when the target electric energy meter is a three-phase three-wire electric energy meter, the target electric energy meter includes three wires. The colors of the three wires are yellow, green, and red in sequence from the left side to the right side of the three-phase three-wire electric energy meter.

[0054] In step S300, the recognition system determines whether there is a first illegal wiring situation in the target electric energy meter according to the wire metal layer recognition area. The first illegal wiring situation includes the risk of exposure of the wire metal layer.

[0055] For example, the recognition system can judge whether there is a risk of exposure of the wire metal layer through image recognition technology.

[0056] Exemplarily, the recognition system can identify whether there is an exposed wire metal layer according to the pixel values (such as pixel width and pixel height) in the wire metal layer recognition area, and further can judge whether there is a risk of exposure of the wire metal layer.

[0057] Figure 2 Another flow diagram showing the recognition method of the embodiment of the present invention is as follows. Figure 2 As shown, step S300 may include steps S310-S350.

[0058] Optionally, in step S310, the recognition system determines the circumscribed rectangle of the metal layer of the wire metal layer recognition area.

[0059] In step S320, the recognition system determines the pixel width and pixel height of the circumscribed rectangle of the metal layer.

[0060] For example, the recognition system obtains the circumscribed rectangle of the metal layer in the recognition area of the wire metal layer according to OpenCV, and then obtains the circumscribed rectangles of the metal layers in the recognition areas of all wires. The recognition system obtains the pixel width and pixel height of all the circumscribed rectangles of the metal layers.

[0061] In step S330, the recognition system determines whether the pixel width and pixel height of the circumscribed rectangle of the metal layer meet the first preset condition.

[0062] For example, the first preset condition can be that the pixel width of the circumscribed rectangle of the metal layer is greater than or equal to the first preset threshold, or the pixel height of the circumscribed rectangle of the metal layer is greater than or equal to the second preset threshold.

[0063] Exemplarily, when the recognition system determines that the pixel width of the circumscribed rectangle of the metal layer is less than the first preset threshold, or the pixel height of the circumscribed rectangle of the metal layer is less than the second preset threshold, it is determined that there is no risk of exposure of the wire metal layer for this wire.

[0064] When the recognition system determines that the pixel width of the circumscribed rectangle of the metal layer is greater than or equal to the first preset threshold, or the pixel height of the circumscribed rectangle of the metal layer is greater than or equal to the second preset threshold, it is determined that there may be a risk of exposure of the wire metal layer for this wire, and further judgment is required, that is, enter step S340.

[0065] In step S340, the recognition system determines the pixel ratio of the wire metal layer recognition area to the sum of the wire metal layer recognition area and the wire insulation layer recognition area.

[0066] For example, the recognition system obtains the pixel area of the wire metal layer recognition area and the pixel area of the wire insulation layer recognition area according to OpenCV, and calculates the pixel ratio based on the pixel areas of the two.

[0067] Exemplarily, the calculation formula of the pixel ratio can be: pixel ratio = pixel area of the wire metal layer recognition area / (pixel area of the wire metal layer recognition area + pixel area of the wire insulation layer recognition area).

[0068] In step S350, when the pixel ratio meets the second preset condition, the recognition system determines that there is a first illegal wiring situation.

[0069] For example, when the pixel ratio is less than the third preset threshold, it indicates that the risk of exposure of the wire metal layer is relatively low. When the pixel ratio is greater than or equal to the third preset threshold, it indicates that the risk of exposure of the wire metal layer is relatively high, and the recognition system determines that there is a risk of exposure of the wire metal layer and gives an alarm prompt.

[0070] Through the above embodiments, the present invention can comprehensively determine whether there is a risk of exposure of the wire metal layer by identifying the pixel width and pixel height of the wire metal layer identification area, as well as the pixel area of the wire metal layer identification area and the pixel area of the wire insulation layer identification area. The present invention has the characteristics of accurate identification.

[0071] In step S400, the identification system determines whether there is a second illegal wiring situation in the target electric energy meter according to the wire insulation layer identification area. The second illegal wiring situation includes the risk of incorrect connection of the wire circuit.

[0072] For example, the identification system can determine whether the wire circuit is incorrectly connected through image recognition technology.

