Method, apparatus, and electronic device for verifying the consistency between a drawing and reality based on on-site images

Abstract

The present application relates to a method, device and electronic device for verifying the consistency between a drawing and the actual situation based on on-site images. Among them, the method for verifying the consistency between a drawing and the actual situation includes: obtaining a plurality of partial on-site images of a power grid under a vertical view captured by a drone; respectively identifying the plurality of on-site images, and the identification results include the positions, shapes and their identification information of power grid equipment, and the power grid equipment with the same identification information is the same power grid equipment; splicing different partial on-site images based on the shapes of the same power grid equipment in different partial on-site images to obtain a global on-site image of the power grid; determining the global actual topological structure of the power grid based on the positions and identification information of each power grid equipment in the global on-site image and the connection relationship between different power grid equipment; verifying the global actual topological structure of the power grid and the topological structure of the power grid model. It solves the problem that the current method for verifying the consistency between a drawing and the actual situation can usually only verify the connection relationship between each power grid equipment.

Description

Technical Field

[0001] This application relates to the field of power grids, and in particular, to a method, device, and electronic device for verifying the consistency between a drawing and reality based on on-site images. Background Art

[0002] In a distribution network, the topological relationship between power grid devices needs to be focused on, which determines the operating conditions of the distribution network. However, in actual scenarios, due to scene environmental factors, the actual topological structure of the distribution network may differ from the ideal topological structure, and thus it is necessary to verify the consistency between the drawing and reality, that is, to determine the difference between the actual topological structure of the distribution network and the topological structure of the designed distribution network model.

[0003] In a current method for verifying the consistency between a drawing and reality, an on-site image of the distribution network is taken by a drone and the topological relationship between the power grid devices in the on-site image is identified, and then compared with the topological structure of the distribution network model to determine the difference between the two. Then, in the current method for verifying the consistency between a drawing and reality, mainly local comparisons are made based on different on-site images, that is, it is respectively determined whether the topological relationship between the power grid devices in each on-site image is correct. However, this method for verifying the consistency between a drawing and reality usually can only verify the connection relationship between each power grid device, but cannot verify the relative position relationship between each power grid device. For example, there are power grid devices A and B in one image, and power grid devices B and C in another image. At this time, it can only be verified whether the connection relationship between power grid devices A and B and the connection relationship between power grid devices B and C are correct, but it cannot be verified whether the relative position relationship among power grid devices A, B, and C is correct.

[0004] Aiming at the problem that the current method for verifying the consistency between a drawing and reality based on on-site images usually can only verify the connection relationship between each power grid device, no effective solution has been proposed yet. Summary of the Invention

[0005] In the present invention, a method, device, and electronic device for verifying the consistency between a drawing and reality based on on-site images are provided to solve the problem that the current method for verifying the consistency between a drawing and reality based on on-site images usually can only verify the connection relationship between each power grid device.

[0006] In the first aspect, the present invention provides a method for verifying the consistency between a drawing and reality based on on-site images, including:

[0007] Obtaining a plurality of local on-site images of the power grid under a vertical perspective taken by a drone;

[0008] Respectively identifying the plurality of on-site images, and the identification results include the positions, shapes, and identification information of the power grid devices, and the power grid devices with the same identification information are the same power grid device;

[0009] Stitch different local on-site images based on the shapes of the same power grid equipment in different local on-site images to obtain the global on-site image of the power grid;

[0010] Based on the positions and identification information of each power grid equipment in the global on-site image and the connection relationship between different power grid equipments, determine the global actual topological structure of the power grid;

[0011] Verify the global actual topological structure of the power grid and the topological structure of the power grid model.

[0012] In some embodiments, stitching different local on-site images based on the shapes of the same power grid equipment in different local on-site images includes:

[0013] Determine a reference on-site image in the several local on-site images, and determine other local on-site images with some power grid equipment the same as that in the reference on-site image as the to-be-stitched on-site images;

[0014] Stitch the to-be-stitched on-site image and the reference on-site image based on the shapes of the same power grid equipment in the to-be-stitched on-site image and the reference on-site image to form a new reference on-site image.

