A power scene change detection method and device, electronic equipment and storage medium

Abstract

This application discloses a method, apparatus, electronic device, and storage medium for detecting changes in a power scene. The method and apparatus are applied to an electronic device to detect changes in a power scene and obtain change detection results. Specifically, it involves acquiring two images of the same power scene at different times for comparison; performing image segmentation on the two images to obtain a first set of segmented regions and a second set of segmented regions; establishing cross-time-time region associations by performing region-level matching on the first and second sets of segmented regions, resulting in multiple region pairs; performing feature difference analysis on each region pair to obtain region change features; and determining the type of change in the power scene based on the region change features to obtain the change detection result. This solution improves the discrimination generalization ability and robustness, enabling timely detection of changes in the power scene.

Description

Technical Field

[0001] This application relates to the field of power operation and maintenance technology, and more specifically, to a method, device, electronic device, and storage medium for detecting changes in power scenarios. Background Technology

[0002] In the operation and maintenance of power systems, it is often necessary to compare and analyze the status of equipment at different times to determine whether there are changes in operating status, abnormal changes, or potential faults. Examples include changes in electricity meter readings, switch open / closed states, disconnector positions, indicator light on / off states, and damage, obstruction, or missing parts of equipment. Current technologies for detecting power scene changes mainly employ manual comparison, pixel-level target segmentation, and target detection. Manual methods are inefficient, and pixel-level target segmentation and target detection require large amounts of scene sample data for training. These methods generally suffer from insufficient robustness, poor interpretability, and limited generalization ability, making it difficult to meet the power system's requirements for high reliability, interpretability, and long-term evolution capabilities. Summary of the Invention

[0003] In view of this, this application provides a method, apparatus, electronic device and storage medium for detecting changes in power scenarios in real time, so as to improve detection efficiency.

[0004] To achieve the above objectives, the following solution is proposed:

[0005] A method for detecting changes in a power scenario, applied to electronic devices, is used to detect changes in a power scenario to obtain a change detection result. The change detection method includes the following steps:

[0006] For the same power scenario, two images to be compared are collected at different times. The two images to be compared include a first image and a second image.

[0007] The two images to be compared are segmented to obtain a first set of structural segmentation regions corresponding to the first image and a second set of structural segmentation regions corresponding to the second image.

[0008] By performing region-level matching on the first set of structural segmentation regions and the second set of structural segmentation regions, cross-time region association relationships are established, resulting in multiple region pairs.

[0009] For each of the aforementioned regions, a feature difference analysis is performed to obtain the regional change characteristics;

[0010] The change type of the power scenario is determined based on the regional change characteristics to obtain the change detection result.

[0011] Optionally, the step of performing image segmentation processing on the two images to be compared to obtain a first set of structural segmentation regions corresponding to the first image and a second set of structural segmentation regions corresponding to the second image includes the following steps:

[0012] A general image segmentation model is used to segment the first image and the second image respectively, and the resolvable structural regions are segmented into multiple segmentation mask regions to obtain the first structural region set and the second structural segmentation region set.

[0013] Optionally, the step of establishing cross-time region associations by performing region-level matching on the first set of structural segmentation regions and the second set of structural segmentation regions to obtain multiple region pairs includes the following steps:

[0014] Based on spatial location relationships, region-level matching is performed on the first set of structural segmentation regions and the second set of structural segmentation regions to obtain the multiple region pairs;

[0015] Alternatively, based on the region overlap relationship, perform region-level matching on the first structural segmentation region set and the second structural segmentation region set to obtain multiple region pairs;

[0016] Alternatively, based on geometric morphological features, region-level matching can be performed on the first set of segmented structural regions and the second set of segmented structural regions to obtain multiple region pairs;

[0017] Alternatively, region-level matching can be performed on the first set of structural segmentation regions and the second set of structural segmentation regions based on visual feature similarity to obtain multiple region pairs.

[0018] Optionally, the step of performing feature difference analysis on each of the regions to obtain regional change characteristics includes the following steps:

[0019] For each pair of regions, extract the features of each region;

[0020] By comparing and analyzing the features of the two regions, the variation characteristics of the regions are obtained.

[0021] Optionally, the feature may be a geometric feature, a visual feature, a semantic feature, or a state feature.