[0073] Exemplarily, the identification system can identify whether the wire circuit is incorrectly connected according to the order of the wire colors in the wire insulation layer identification area.

[0074] Figure 3 Another flowchart showing the identification method according to an embodiment of the present invention is as follows Figure 3 As shown, step S400 may include steps S410 - S430.

[0075] Optionally, in step S410, the identification system determines the circumscribed rectangle of the insulation layer of the wire insulation layer identification area.

[0076] For example, the identification system obtains the circumscribed rectangle of the insulation layer of the wire insulation layer identification area according to OpenCV, and further obtains the circumscribed rectangles of the insulation layers of all wires in the wire insulation layer identification area.

[0077] In step S420, the identification system determines the color sequence of all wire insulation layers in the circumscribed rectangle of the insulation layer.

[0078] For example, the identification system can classify the colors of the wires in the wire insulation layer based on image recognition technology, and sequentially determine the color sequence of all wires in the circumscribed rectangle of the insulation layer in a preset direction.

[0079] Exemplarily, the preset direction may be from the left side to the right side of the target electric energy meter.

[0080] In step S430, when the color sequence is inconsistent with the theoretical color sequence of the target electric energy meter, the identification system determines that there is a second illegal wiring situation.

[0081] For example, each type of electric energy meter corresponds to a set of correct wiring sequences, that is, corresponds to a theoretical color sequence. When the identified color sequence is inconsistent with the theoretical color sequence, the identification system determines that there is a risk of incorrect connection of the wire circuit and gives an alarm prompt.

[0082] For example, taking a single-phase watt-hour meter as an example, if it is recognized that the color sequence of the single-phase watt-hour meter is not the sequence of red and black, the recognition system determines that the wire connection is incorrect and gives an alarm prompt.

[0083] Taking a three-phase four-wire watt-hour meter as an example, if it is recognized that the color sequence of the three-phase four-wire watt-hour meter is not the sequence of yellow, green, red, and black, the recognition system determines that the wire connection is incorrect and gives an alarm prompt.

[0084] Taking a three-phase three-wire watt-hour meter as an example, if it is recognized that the color sequence of the three-phase three-wire watt-hour meter is not the sequence of yellow, green, and red, the recognition system determines that the wire connection is incorrect and gives an alarm prompt.

[0085] Through the above embodiments, the present invention can determine whether there is a risk of incorrect wire connection by recognizing the color sequence of the wire insulation layer recognition area, and the present invention has the characteristics of accurate recognition.

[0086] In step S500, the recognition system determines whether there is a third illegal wiring situation for the target watt-hour meter according to the wire key points. The third illegal wiring situation includes the risk that the wire bending angle is non-compliant.

[0087] For example, the recognition system can judge whether there is a risk that the wire bending angle is non-compliant through image recognition technology.

[0088] Exemplarily, the recognition system can recognize whether the wire is bent according to the wire inflection points in the wire insulation layer recognition area.

[0089] Figure 4 Another flow schematic diagram showing the recognition method of the embodiment of the present invention is shown. As Figure 4 shown, step S500 may include steps S510 - S530.

[0090] Optionally, in step S510, the recognition system determines the target wire key points in the wire insulation layer recognition area according to the wire key points.

[0091] For example, the recognition system filters the wire inflection points outside the wire insulation layer recognition area based on the wire insulation layer recognition area to obtain the target wire inflection points in the wire insulation layer recognition area.

[0092] In step S520, the recognition system determines the included angle between adjacent wires in the wire insulation layer recognition area according to the target wire key points.

[0093] For example, the recognition system determines the equations of the connecting lines of all adjacent inflection points of each wire according to the target wire inflection points to calculate the included angles between all adjacent wires in the order from top to bottom.

[0094] In step S530, when there is an included angle between at least two adjacent wires that satisfies the third preset condition, the recognition system determines that there is a third illegal wiring situation.

[0095] For example, the third preset condition may be that the absolute value of the difference between the included angle and 90 degrees is greater than the fourth preset threshold.

[0096] Exemplarily, when the recognition system determines that there is an included angle between at least two adjacent wires that satisfies the third preset condition, the recognition system determines that there is a risk of non-compliant wire bending and gives an alarm prompt.