[0015] In some embodiments, stitching the to-be-stitched on-site image and the reference on-site image based on the shapes of the same power grid equipment in the to-be-stitched on-site image and the reference on-site image includes:

[0016] When there is a pair of the same power grid equipment in the to-be-stitched on-site image and the reference on-site image, respectively determine the shape feature points of the pair of the same power grid equipment, and the shape feature points are feature points that can be uniquely determined according to the shape;

[0017] Move the position of the to-be-stitched on-site image to make the shape feature points of the pair of the same power grid equipment coincide;

[0018] Rotate and scale the to-be-stitched on-site image based on the coincident shape feature points to make the shapes of the pair of the same power grid equipment coincide;

[0019] When there are more than two pairs of the same power grid equipment in the to-be-stitched on-site image and the reference on-site image, determine the shape feature points of two pairs of the same power grid equipment;

[0020] Transform the to-be-stitched on-site image to make the shape feature points of the two pairs of the same power grid equipment correspond and coincide.

[0021] In some embodiments, the shape feature point is one of the geometric center of the shape, the center of the minimum circumscribed circle, and the center of the maximum inscribed circle.

[0022] In some of these embodiments, the shape feature point is the geometric center of the shape;

[0023] Rotating and scaling the on-site image to be stitched based on the coincident shape feature points so that the shapes of the pair of identical power grid devices coincide includes:

[0024] Rotating the on-site image to be stitched around the coincident shape feature points and continuously calculating the sequence of shape boundary distances of the pair of identical power grid devices during the rotation until the volatility of the sequence of shape boundary distances is minimized. The sequence of shape boundary distances includes the distances of the shape boundaries of the pair of identical power grid devices in each scattering direction of the coincident shape feature points;

[0025] Scaling the on-site image to be stitched with the coincident shape feature point as the scaling base point so that the shapes of the pair of identical power grid devices coincide.

[0026] In some of these embodiments, scaling the on-site image to be stitched with the coincident shape feature point as the scaling base point so that the shapes of the pair of identical power grid devices coincide includes:

[0027] Scaling the on-site image to be stitched with the coincident shape feature point as the scaling base point and continuously calculating the sequence of shape boundary distances of the pair of identical power grid devices during the scaling until the scalar average value of the sequence of shape boundary distances is minimized.

[0028] In some of these embodiments, transforming the on-site image to be stitched so that the shape feature points of the two pairs of identical power grid devices correspond and coincide includes:

[0029] Connecting two feature points in the on-site image to be stitched to form a first line segment, and connecting two feature points in the reference on-site image to form a second line segment;

[0030] Moving the on-site image to be stitched so that the shape feature points of one pair of identical power grid devices coincide;

[0031] Rotating the on-site image to be stitched around the coincident shape feature points so that the first line segment and the second line segment coincide;

[0032] Scaling the on-site image to be stitched with the coincident shape feature point as the scaling base point so that the shape feature points of the other pair of identical power grid devices coincide.

[0033] In a second aspect, the present invention provides a device for verifying the consistency between a drawing and reality based on an on-site image, including:

[0034] An image acquisition module, configured to acquire a plurality of local on-site images of a power grid captured by a drone based on a vertical perspective;

[0035] An image recognition module, configured to respectively recognize the plurality of on-site images, and the recognition results include the positions, shapes, and identification information of power grid devices. Power grid devices with the same identification information are the same power grid device;

[0036] An image stitching module, configured to stitch different local on-site images based on the shapes of the same power grid devices in different local on-site images to obtain a global on-site image of the power grid;

[0037] A topology generation module, configured to determine the global actual topology structure of the power grid based on the positions and identification information of each power grid device in the global on-site image and the connection relationship between different power grid devices;

[0038] A topology verification module, configured to verify the global actual topology structure of the power grid and the topology structure of the power grid model.