[0022] Optionally, the step of determining the change type of the power scenario based on the regional change characteristics to obtain the change detection result includes the following steps:

[0023] Based on the characteristics of regional changes, rule-based discrimination, statistical analysis, or machine learning models are used to determine the type of regional changes, thereby obtaining the change detection results.

[0024] Optionally, the change detection results include one or more of the following: numerical change, state change, structural change, addition or missing change, and abnormal change.

[0025] A power scenario change detection device, applied to electronic equipment, is used to detect changes in the power scenario to obtain change detection results. The change detection device includes:

[0026] The image acquisition module is configured to acquire two images to be compared at different times for the same power scenario, the two images to be compared including a first image and a second image;

[0027] The image segmentation module is configured to perform image segmentation processing on the two images to be compared, respectively, to obtain a first structural segmentation region set corresponding to the first image and a second structural segmentation region set corresponding to the second image.

[0028] The region matching module is configured to establish cross-time region associations by performing region-level matching on the first set of structural segmented regions and the second set of structural segmented regions, thereby obtaining multiple region pairs.

[0029] The feature analysis module is configured to perform feature difference analysis for each pair of regions to obtain regional change features;

[0030] The detection execution module is configured to determine the change type of the power scenario based on the change characteristics of the region, and obtain the change detection result.

[0031] An electronic device includes at least one processor and a memory connected to the processor, wherein:

[0032] The memory is used to store computer programs or instructions;

[0033] The processor is used to execute the computer program or instructions to enable the electronic device to implement the power scene change detection method as described above.

[0034] A computer-readable storage medium is applied to an electronic device, the storage medium carrying one or more computer programs that can be executed by the electronic device, thereby enabling the electronic device to implement the power scene change detection method as described above.

[0035] As can be seen from the above technical solution, this application discloses a method, apparatus, electronic device, and storage medium for detecting changes in power scenarios. This method and apparatus are applied to electronic devices to detect changes in power scenarios and obtain change detection results. Specifically, it involves acquiring two images to be compared at different times for the same power scenario; performing image segmentation on the two images to obtain a first set of segmented regions and a second set of segmented regions; establishing cross-time-time region associations by performing region-level matching on the first and second sets of segmented regions, resulting in multiple region pairs; performing feature difference analysis on each region pair to obtain region change features; and judging the type of change in the power scenario based on the region change features to obtain the change detection result. This solution can detect changed regions without relying on a large number of samples for training, thereby improving the detection generalization ability and robustness, and enabling timely detection of changes in power scenarios. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart of a method for detecting changes in a power scenario according to an embodiment of this application;

[0038] Figure 2 This is a block diagram of a power scene change detection device according to an embodiment of this application;

[0039] Figure 3 This is a block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0040] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0041] Figure 1 This is a flowchart of a method for detecting changes in a power scenario according to an embodiment of this application.

[0042] like Figure 1As shown, the power scenario change detection method provided in this embodiment is applied to an electronic device to effectively detect changes in the power scenario. This electronic device can be understood as a computer, server, or cloud platform with data computing and information processing capabilities. The change detection method specifically includes the following steps:

[0043] S1. Collect two images to be compared at different times for the same power scenario.

[0044] The power scenario can include distribution areas, transformers, main control rooms, and power lines—any location where changes need to be detected. High-definition cameras or digital cameras can be used to capture images, resulting in two images for comparison. For ease of description, the images to be compared are the initial first image (representing the original state) and the second image captured at specific points in time.

[0045] S2. Perform image segmentation processing on the images to be compared to obtain a first set of segmented regions and a second set of segmented regions.

[0046] That is, image segmentation processing is performed on the first image to obtain a set of first structure segmentation regions including multiple first structure segmentation regions. Similarly, image segmentation processing is performed on the second image to obtain a set of second structure segmentation regions including multiple second structure segmentation regions. In the specific implementation of image segmentation processing, this application uses a general image segmentation model to process the input image. The general image segmentation model can segment the resolvable structural regions in the image without predefined categories, generating multiple non-overlapping or partially overlapping segmentation mask regions.