[0097] Through the above embodiments, the present invention can determine the included angle between adjacent wires through the key points of the target wire, and further can judge whether there is a risk of non-compliant wire bending angle based on this included angle. The present invention has the characteristics of accurate recognition.

[0098] In step S600, the recognition system determines whether there is a fourth illegal wiring situation for the target electricity meter according to the wire label recognition area. The fourth illegal wiring situation includes wire label mismatch.

[0099] For example, the recognition system can judge whether the label set on the target electricity meter is correct through image recognition technology.

[0100] Exemplarily, the recognition system can identify whether the wire label set on the target electricity meter is correct by judging whether the recognized wire label information is consistent with the theoretical wire label information of the target electricity meter.

[0101] Figure 5 Another flowchart showing the recognition method of the embodiment of the present invention is as follows Figure 5 As shown, step S600 may include steps S610-S640.

[0102] Optionally, in step S610, the recognition system determines the label circumscribed rectangle of the wire label recognition area.

[0103] In step S620, the recognition system determines whether the wire label recognition area is a recognition area with qualified quality according to the label circumscribed rectangle.

[0104] In step S630, the recognition system performs text positioning and text recognition on the label circumscribed rectangle with qualified quality to obtain the wire label information (such as string information) of the wire label. For the label circumscribed rectangle with unqualified quality, the recognition system sets the wire label information of its wire label to be empty.

[0105] In step S640, when the wire label information is inconsistent with the theoretical wire label information, the recognition system determines that there is a fourth illegal wiring situation.

[0106] For example, if the string information of the wire label does not match the string rule of the wire insulation layer, the recognition system determines that the wire label does not match and gives an alarm prompt.

[0107] Through the above embodiments, the present invention can determine the situation where the wire label does not match by judging whether the label information set for the target electricity meter is consistent with the theoretical label information, and the present invention has the characteristics of accurate recognition.

[0108] Through the above embodiments, the present invention obtains the image information of the target electricity meter, and determines the wire metal layer recognition area, wire insulation layer recognition area, wire label recognition area and wire key points of all wires of the target electricity meter according to the image information. And the present invention can determine whether there is a first illegal wiring situation in the target electricity meter through the wire metal layer recognition area, determine whether there is a second illegal wiring situation in the target electricity meter according to the wire insulation layer recognition area, determine whether there is a third illegal wiring situation in the target electricity meter according to the wire key points, and determine whether there is a fourth illegal wiring situation in the target electricity meter according to the wire label recognition area.

[0109] The present invention can identify the illegal wiring of the electricity meter simultaneously from multiple levels (such as exposed wire metal layer, wrong wire connection, wire bending, and wire label mismatch, etc.), so as to more comprehensively and accurately identify whether there is an illegal wiring operation in the target electricity meter. Furthermore, it can avoid the safety risks caused by the illegal wiring of the electricity meter during the electricity metering process.

[0110] According to another aspect of the present invention, the present invention also provides a recognition system for illegal wiring of an electricity meter. Figure 6 The structural schematic diagram of the recognition system according to the embodiment of the present invention is shown as Figure 6 As shown, the recognition system 1 includes an image processing module 10 and an information processing module 20.

[0111] According to the exemplary embodiment, the image processing module 10 obtains the image information of the target electricity meter.

[0112] For example, the target electricity meter can be an electricity meter that needs to determine whether there is an illegal wiring operation. The image information can include the image data and type data of the target electricity meter.

[0113] The user can collect the image data of the target electricity meter through an image acquisition device, and send the image data of the target electricity meter and the type data of the target electricity meter (such as the type data can be the model of the target electricity meter, etc.) to the image processing module 10 through the image acquisition device.

[0114] Exemplarily, the image acquisition device includes but is not limited to a mobile terminal configured with a camera such as a mobile phone, a tablet or a laptop computer, and the present invention is not limited thereto.

[0115] According to the exemplary embodiment, the image processing module 10 determines the wire metal layer identification region, the wire insulation layer identification region, the wire label identification region, and the wire key points of all the wires of the target electric energy meter according to the image information.

[0116] For example, the image processing module 10 can perform wire metal layer segmentation, wire insulation layer segmentation, and wire label segmentation respectively based on the image segmentation recognition technology according to the image data of the target electric energy meter, so as to obtain the wire metal layer identification region, the wire insulation layer identification region, and the wire label identification region corresponding to each wire of the target electric energy meter respectively.