[0039] In a third aspect, the present invention provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the method for verifying the drawing-reality consistency based on on-site images described in the first aspect.

[0040] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for verifying the drawing-reality consistency based on on-site images described in the first aspect are implemented.

[0041] Compared with the related art, the present invention stitches a plurality of local on-site images into a global on-site image. Since the positions, identification information of each power grid device in the global on-site image and the connection relationship between different power grid devices are all known, a global actual topology structure of the power grid can be constructed. Moreover, the global actual topology structure is a spatial topology structure including the relative position information of each node. By comparing the global actual topology structure and the topology structure of the power grid model, it is not only possible to determine whether the connection relationship between each power grid device is correct, but also possible to determine whether the relative position relationship between each power grid device is correct, solving the problem that the existing method for verifying the drawing-reality consistency based on on-site images usually can only verify the connection relationship between each power grid device.

[0042] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more concise and understandable. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1It is a flowchart of the method for verifying the consistency between the drawing and the actual situation based on the on-site image provided in this embodiment. Detailed implementation manners

[0044] To understand the purpose, technical solution and advantages of this application more clearly, the following describes and explains this application in combination with the drawings and embodiments.

[0045] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by those with ordinary skills in the technical field to which this application belongs. In this application, words such as "a", "one", "a kind of", "the", "these" and the like do not indicate a limitation in quantity, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent in these processes, methods, products or devices. The terms "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly connected. The "plurality" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may represent: A exists alone, A and B exist simultaneously, and B exists alone. Usually, the character " / " indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third" and the like involved in this application are only used to distinguish similar objects and do not represent a specific sorting of the objects.

[0046] In this embodiment, a method for verifying the consistency between the drawing and the actual situation based on the on-site image is provided. Figure 1 It is a flowchart of the method for verifying the consistency between the drawing and the actual situation based on the on-site image provided in this embodiment, as Figure 1 shown. This process includes step S110, step S120, step S130, step S140 and step S150.

[0047] Step S110: Obtain a number of local on-site images of the power grid from a vertical perspective taken by a drone.

[0048] Before the implementation of the method for verifying the consistency between the drawing and the actual situation in this embodiment, it is necessary to take pictures of the power grid site by using a drone. Since the method for verifying the consistency between the drawing and the actual situation in this embodiment requires obtaining images from a vertical perspective, the drone needs to take pictures of the power grid site from a vertical perspective. Specifically, during the horizontal flight of the drone, the camera perspective is always vertically downward to avoid perspective distortion of the image as much as possible. For slight perspective distortion of the image caused by the jitter of the drone, the image can be transformed and corrected by using perspective correction technology.

[0049] Step S120: Identify several on-site images respectively. The identification results include the positions, shapes and their identification information of power grid equipment. Power grid equipment with the same identification information is the same power grid equipment.

[0050] Power grid equipment includes equipment such as poles, switches, transformers and generators. Since there are differences and specificities in the shapes of different power grid equipment, the power grid equipment in the image can be identified by using image recognition technology, and the shape contours and positions (positions in the image coordinate system) of each power grid equipment can be given. At the same time, identification information is marked on the power grid equipment, such as equipment ID and equipment nameplate information. Therefore, the identification information of each power grid equipment can be identified by using image recognition technology, and different power grid equipment can be distinguished. In summary, the shape and its identification information of power grid equipment can be obtained through currently relatively mature image recognition technology.