[0047] The structural segmentation regions include, but are not limited to, the overall area of ​​the power equipment, the local structural area of ​​the equipment, the display area, the operation panel area, and the background structural area. Since the change detection categories under power conditions are not fixed, using predefined categories can easily lead to missed changes, while general segmentation models such as transformers can effectively reduce the missed detection rate.

[0048] In this application, the so-called structural segmentation region refers to a spatially connected, visually consistent, and sustainably matchable region unit automatically extracted from images of power scenes by a general image segmentation model. It does not rely on predefined equipment categories or semantic labels, but is formed based on the visual structural features in the image, serving as the basic object for cross-time-lapse change analysis. Its domain can characterize the overall structure, local structure, functional areas, or background structure of power equipment, and changes in its shape, position, or visual features can be used to reflect changes in the operating state of the power equipment.

[0049] Structural segmentation regions, as fundamental objects for power scenario change analysis, can characterize the overall structure, local composition, or related background structure of power equipment. For the same power scenario, structural segmentation regions exhibit a certain degree of stability in spatial location, morphology, or visual features at different acquisition times, thus supporting cross-time-based regional correlation and comparative analysis. Changes in the morphology, location, visual attributes, or existence of structural segmentation regions can all serve as evidence reflecting changes in the operating status of power equipment.

[0050] S3. By performing region-level matching on the first and second structure segmentation regions, cross-time region associations are established, resulting in multiple region pairs.

[0051] Specifically, this involves matching structurally segmented regions at the same location at different times. Region-level matching is based on the similarity of structurally segmented regions in terms of spatial and visual features. Matching methods include one or more of the following:

[0052] 1) Matching based on spatial location: Determine candidate matching regions based on the geometric center position, bounding box position, or relative spatial layout relationship of the structural segmentation region in the image;

[0053] 2) Matching based on region overlap: Based on image alignment or registration, the matching relationship is determined according to the overlap of the bounding boxes or the cross-union ratio of the mask in the images of the structural segmentation region at different times;

[0054] 3) Matching based on geometric morphological features: By comparing the area ratio, perimeter, aspect ratio, or shape description features of structurally segmented regions, pairs of regions with similar morphology are identified.

[0055] 4) Matching based on visual feature similarity: Visually similar regions are determined by comparing the color distribution, texture features, depth features, or feature vectors extracted by the depth model of the structural segmentation regions.

[0056] During the matching process, a matching confidence threshold can be set for each structural segmentation region. When the similarity of candidate regions meets the preset conditions, a cross-timeframe structural region correspondence is established. When no corresponding region meeting the conditions is found, the structural segmentation region can be marked as a newly added or missing region for subsequent change type discrimination. In this way, a correspondence between images of the same structural region at different times is established. The specific implementation method is as follows:

[0057] Let the set of the first structural segmentation regions corresponding to the first image be:

[0058]

[0059] The set of second-structure segmentation regions corresponding to the second image is:

[0060] Here, t and t+1 represent images acquired at two different times. In defect identification, the image at time t is usually the reference image, and the image at time t+1 is the image at the time to be detected. and These represent the i-th and j-th structural regions at two different time points.

[0061] For any pair of regions ( , ), calculate its comprehensive matching similarity S(i,sj), which is defined as:

[0062] ,

[0063] Where α, β, and γ are weighting coefficients, and α+β+γ=1;

[0064] Indicates spatial similarity. Indicates geometric similarity. Indicates visual feature similarity.

[0065] Geometric similarity matching is implemented as follows:

[0066] Spatial similarity Calculate based on the distance d(i,j) between the geometric centers of the regions:

[0067] ,

[0068] in, This represents the spatial scale control parameter, which adjusts the degree of influence of spatial distance on similarity attenuation. It can be adaptively set according to image resolution and device scale.

[0069] Geometric similarity S_geo(i,j) is calculated based on region area ratio or shape difference:

[0070]

[0071] Where A represents the area.

[0072] Visual feature similarity Calculated based on cosine similarity or Euclidean distance of region feature vectors. When S(i,j) is greater than a preset matching threshold θ, the region is determined. and For matching region pairs; when no matching region meets the conditions, the corresponding region is marked as a new region or a missing region for subsequent change type determination.

[0073] S4. Perform feature difference analysis for each region to obtain regional change characteristics.