[0117] Exemplarily, the image segmentation recognition technology includes but is not limited to SSD, YOLO, RetinaNet, or RT-DETR, etc., and the present invention does not limit this.

[0118] In addition, the image processing module 10 can perform wire key point detection based on the key point detection technology according to the image data of the target electric energy meter to obtain the wire key points. The wire key points can be custom-set according to user requirements.

[0119] For example, the wire key point can be a wire inflection point.

[0120] As an exemplary embodiment, when the target electric energy meter is a single-phase electric energy meter, the target electric energy meter includes two wires. The colors of the two wires are red and black in sequence from the left side to the right side of the single-phase electric energy meter.

[0121] As another exemplary embodiment, when the target electric energy meter is a three-phase four-wire electric energy meter, the target electric energy meter includes four wires. The colors of the four wires are yellow, green, red, and black in sequence from the left side to the right side of the three-phase four-wire electric energy meter.

[0122] As another exemplary embodiment, when the target electric energy meter is a three-phase three-wire electric energy meter, the target electric energy meter includes three wires. The colors of the three wires are yellow, green, and red in sequence from the left side to the right side of the three-phase three-wire electric energy meter.

[0123] According to the exemplary embodiment, the information processing module 20 determines whether there is a first illegal wiring situation in the target electric energy meter according to the wire metal layer identification region. The first illegal wiring situation includes the risk of wire metal layer exposure.

[0124] For example, the information processing module 20 can judge whether there is a risk of wire metal layer exposure through image recognition technology.

[0125] Exemplarily, the information processing module 20 can identify whether there is an exposed wire metal layer based on the pixel values (such as pixel width and pixel height) in the wire metal layer identification area, and then can determine whether there is a risk of exposure of the wire metal layer.

[0126] Optionally, the information processing module 20 determines the circumscribed rectangle of the metal layer in the wire metal layer identification area.

[0127] The information processing module 20 determines the pixel width and pixel height of the circumscribed rectangle of the metal layer.

[0128] For example, the information processing module 20 obtains the circumscribed rectangle of the metal layer in the wire metal layer identification area according to OpenCV, and then obtains the circumscribed rectangles of the metal layers of all wires. The information processing module 20 obtains the pixel width and pixel height of all the circumscribed rectangles of the metal layers.

[0129] The information processing module 20 determines whether the pixel width and pixel height of the circumscribed rectangle of the metal layer meet the first preset condition.

[0130] For example, the first preset condition can be that the pixel width of the circumscribed rectangle of the metal layer is greater than or equal to the first preset threshold, or the pixel height of the circumscribed rectangle of the metal layer is greater than or equal to the second preset threshold.

[0131] Exemplarily, when the information processing module 20 determines that the pixel width of the circumscribed rectangle of the metal layer is less than the first preset threshold, or the pixel height of the circumscribed rectangle of the metal layer is less than the second preset threshold, it is determined that there is no risk of exposure of the wire metal layer for this wire.

[0132] When the information processing module 20 determines that the pixel width of the circumscribed rectangle of the metal layer is greater than or equal to the first preset threshold, or the pixel height of the circumscribed rectangle of the metal layer is greater than or equal to the second preset threshold, it is determined that there may be a risk of exposure of the wire metal layer for this wire, and further judgment is required.

[0133] The information processing module 20 determines the pixel ratio of the wire metal layer identification area to the sum of the wire metal layer identification area and the wire insulation layer identification area.

[0134] For example, the information processing module 20 obtains the pixel area of the wire metal layer identification area and the pixel area of the wire insulation layer identification area according to OpenCV, and calculates the pixel ratio based on the pixel areas of the two.

[0135] Exemplarily, the calculation formula for the pixel ratio can be: pixel ratio = pixel area of the wire metal layer identification area / (pixel area of the wire metal layer identification area + pixel area of the wire insulation layer identification area).

[0136] When the pixel ratio meets the second preset condition, the information processing module 20 determines that there is a first illegal wiring situation.

[0137] For example, when the pixel ratio is less than the third preset threshold, it indicates that the exposure risk of the wire metal layer is relatively low. When the pixel ratio is greater than or equal to the third preset threshold, it indicates that the exposure risk of the wire metal layer is relatively high. Then, the information processing module 20 determines that there is an exposure risk of the wire metal layer and gives an alarm prompt.