[0051] In this embodiment, a neural network model is used to perform the image recognition task. Among them, the shape recognition of power grid equipment can be realized through object detection tasks and instance segmentation tasks, that is, the positioning and shape detection of power grid equipment are completed by combining an object detection model and an instance segmentation model. For example, the object detection model can adopt YOLOv8, which outputs the bounding box and class label of the power grid equipment. The instance segmentation model can adopt Mask R-CNN, which generates a pixel-level mask based on object detection and accurately extracts the contour shape of the power grid equipment. The identification information of power grid equipment can be realized through a text recognition task, that is, a text recognition model is used to complete the extraction of the identification information. For example, the text recognition model can adopt CRNN, and its output is structured text such as the ID and nameplate information of each power grid equipment. By combining multiple models, a multi-task model can be obtained. Through this multi-task model, the power grid equipment in the image can be positioned and its shape and identification information can be recognized.

[0052] It should be noted that the image recognition in this step can be realized based on currently mature image recognition technology, which is not the focus of this invention, so it will not be further described.

[0053] Step S130: Stitch different local on-site images based on the shapes of the same power grid equipment in different local on-site images to obtain a global on-site image of the power grid.

[0054] In this step, different local on-site images are stitched together to form a global on-site image. Image stitching is mainly achieved through the identical parts in two images. Specifically, since the shapes and logo information of power grid equipment in each local on-site image have been identified in the previous step, based on the logo information, it can be determined whether there are identical power grid equipment in any two local on-site images. If so, there must be extremely similar or even identical shape graphics (corresponding to the same power grid equipment) in the corresponding two local on-site images, and then the stitching can be performed based on this pair of shape graphics.

[0055] In this embodiment, a new image stitching method applicable to power grid image stitching is also provided. Among them, step S130 specifically includes step S131 and step S132.

[0056] Step S131, determine a reference on-site image among several local on-site images, and determine other local on-site images with some power grid equipment identical to that in the reference on-site image as the to-be-stitched on-site images.

[0057] Step S132, stitch the to-be-stitched on-site images and the reference on-site image based on the shapes of the identical power grid equipment in the to-be-stitched on-site images and the reference on-site image to form a new reference on-site image.

[0058] In this embodiment, a local on-site image is randomly used as the reference on-site image, and then the to-be-stitched on-site images that can be stitched with this reference on-site image are determined. Finally, the stitched image is used as the new reference on-site image until there are no local on-site graphics that meet the stitching conditions, and then the final reference on-site image is used as the global on-site image. Among them, the stitching conditions include: there is at least one pair of identical power grid equipment (the basis for realizing image stitching) between the to-be-stitched on-site image and the reference on-site image, and only some power grid equipment in the to-be-stitched on-site image is identical to that in the reference on-site image. If all the power grid equipment in the on-site image exists in the reference on-site image, it means that this on-site image will not provide additional power grid topology information, and thus does not need to participate in the stitching to improve the image stitching efficiency.

[0059] Through the above stitching method, the local on-site images can be stitched into a global on-site image orderly and efficiently. Compared with other random and disordered stitching methods, it has higher stitching efficiency.

[0060] Furthermore, in this embodiment, step S132 includes step S132a, step S132b, step S132c, step S132d and step S132e.

[0061] Step S132a: When there is a pair of identical power grid devices in the to-be-stitched on-site image and the reference on-site image, respectively determine the shape feature points of the pair of identical power grid devices. The shape feature points are feature points that can be uniquely determined according to the shape. In this step, the shape feature points are the geometric centers of the shapes.

[0062] Step S132b: Move the position of the to-be-stitched on-site image to make the shape feature points of the pair of identical power grid devices coincide.

[0063] Step S132c: Rotate and scale the to-be-stitched on-site image based on the coincident shape feature points to make the shapes of the pair of identical power grid devices coincide.

[0064] For Step S132a, Step S132b, and Step S132c, they are mainly used to implement image stitching when there is only one pair of identical power grid devices in two images. For example, if there is only one power grid device A in the to-be-stitched on-site image and one power grid device B in the reference on-site image, and they are the same power grid device, then power grid device A and power grid device B form a pair of identical power grid devices. Essentially, they are the same power grid device, just existing in different images.