[0074] After obtaining multiple region pairs, region-level features are extracted from the first and second structural segmentation regions in each region pair, and quantitative comparative analysis is performed on the features at different times. Region-level features include at least one of the following: geometric features, visual features, semantic features, and state features. Geometric features refer to region area, perimeter, aspect ratio, and shape change rate; visual features refer to color distribution, brightness variation, texture features, or depth features; semantic features refer to text recognition results, symbol recognition results, or state indication features within the region; state features refer to the existence, occlusion degree, or integrity features of structures within the region. By comparing region features at different times, a description of region change features is generated.

[0075] In one implementation, for matching region pairs ( , ), extract feature vectors respectively and The feature vector must include at least geometric features, visual features, or state features. The region variation feature Δf can be expressed as:

[0076] ,

[0077] Here, Δf is used to characterize the degree of change of the corresponding structural segmentation region at different times.

[0078] In one implementation, the area change rate ΔA can be defined for geometric features:

[0079] ,

[0080] For visual features, color histogram differences, mean brightness differences, or texture feature distances can be calculated; for state features, binary or multi-valued descriptions can be performed based on whether a region exists, whether it is occluded, or whether its integrity changes.

[0081] When the change characteristics of a region exceed the corresponding change threshold, it is determined that the segmented region of the structure has changed, and the change result is used as the basis for determining the change type.

[0082] S5. Based on regional change characteristics, the change type of the power scenario is identified to obtain the change detection results.

[0083] Based on the aforementioned regional change characteristics, rule-based discrimination, statistical analysis, or machine learning models are used to identify the types of regional changes, thereby obtaining the change detection results for the power scenario. Change types include, but are not limited to, partial or complete variations of numerical changes, state changes, structural changes, new or missing changes, and anomalous changes.

[0084] As can be seen from the above technical solution, this embodiment provides a method for detecting changes in a power scene. This method is applied to electronic devices to detect changes in a power scene and obtain change detection results. Specifically, it involves acquiring two images to be compared at different times for the same power scene; performing image segmentation processing on the two images to obtain a first set of structural segmentation regions and a second set of structural segmentation regions; establishing cross-time-time regional associations by performing region-level matching on the first set of structural segmentation regions and the second set of structural segmentation regions to obtain multiple region pairs; performing feature difference analysis on each region pair to obtain regional change features; and judging the change type of the power scene based on the regional change features to obtain change detection results.

[0085] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0086] Although the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous.

[0087] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0088] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer.

[0089] Figure 2 This is a block diagram of a power scene change detection device according to an embodiment of this application.

[0090] like Figure 2 As shown, the power scenario change detection device provided in this embodiment is applied to an electronic device to effectively detect changes in the power scenario. This electronic device can be understood as a computer, server, or cloud platform with data computing and information processing capabilities. Specifically, the change detection device includes an image acquisition module 10, an image segmentation module 20, a region matching module 30, a feature analysis module 40, and a detection execution module 50.

[0091] The image acquisition module is used to acquire two images to be compared at different times for the same power scene.

[0092] The power scenario can be a distribution area, transformer, main control room, or power lines—any location where changes need to be detected. High-definition cameras or digital cameras can be used to capture images, resulting in two images for comparison. For ease of description, the images to be compared are an initial first image (representing the original state) and one or more second images captured at specific points in time.

[0093] The image segmentation module is used to perform image segmentation processing on the images to be compared, resulting in a first set of structural segmentation regions and a second set of structural segmentation regions.

[0094] That is, image segmentation processing is performed on the first image to obtain a set of first structure segmentation regions including multiple first structure segmentation regions. Similarly, image segmentation processing is performed on the second image to obtain a set of second structure segmentation regions including multiple second structure segmentation regions. In the specific implementation of image segmentation processing, this application uses a general image segmentation model to process the input image. The general image segmentation model can segment the resolvable structural regions in the image without predefined categories, generating multiple non-overlapping or partially overlapping segmentation mask regions.

[0095] The structural segmentation regions include, but are not limited to, the overall area of ​​the power equipment, the local structural area of ​​the equipment, the display area, the operation panel area, and the background structural area. Since the change detection categories under power conditions are not fixed, using predefined categories can easily lead to missed changes, while general segmentation models such as transformers can effectively reduce the missed detection rate.