[0138] Through the above embodiments, the present invention can comprehensively determine whether there is an exposure risk of the wire metal layer based on the pixel width and pixel height of the wire metal layer recognition area, as well as the pixel area of the wire metal layer recognition area and the pixel area of the wire insulation layer recognition area. The present invention has the characteristics of accurate recognition.

[0139] According to the exemplary embodiment, the information processing module 20 determines whether there is a second illegal wiring situation in the target electric energy meter based on the wire insulation layer recognition area. The second illegal wiring situation includes the risk of incorrect wire connection.

[0140] For example, the information processing module 20 can determine whether the wire connection is incorrect through image recognition technology.

[0141] Exemplarily, the information processing module 20 can identify whether the wire connection is incorrect according to the order of the wire colors in the wire insulation layer recognition area.

[0142] Optionally, the information processing module 20 determines the circumscribed rectangle of the insulation layer of the wire insulation layer recognition area.

[0143] For example, the information processing module 20 obtains the circumscribed rectangle of the insulation layer of the wire insulation layer recognition area according to OpenCV, and further obtains the circumscribed rectangles of the insulation layers of all wires in the wire insulation layer recognition area.

[0144] The information processing module 20 determines the color sequence of all wire insulation layers in the circumscribed rectangle of the insulation layer.

[0145] For example, the information processing module 20 can classify the colors of the wires in the wire insulation layer based on image recognition technology, and sequentially determine the color sequence of all wires in the circumscribed rectangle of the insulation layer in a preset direction.

[0146] Exemplarily, the preset direction can be from the left side to the right side of the target electric energy meter.

[0147] When the color sequence is inconsistent with the theoretical color sequence of the target electric energy meter, the information processing module 20 determines that there is a second illegal wiring situation.

[0148] For example, each type of electricity meter corresponds to a set of correct wiring sequences, that is, corresponds to a theoretical color sequence. In the case where the recognized color sequence is inconsistent with the theoretical color sequence, the information processing module 20 determines that there is a risk of incorrect wiring of the wire lines and gives an alarm prompt.

[0149] For example, taking a single-phase electricity meter as an example, if the recognized color sequence of the single-phase electricity meter is not the sequence of red and black, the information processing module 20 determines that the wire lines are incorrectly wired and gives an alarm prompt.

[0150] Taking a three-phase four-wire electricity meter as an example, if the recognized color sequence of the three-phase four-wire electricity meter is not the sequence of yellow, green, red, and black, the information processing module 20 determines that the wire lines are incorrectly wired and gives an alarm prompt.

[0151] Taking a three-phase three-wire electricity meter as an example, if the recognized color sequence of the three-phase three-wire electricity meter is not the sequence of yellow, green, and red, the information processing module 20 determines that the wire lines are incorrectly wired and gives an alarm prompt.

[0152] Through the above embodiments, the present invention can determine whether there is a risk of incorrect wiring of the wire lines by recognizing the color sequence of the wire insulation layer recognition area, and the present invention has the characteristics of accurate recognition.

[0153] The information processing module 20 determines whether there is a third illegal wiring situation in the target electricity meter according to the wire key points. The third illegal wiring situation includes the risk that the wire bending angle is non-compliant.

[0154] For example, the information processing module 20 can determine whether there is a risk that the wire bending angle is non-compliant through image recognition technology.

[0155] Exemplarily, the information processing module 20 can identify whether the wire is bent according to the wire inflection point in the wire insulation layer recognition area.

[0156] Optionally, the information processing module 20 determines the target wire key points in the wire insulation layer recognition area according to the wire key points.

[0157] For example, the information processing module 20 filters the wire inflection points outside the wire insulation layer recognition area based on the wire insulation layer recognition area to obtain the target wire inflection points in the wire insulation layer recognition area.

[0158] The information processing module 20 determines the included angle between adjacent wires in the wire insulation layer recognition area according to the target wire key points.

[0159] For example, the information processing module 20 determines the equations of the connecting lines of all adjacent inflection points of each wire according to the target wire inflection points, so as to calculate the angles between all adjacent wires of all wires in the order from top to bottom.