[0065] Specifically, in the case of no perspective difference, determining the translation relationship and rotation relationship between two images is required to complete the stitching of the two images. In this embodiment, innovatively, the shape feature points of the identical power grid devices are used as the reference points for moving and rotating the to-be-stitched on-site image. First, determine the shape feature points of the identical power grid devices in the two images. By moving the to-be-stitched image to make the two corresponding graphic feature points coincide, the translation operation of the to-be-stitched image is completed, that is, the translation error between the two images is eliminated. Further, it is also necessary to eliminate the rotation angle error and scaling ratio error (this error is caused by different shooting heights of the unmanned aerial vehicle or formed by perspective correction) between the to-be-stitched image and the reference on-site image, and finally make the shapes of the two identical power grid devices completely coincide, thereby aligning the two images.

[0066] Further, in this embodiment, Step S132c specifically includes: rotating the to-be-stitched on-site image around the coincident shape feature points and continuously calculating the shape boundary distance sequence of a pair of identical power grid devices during the rotation until the volatility of the shape boundary distance sequence is the smallest. The shape boundary distance sequence includes the distances of the shape boundaries of a pair of identical power grid devices in each scattering direction of the coincident shape feature points; scaling the to-be-stitched on-site image with the coincident shape feature points as the scaling base point to make the shapes of a pair of identical power grid devices coincide.

[0067] Since the scaling ratios between the to-be - stitched image and the reference site image may be different, it is impossible to determine whether the rotation angle error has been eliminated by judging whether the shapes of two identical power grid devices completely overlap. In this embodiment, considering that for two figures with the same shape but different sizes, when there is no rotation error between the two figures (the connecting lines of corresponding points in the two figures point to the geometric center), the volatility of the shape boundary between them should be the smallest. For example, common regular polygons, matrices, circles, and ellipses all satisfy the above rules, and these figures are all common shapes of power grid devices. Exemplarily, for two squares with different sizes, when their geometric centers coincide and there is no rotation error, the minimum shape boundary distance between them is the distance between their shape boundaries in the vertical or horizontal direction, and the maximum shape boundary distance between them is the distance between their shape boundaries in the 45° diagonal direction. At this time, the difference between the maximum and minimum shape boundary distances is the smallest, and the change in the shape boundary distances in continuously different directions is gentle. When there is any rotation error between the two squares, the difference between the maximum and minimum shape boundary distances will become larger, and the change in the shape boundary distances in continuously different directions is more obvious. Therefore, in this embodiment, when the volatility of the shape boundary distance sequence is the smallest, the rotation of the to - be - stitched site image is stopped, which can effectively eliminate the rotation error between the to - be - stitched site image and the reference site image. Exemplarily, indicators such as the standard deviation, variance, and range of the shape boundary distance sequence can be used to characterize the volatility.

[0068] After eliminating the rotation error between the to - be - stitched site image and the reference site image, the scaling error between the two can be further eliminated. Since the rotation error has been eliminated, scaling the to - be - stitched site image with the coincident shape feature points as the scaling base points can make the shapes of the same power grid devices coincide.

[0069] Furthermore, considering the actual situation, it is difficult to completely eliminate the rotation error, and there may also be errors in perspective correction, making it impossible for the shapes of the same power grid devices to completely coincide. Therefore, scaling the to - be - stitched site image with the coincident shape feature points as the scaling base points to make the shapes of a pair of the same power grid devices coincide includes: scaling the to - be - stitched site image with the coincident shape feature points as the scaling base points, and continuously calculating the shape boundary distance sequence of a pair of the same power grid devices during the scaling process until the scalar average value of the shape boundary distance sequence is the smallest. In this embodiment, the scalar average value of the shape boundary distance sequences of two identical power grid devices is used to measure the shape coincidence degree of the two identical power grid devices. It can be understood that when the shapes of two identical power grid devices completely coincide, the scalar average value of the shape boundary distance sequences of the two identical power grid devices is 0. Therefore, when the scalar average value of the shape boundary distance sequences of the two identical power grid devices is the smallest, the scaling is stopped, and the image stitching is completed.