[0096] The region matching module is used to establish cross-time region associations by performing region-level matching on the first structure segmentation region set and the second structure segmentation region set, and obtain multiple region pairs.

[0097] Specifically, this involves matching structurally segmented regions at the same location at different times. Region-level matching is based on the similarity of structurally segmented regions in terms of spatial and visual features. Matching methods include one or more of the following:

[0098] 1) Matching based on spatial location: Determine candidate matching regions based on the geometric center position, bounding box position, or relative spatial layout relationship of the structural segmentation region in the image;

[0099] 2) Matching based on region overlap: Based on image alignment or registration, the matching relationship is determined according to the overlap of the bounding boxes or the cross-union ratio of the mask in the images of the structural segmentation region at different times;

[0100] 3) Matching based on geometric morphological features: By comparing the area ratio, perimeter, aspect ratio, or shape description features of structurally segmented regions, pairs of regions with similar morphology are identified.

[0101] 4) Matching based on visual feature similarity: Visually similar regions are determined by comparing the color distribution, texture features, depth features, or feature vectors extracted by the depth model of the structural segmentation regions.

[0102] The feature analysis module is used to perform feature difference analysis for each region to obtain regional change characteristics.

[0103] After obtaining multiple region pairs, region-level features are extracted from the first and second structural segmentation regions in each region pair, and quantitative comparative analysis is performed on the features at different times. Region-level features include at least one of the following: geometric features, visual features, semantic features, and state features. Geometric features refer to region area, perimeter, aspect ratio, and shape change rate; visual features refer to color distribution, brightness variation, texture features, or depth features; semantic features refer to text recognition results, symbol recognition results, or state indication features within the region; state features refer to the existence, occlusion degree, or integrity features of structures within the region. By comparing region features at different times, a description of region change features is generated.

[0104] The detection execution module is used to identify the type of change in the power scenario based on regional change characteristics and obtain change detection results.

[0105] Based on the aforementioned regional change characteristics, rule-based discrimination, statistical analysis, or machine learning models are used to identify the types of regional changes, thereby obtaining the change detection results for the power scenario. Change types include, but are not limited to, partial or complete variations of numerical changes, state changes, structural changes, new or missing changes, and anomalous changes.

[0106] As can be seen from the above technical solution, this embodiment provides a power scene change detection device. This device is applied to electronic equipment to detect changes in the power scene and obtain change detection results. Specifically, it acquires two images to be compared at different times for the same power scene; performs image segmentation processing on the two images to obtain a first structural segmentation region set and a second structural segmentation region set; establishes cross-time-time regional correlation by performing region-level matching on the first and second structural segmentation region sets, obtaining multiple region pairs; performs feature difference analysis on each region pair to obtain regional change features; and determines the change type of the power scene based on the regional change features to obtain change detection results. This solution improves the discrimination generalization ability and robustness, and can promptly detect changes in the power scene.

[0107] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0108] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0109] Figure 3 This is a block diagram of an electronic device according to an embodiment of this application.

[0110] The following is for reference. Figure 3 This document illustrates a structural diagram suitable for implementing the electronic device in the embodiments of this disclosure. The terminal device in the embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. This electronic device is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this disclosure.

[0111] The electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from an input device 306 into a random access memory (RAM) 303. The RAM also stores various programs and data required for the operation of the electronic device. The processing unit, ROM, and RAM are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0112] Typically, the following devices can be connected to the I / O interface: input devices including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows the electronic device to communicate wirelessly or wiredly with other devices to exchange data. Although electronic devices with various devices are shown in the figures, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0113] This application provides an embodiment of a computer-readable storage medium.

[0114] The aforementioned computer-readable storage medium is applied to an electronic device and carries one or more computer programs. When these programs are executed by the electronic device, the device acquires two images to be compared at different times for the same power scenario. The two images are then segmented to obtain a first set of segmented regions and a second set of segmented regions. Region-level matching is performed on the first and second sets of segmented regions to establish cross-time-time region associations, resulting in multiple region pairs. Feature difference analysis is performed on each region pair to obtain region change features. Based on these region change features, the type of change in the power scenario is determined, yielding a change detection result. This scheme improves the discrimination generalization ability and robustness, enabling timely detection of changes in the power scenario.