[0160] When there is at least one angle between adjacent wires that satisfies the third preset condition, the information processing module 20 determines that there is a third illegal wiring situation.

[0161] For example, the third preset condition may be that the absolute value of the difference between the angle and 90 degrees is greater than the fourth preset threshold.

[0162] Exemplarily, when the information processing module 20 determines that there is at least one angle between adjacent wires that satisfies the third preset condition, the information processing module 20 determines that there is a risk of non-compliant wire bending angle and gives an alarm prompt.

[0163] Through the above embodiments, the present invention can determine the angle between adjacent wires through the key points of the target wire, and further can judge whether there is a risk of non-compliant wire bending angle according to the angle, with the characteristics of accurate identification.

[0164] According to the exemplary embodiment, the information processing module 20 determines whether there is a fourth illegal wiring situation of the target watt-hour meter according to the wire label recognition area. The fourth illegal wiring situation includes wire label mismatch.

[0165] For example, the information processing module 20 can judge whether the label set on the target watt-hour meter is correct through image recognition technology.

[0166] Exemplarily, the information processing module 20 can identify whether the wire label set on the target watt-hour meter is correct by judging whether the recognized wire label information is consistent with the theoretical wire label information of the target watt-hour meter.

[0167] Optionally, the information processing module 20 determines the circumscribed rectangle of the label in the wire label recognition area.

[0168] The information processing module 20 judges whether the wire label recognition area is a recognition area with qualified quality according to the circumscribed rectangle of the label.

[0169] The information processing module 20 performs text positioning and text recognition on the circumscribed rectangle of the label with qualified quality to obtain the wire label information (such as string information) of the wire label. For the circumscribed rectangle of the label with unqualified quality, the information processing module 20 sets the wire label information of its wire label to be empty.

[0170] When the wire label information is inconsistent with the theoretical wire label information, the information processing module 20 determines that there is a fourth illegal wiring situation.

[0171] For example, if the string information of the wire label does not match the string rule of the wire insulation layer, the information processing module 20 determines that the wire label does not match and gives an alarm prompt.

[0172] Through the above embodiments, the present invention can determine the situation where the wire label does not match by judging whether the label information set for the target electric energy meter is consistent with the theoretical label information. The present invention has the characteristics of accurate identification.

[0173] Through the above embodiments, the present invention obtains the image information of the target electric energy meter, and determines the wire metal layer identification area, wire insulation layer identification area, wire label identification area and wire key points of all wires of the target electric energy meter according to the image information. And the present invention can determine whether there is a first illegal wiring situation in the target electric energy meter according to the wire metal layer identification area, determine whether there is a second illegal wiring situation in the target electric energy meter according to the wire insulation layer identification area, determine whether there is a third illegal wiring situation in the target electric energy meter according to the wire key points, and determine whether there is a fourth illegal wiring situation in the target electric energy meter according to the wire label identification area.

[0174] The present invention can identify the illegal wiring of the electric energy meter simultaneously from multiple levels (such as exposed wire metal layer, wrong wire connection, wire bending, and non-matching wire labels, etc.), so as to more comprehensively and accurately identify whether there is an illegal wiring operation in the target electric energy meter. Furthermore, it can avoid the safety risks caused by the illegal wiring of the electric energy meter during the electric energy metering process.

[0175] According to another aspect of the present invention, the present invention also provides an electronic device. The electronic device includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors can implement the identification method as described above.

[0176] According to another aspect of the present invention, the present invention also provides a non-volatile computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by a processor, it can implement the identification method as described above.

[0177] According to another aspect of the present invention, the present invention also provides a computer program product. The computer program product includes: a computer program stored on a computer-readable storage medium; the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the identification method as described above.

[0178] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions of the foregoing embodiments or perform equivalent replacements on some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for identifying illegal wiring of an electric energy meter, characterized in that: include: Acquire image information of the target electric energy meter; Determine, based on the image information, a wire metal layer identification area, a wire insulation layer identification area, a wire label identification area, and wire key points of all wires of the target electric energy meter; Determining whether the target electric energy meter has a first illegal wiring condition according to the wire metal layer identification area, wherein the first illegal wiring condition includes a risk of the wire metal layer being exposed; Determining whether the target electric energy meter has a second illegal wiring situation according to the wire insulation layer identification area, wherein the second illegal wiring situation includes a risk of wrong wire connection; Determining whether the target electric energy meter has a third illegal wiring situation according to the key points of the wire, wherein the third illegal wiring situation includes a risk of non-compliance with the bending angle of the wire; It is determined whether the target electric energy meter has a fourth illegal wiring situation according to the wire label identification area, and the fourth illegal wiring situation includes that the wire label does not match.