[0070] Step S132d: When there are more than two pairs of identical power grid devices in the to-be-stitched on-site image and the reference on-site image, determine the shape feature points of two pairs of the identical power grid devices. In this step, the shape feature point is one of the geometric center of the shape, the center of the minimum circumscribed circle, and the center of the maximum inscribed circle.

[0071] Step S132e: Transform the to-be-stitched on-site image so that the shape feature points of the two pairs of identical power grid devices correspond and coincide.

[0072] For Step S132d and Step S132e, they are mainly used to achieve image stitching when there are at least two pairs of identical power grid devices in two images. Compared with Step S132a, Step S132b, and Step S132c, they can achieve more efficient and rapid image stitching. It only needs to transform the to-be-stitched on-site image so that the shape feature points of the two pairs of identical power grid devices correspond and coincide. For example, if the power grid devices A1 and A2 in the to-be-stitched on-site image are the same devices as the power grid devices B1 and B2 in the reference on-site image respectively, it only needs to make the shape feature points of the power grid device A1 coincide with the shape feature points of the power grid device B1 and the shape feature points of the power grid device A2 coincide with the shape feature points of the power grid device B2.

[0073] Specifically, Step S132e includes: connecting two feature points in the to-be-stitched on-site image to form a first line segment, and connecting two feature points in the reference on-site image to form a second line segment; moving the to-be-stitched on-site image so that the shape feature points of one pair of identical power grid devices coincide; rotating the to-be-stitched on-site image around the coincident shape feature points so that the first line segment and the second line segment coincide; scaling the to-be-stitched on-site image with the coincident shape feature points as the scaling base point so that the shape feature points of the other pair of identical power grid devices coincide.

[0074] Exemplarily, assume that the power grid devices A1 and A2 in the to-be-stitched on-site image are the same devices as the power grid devices B1 and B2 in the reference on-site image respectively. Then the connection line of the shape feature points between the power grid device A1 and the power grid device B1 is the first line segment, and the connection line of the shape feature points between the power grid device A2 and the power grid device B2 is the second line segment. First, the to-be-stitched on-site image can be moved so that the shape feature points of the power grid device A1 and the power grid device B1 coincide to eliminate the translation error between the two images; then, rotate the to-be-stitched on-site image around the shape feature points of the power grid device A1 and the power grid device B1 so that the first line segment and the second line segment coincide to eliminate the rotation error between the two images; finally, scale the to-be-stitched on-site image with the shape feature points of the power grid device A1 and the power grid device B1 as the scaling base point so that the shape feature points of the power grid device A2 and the power grid device B2 coincide to eliminate the scaling error between the two images.

[0075] As can be seen from the above description, when there are at least two pairs of the same power grid devices in the to-be-stitched on-site image and the reference on-site image, the image stitching can be completed in a more efficient and rapid manner.

[0076] The above is the specific description of step S130. Through step S130, a global on-site image can be quickly and efficiently constructed based on a number of local on-site images.

[0077] Step S140: Determine the global actual topological structure of the power grid based on the positions and identification information of each power grid device in the global on-site image and the connection relationships between different power grid devices.

[0078] Since the positions (the positions of each power grid device in the local on-site image have been identified, and thus the positions of each power grid device in the stitched global on-site image are also known) and identification information of each power grid device have been identified in the previous steps, in the topological structure identification, only the connection relationships between each power grid device in the global on-site image need to be further identified. Power grid devices are mainly connected by cables. Therefore, by detecting the cables and judging the positions at both ends of the cables, the power grid devices connected by the cables can be determined, that is, the connection relationships between different power grid devices can be determined. Cable identification can be achieved through an instance segmentation task. For example, the U-Net with Attention model is used to identify the global on-site image, and its output is the pixel-level segmentation mask of the cable, so that the positions at both ends of the cable in the global on-site image can be determined, and then the power grid devices connected by each cable can be determined.