[0115] It should be noted that the computer-readable medium described above in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0116] In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0117] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0118] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0119] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0120] The technical solution provided by the present invention has been described in detail above. Specific examples have been used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for detecting changes in a power scenario, applied to electronic equipment, for detecting changes in a power scenario to obtain change detection results, characterized in that, The change detection method includes the following steps: For the same power scenario, two images to be compared are collected at different times. The two images to be compared include a first image and a second image. The two images to be compared are segmented to obtain a first set of structural segmentation regions corresponding to the first image and a second set of structural segmentation regions corresponding to the second image. By performing region-level matching on the first set of structural segmentation regions and the second set of structural segmentation regions, cross-time region association relationships are established, resulting in multiple region pairs. For each of the aforementioned regions, a feature difference analysis is performed to obtain the regional change characteristics; The change type of the power scenario is determined based on the regional change characteristics to obtain the change detection result.

2. The change detection method as described in claim 1, characterized in that, The step of performing image segmentation processing on the two images to be compared to obtain a first set of structural segmentation regions corresponding to the first image and a second set of structural segmentation regions corresponding to the second image includes the following steps: A general image segmentation model is used to segment the first image and the second image respectively, and the resolvable structural regions are segmented into multiple segmentation mask regions to obtain the first structural region set and the second structural segmentation region set.

3. The change detection method as described in claim 1, characterized in that, The step of establishing cross-time region associations by performing region-level matching on the first set of structural segmentation regions and the second set of structural segmentation regions to obtain multiple region pairs includes the following steps: Based on spatial location relationships, region-level matching is performed on the first set of structural segmentation regions and the second set of structural segmentation regions to obtain the multiple region pairs; Alternatively, based on the region overlap relationship, perform region-level matching on the first structural segmentation region set and the second structural segmentation region set to obtain multiple region pairs; Alternatively, based on geometric morphological features, region-level matching can be performed on the first set of segmented structural regions and the second set of segmented structural regions to obtain multiple region pairs; Alternatively, region-level matching can be performed on the first set of structural segmentation regions and the second set of structural segmentation regions based on visual feature similarity to obtain multiple region pairs.

4. The change detection method as described in claim 1, characterized in that, The step of performing feature difference analysis on each of the regions to obtain regional change characteristics includes the following steps: For each pair of regions, extract the features of each region; By comparing and analyzing the features of the two regions, the variation characteristics of the regions are obtained.

5. The change detection method as described in claim 4, characterized in that, The features are geometric features, visual features, semantic features, or state features.

6. The change detection method as described in claim 1, characterized in that, The step of determining the change type of the power scenario based on the regional change characteristics to obtain the change detection result includes the following steps: Based on the characteristics of regional changes, rule-based discrimination, statistical analysis, or machine learning models are used to determine the type of regional changes, thereby obtaining the change detection results.

7. The change detection method as described in claim 6, characterized in that, The change detection results include one or more of the following: numerical changes, state changes, structural changes, additions or omissions, and abnormal changes.

8. A power scene change detection device, applied to electronic equipment, for detecting changes in the power scene to obtain change detection results, characterized in that, The change detection device includes: The image acquisition module is configured to acquire two images to be compared at different times for the same power scenario, the two images to be compared including a first image and a second image; The image segmentation module is configured to perform image segmentation processing on the two images to be compared, respectively, to obtain a first structural segmentation region set corresponding to the first image and a second structural segmentation region set corresponding to the second image. The region matching module is configured to establish cross-time region associations by performing region-level matching on the first set of structural segmented regions and the second set of structural segmented regions, thereby obtaining multiple region pairs. The feature analysis module is configured to perform feature difference analysis for each pair of regions to obtain regional change features; The detection execution module is configured to determine the change type of the power scenario based on the change characteristics of the region, and obtain the change detection result.

9. An electronic device, characterized in that, The electronic device includes at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs or instructions; The processor is used to execute the computer program or instructions to enable the electronic device to implement the power scene change detection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium for use in electronic devices, characterized in that, The storage medium carries one or more computer programs that can be executed by the electronic device, thereby enabling the electronic device to implement the power scene change detection method as described in any one of claims 1 to 7.

Images