2. The identification method according to claim 1, characterized in that: The determining whether the target electric energy meter has a first illegal wiring situation according to the wire metal layer identification area includes: Determine the metal layer circumscribed rectangle of the wire metal layer identification area; Determine the pixel width and pixel height of the circumscribed rectangle of the metal layer; Determining whether the pixel width and pixel height of the circumscribed rectangle of the metal layer meet a first preset condition; If yes, determining the pixel ratio of the wire metal layer identification area to the sum of the wire metal layer identification area and the wire insulation layer identification area; When the pixel ratio satisfies a second preset condition, it is determined that the first illegal wiring situation exists.

3. The identification method according to claim 1, characterized in that: The determining whether the target electric energy meter has a second illegal wiring situation according to the wire insulation layer identification area includes: Determine the insulation layer circumscribed rectangle of the wire insulation layer identification area; Determine the color order of all wire insulation layers in the insulation layer circumscribed rectangle; When the color sequence is inconsistent with the theoretical color sequence of the target electric energy meter, it is determined that the second illegal wiring situation exists.

4. The identification method according to claim 1, characterized in that: The determining, according to the wire key points, whether the target electric energy meter has a third illegal wiring situation comprises: Determine the target wire key point in the wire insulation layer identification area according to the wire key point; Determining the angle between adjacent wires in the wire insulation layer identification area according to the target wire key point; In the case that the included angle between at least one adjacent wire satisfies the third preset condition, it is determined that the third illegal wiring situation exists.

5. A system for identifying illegal wiring of electric energy meters, characterized in that: include: An image processing module, which obtains image information of a target electric energy meter, and determines, based on the image information, a wire metal layer identification area, a wire insulation layer identification area, a wire label identification area, and wire key points of all wires of the target electric energy meter; An information processing module determines whether the target electric energy meter has a first illegal wiring situation based on the wire metal layer identification area, the first illegal wiring situation includes the risk of the wire metal layer being exposed; determines whether the target electric energy meter has a second illegal wiring situation based on the wire insulation layer identification area, the second illegal wiring situation includes the risk of wrong wire connection; determines whether the target electric energy meter has a third illegal wiring situation based on the wire key points, the third illegal wiring situation includes the risk of non-compliant wire bending angles; determines whether the target electric energy meter has a fourth illegal wiring situation based on the wire label identification area, the fourth illegal wiring situation includes a mismatch in wire labels.

6. The identification system according to claim 5, characterized in that: The information processing module determines the metal layer circumscribed rectangle of the wire metal layer identification area; The information processing module determines the pixel width and pixel height of the circumscribed rectangle of the metal layer; The information processing module determines whether the pixel width and pixel height of the circumscribed rectangle of the metal layer meet a first preset condition; If yes, the information processing module determines the pixel ratio of the wire metal layer identification area to the sum of the wire metal layer identification area and the wire insulation layer identification area; The information processing module determines that the first illegal wiring situation exists when the pixel ratio meets a second preset condition.

7. The identification system according to claim 5, characterized in that: The information processing module determines the insulation layer circumscribed rectangle of the wire insulation layer identification area; The information processing module determines the color sequence of all the wire insulation layers in the insulation layer circumscribed rectangle; The information processing module determines that the second illegal wiring situation exists when the color sequence is inconsistent with the theoretical color sequence of the target electric energy meter.

8. The identification system according to claim 5, characterized in that: The information processing module determines the target wire key point in the wire insulation layer identification area according to the wire key point; The information processing module determines the angle between adjacent wires in the wire insulation layer identification area according to the target wire key point; The information processing module determines that the third illegal wiring situation exists when the angle between at least one adjacent wire satisfies the third preset condition.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the identification method as described in any one of claims 1-4.

10. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the identification method according to any one of claims 1 to 4 is implemented.

Images