[0079] Step S150: Verify the global actual topological structure of the power grid and the topological structure of the power grid model.

[0080] Since the positions and identification information of each power grid device in the global on-site image and the connection relationships between different power grid devices are all known, the global actual topological structure of the power grid can be constructed. Moreover, this global actual topological structure is a spatial topological structure including the relative position information of each node. Comparing this global actual topological structure with the topological structure of the power grid model can not only judge whether the connection relationships between each power grid device are correct, but also judge whether the relative position relationships between each power grid device are correct, solving the problem that the current method for verifying the graph-reality consistency based on on-site images usually can only verify the connection relationships between each power grid device. Among them, the topological structure of the power grid model can be established in advance. During the establishment process, the connection relationships between each power grid device can be established based on the power grid CIM model, and the relative position relationships between each power grid device can be established in combination with the map system.

[0081] In this embodiment, a device for verifying the consistency between a drawing and the actual situation based on on-site images is further provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated here. The following terms such as "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0082] The device for verifying the consistency between a drawing and the actual situation based on on-site images includes: an image acquisition module, an image recognition module, an image stitching module, a topology generation module, and a topology verification module.

[0083] The image acquisition module is used to acquire a number of partial on-site images of the power grid taken by a drone from a vertical perspective.

[0084] The image recognition module is used to respectively recognize a number of on-site images. The recognition results include the positions, shapes, and their identification information of power grid equipment. Power grid equipment with the same identification information is the same power grid equipment.

[0085] The image stitching module is used to stitch different partial on-site images based on the shapes of the same power grid equipment in different partial on-site images to obtain a global on-site image of the power grid.

[0086] The topology generation module is used to determine the global actual topology structure of the power grid based on the positions and identification information of each power grid equipment in the global on-site image and the connection relationship between different power grid equipment.

[0087] The topology verification module is used to verify the global actual topology structure of the power grid and the topology structure of the power grid model.

[0088] It should be noted that the above-mentioned each module can be a functional module or a program module, and can be implemented either by software or by hardware. For the modules implemented by hardware, the above-mentioned each module can be located in the same processor; or the above-mentioned each module can also be located in different processors in any combined form.

[0089] In this embodiment, an electronic device is further provided, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the method for verifying the consistency between a drawing and the actual situation based on on-site images in this embodiment.

[0090] In this embodiment, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for verifying the consistency between a drawing and the actual situation based on on-site images in this embodiment are implemented.

[0091] It should be understood that the specific embodiments described herein are for explaining this application rather than limiting it. All other embodiments obtained by those of ordinary skill in the art without creative efforts according to the embodiments provided in this application fall within the scope of protection of this application.

[0092] Obviously, the attached drawings are only some examples or embodiments of this application. For those of ordinary skill in the art, this application can also be applied to other similar situations based on these drawings without creative efforts. Additionally, it can be understood that although the work done during this development process may be complex and time-consuming, for those of ordinary skill in the art, certain design, manufacturing, or production changes based on the technical content disclosed in this application are only routine technical means and should not be regarded as insufficient disclosure of this application.

Claims

1. A method for verifying image-reality consistency based on on-site images, characterized in that: include: Acquire several local on-site images of the power grid from a vertical perspective taken by a UAV; Recognizing the plurality of local site images respectively, wherein the recognition results include the position, shape, and mark information of the power grid equipment, and the power grid equipment with the same mark information is the same power grid equipment; Determining a reference scene image from the plurality of local scene images, and determining other local scene images having some power grid equipment identical to the power grid equipment in the reference scene image as scene images to be spliced; When the scene image to be spliced and the reference scene image have a pair of identical power grid devices, respectively determining shape feature points of the pair of identical power grid devices, where the shape feature points are feature points that can be uniquely determined based on the shape, and the shape feature points are the geometric centers of the shapes; Moving the positions of the on-site images to be spliced so that the shape feature points of the pair of identical power grid devices overlap; Rotating the on-site image to be stitched around the overlapping shape feature point and continuously calculating a shape boundary distance sequence of the pair of identical power grid devices during the rotation process until the fluctuation of the shape boundary distance sequence is minimized, the shape boundary distance sequence including distances between the shape boundaries of the pair of identical power grid devices in each scattering direction of the overlapping shape feature point; Scaling the on-site image to be stitched using the coincident shape feature points as scaling base points, and continuously calculating the shape boundary distance sequence of the pair of identical power grid devices during the scaling process until the scalar average value of the shape boundary distance sequence is minimized, thereby forming a new reference on-site image; Obtaining a global on-site image of the power grid; Determining a global actual topology of the power grid based on the location and marker information of each power grid device in the global on-site image and the connection relationship between different power grid devices; A global actual topology of the power grid and a model power grid topology are verified.

2. The method for verifying image-reality consistency based on on-site images according to claim 1, characterized in that: Also includes: When the scene image to be spliced and the reference scene image have two or more pairs of identical power grid devices, determining shape feature points of two pairs of identical power grid devices; The on-site image to be spliced is transformed so that the shape feature points of the two pairs of identical power grid devices coincide with each other, thereby forming a new reference on-site image.

3. The method for verifying image-reality consistency based on on-site images according to claim 2, characterized in that: Transforming the on-site images to be spliced so that the shape feature points of the two pairs of identical power grid devices coincide with each other includes: Connecting two feature points in the scene image to be spliced to form a first line segment, and connecting two feature points in the reference scene image to form a second line segment; Moving the on-site images to be spliced so that shape feature points of a pair of identical power grid devices overlap; Rotating the scene image to be spliced around the coincident shape feature point so that the first line segment and the second line segment coincide with each other; The on-site images to be spliced are scaled using the coincident shape feature points as scaling base points so that another pair of shape feature points of the same power grid equipment coincide with each other.

4. A device for verifying image-reality consistency based on on-site images, characterized in that: include: An image acquisition module is used to acquire a number of local on-site images of the power grid taken by the UAV based on a vertical perspective; An image recognition module is used to recognize the plurality of local site images respectively, wherein the recognition results include the position, shape and mark information of the power grid equipment, and the power grid equipment with the same mark information is the same power grid equipment; An image stitching module is configured to determine a reference scene image from the plurality of local scene images, and to determine other local scene images having some power grid equipment identical to the power grid equipment in the reference scene image as scene images to be stitched; when the scene image to be stitched and the reference scene image have a pair of identical power grid equipment, respectively determine shape feature points of the pair of identical power grid equipment, where a shape feature point is a feature point that can be uniquely determined based on a shape, and a shape feature point is a geometric center of a shape; move the positions of the scene images to be stitched so that the shape feature points of the pair of identical power grid equipment coincide; rotate the scene image to be stitched around the coincident shape feature point and continuously calculate a shape boundary distance sequence of the pair of identical power grid equipment during the rotation process until the volatility of the shape boundary distance sequence is minimized, wherein the shape boundary distance sequence includes the distance between the shape boundaries of the pair of identical power grid equipment in each scattering direction of the coincident shape feature point; scale the scene image to be stitched using the coincident shape feature point as a scaling base point, and continuously calculate the shape boundary distance sequence of the pair of identical power grid equipment during the scaling process until the scalar average value of the shape boundary distance sequence is minimized, thereby forming a new reference scene image; and obtain a global scene image of the power grid; a topology generation module, configured to determine a global actual topology of the power grid based on the location and marker information of each power grid device in the global on-site image and the connection relationship between different power grid devices; The topology verification module is used to verify the global actual topology structure of the power grid and the power grid model topology structure.

5. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the image-reality consistency verification method based on on-site images according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for verifying image-reality consistency based on on-site images according to any one of claims 1 to 3 are implemented.

Images