Manufacturing method and manufacturing system of power transmission and transformation scene change detection data set

Abstract

The invention relates to the technical field of local redrawing regulation and control, in particular to a power transmission and transformation scene change detection data set manufacturing method and system, and the method comprises the steps: obtaining redrawing instruction information which comprises target position information and a redrawing prompt word, and the target position information comprises a target redrawing center point and a redrawing area size; extracting a corresponding redrawing area image from the original scene image based on the target position information; identifying redrawing features contained in the redrawing prompt words, and determining corresponding redrawing content based on the redrawing features; identifying a scene resolution corresponding to the original scene image, and determining a local redrawing image based on the scene resolution, the redrawing area image and the redrawing content; a resulting scene image is determined based on the local redrawing image and the original scene image, and a change detection training dataset is determined based on the resulting scene image and the original scene image. According to the invention, the effectiveness of determining the change detection training data set is improved.

Description

Technical Field

[0001] The present application relates to the technical field of local redrawing control, and in particular to a method and system for producing a data set for detecting changes in power transmission and transformation scenarios. Background Art

[0002] Transmission and substations are usually located in complex outdoor environments. Traditional manual inspection methods are difficult to cover these areas comprehensively and in real time, and are easily affected by human factors. Therefore, hidden danger identification models are often used to monitor images containing transmission and substations to promptly discover potential safety hazards that may exist during the operation of the transmission and substations.

[0003] Since the training effect of the hidden danger identification model may directly affect the accuracy of the safety hidden danger monitoring results, and the change detection training data set is generally used to train the hidden danger identification model, the effectiveness of the change detection training data set is particularly critical to improving the accuracy of the safety hidden danger monitoring results. Summary of the invention

[0004] In order to improve the effectiveness of determining a change detection training data set, thereby improving the accuracy of potential safety hazard monitoring results, the present application provides a method and system for producing a change detection data set for a power transmission and transformation scenario.

[0005] In a first aspect, the present application provides a method for preparing a data set for detecting power transmission and transformation scene changes, using the following technical solution: A method for preparing a data set for detecting power transmission and transformation scene changes, comprising: Obtaining redraw instruction information, wherein the redraw instruction information includes target position information and redraw prompt words, and the target position information includes a target redraw center point and a redraw area size; Extracting a corresponding redrawing area image from the original scene image based on the target position information; Identifying the redrawing features contained in the redrawing prompt word, and determining the corresponding redrawing content based on the redrawing features; Identifying a scene resolution corresponding to the original scene image, and determining a local redrawn image based on the scene resolution, the redrawn area image, and the redrawn content; A result scene image is determined based on the partial redrawn image and the original scene image, and a change detection training data set is determined based on the result scene image and the original scene image.

[0006] By adopting the above technical scheme, the accuracy of determining the redrawing area image is improved by analyzing the redrawing instruction information. In addition, after analyzing the redrawing features contained in the redrawing prompt words, the corresponding redrawing content is determined based on the redrawing features, rather than determining the redrawing content according to fixed rules, which is convenient for improving the adaptability between the redrawing content and the redrawing prompt words, and also convenient for improving the richness of the redrawing content, thereby facilitating improving the richness of the change detection training data set. By generating a local redrawn image based on the scene resolution of the reference original scene image, it is convenient to improve the consistency between the local redrawn image and the original scene image, that is, it is convenient to improve the consistency between the result scene image and the original scene image, thereby facilitating improving the quality and effectiveness of the change detection training data set. Finally, a change detection training data set is jointly constructed based on the original scene image and the result scene image, which is convenient for improving the training effect of the hidden danger identification model, thereby improving the generalization ability and recognition accuracy of the hidden danger identification model in practical applications, and then facilitating improving the accuracy of the safety hidden danger monitoring results.

[0007] In a possible implementation manner, before determining the result scene image based on the partial redrawn image and the original scene image, the method further includes: Identifying redrawing feature information contained in the partial redrawn image, wherein the redrawing feature information includes texture redrawing features, color redrawing features, illumination redrawing features, and feature values ​​corresponding to each redrawing feature; Identify original feature information contained in the original scene image, wherein the original feature information includes texture original features, color original features, illumination original features, and feature values ​​corresponding to each original feature; Matching the redrawn feature information with the original feature information to obtain a feature matching value between the local redrawn image and the original scene image; When the feature matching value is lower than the preset matching value, based on the feature difference between the feature matching value and the preset matching value and the preset edge expansion information mapping relationship, determining the edge expansion information corresponding to the feature difference, wherein the preset edge expansion information mapping relationship is a corresponding relationship between the feature difference and the edge expansion information, and the edge expansion information includes an edge expansion size and an edge expansion transparency; The redrawing region image is adjusted based on the edge expansion information to obtain an updated redrawing region image, and then an updated partial redrawing image is determined based on the updated redrawing region image.

[0008] By adopting the above technical scheme, by matching the redrawn feature information contained in the local redrawn image with the original feature information contained in the original scene image, it is convenient to analyze and understand the difference between the local redrawn image and the original scene image. When the difference between the local redrawn image and the original scene image is large, the edge expansion processing can be performed on the redrawn area image, that is, the edge expansion processing is performed on the local redrawn image to reduce the difference between the local redrawn image and the original scene image. In the process of expanding the edge of the redrawn area image, the edge expansion is not random, but the edge expansion information is determined based on the feature difference between the local redrawn image and the original scene image, so as to improve the effectiveness of the edge expansion.

[0009] In a possible implementation, adjusting the redrawing area image based on the edge expansion information to obtain an updated redrawing area image includes: Identifying redrawn edge information corresponding to the redrawn content, and determining an edge point discrete level corresponding to the redrawn content based on the redrawn edge information; Determining an edge expansion type based on the discrete level of the edge points, wherein the edge expansion type includes balanced edge expansion and unbalanced edge expansion; When the edge expansion type is balanced edge expansion, determining an updated redrawing area image based on the target redrawing center point and the edge expansion information; When the edge expansion type is non-balanced edge expansion, the content center point corresponding to the redrawn content is identified, the target redrawing center point is adjusted based on the content center point to obtain an updated target redrawing center point, and an updated redrawing area image is determined based on the updated target redrawing center point and the edge expansion information.

[0010] By adopting the above technical solution, after determining the edge expansion information, the redrawn edge information of the redrawn content can be analyzed to determine the edge expansion method suitable for the redrawn content, and the redrawn area image is expanded based on the adapted edge expansion method, so as to improve the coordination between the local redrawn image and the original scene image, thereby improving the effectiveness of the resulting scene image.

[0011] In a possible implementation manner, after extracting the corresponding redrawing area image from the original scene image based on the target position information, the method further includes: Identify the scene features contained in the redrawing area image, and when the redrawing area image contains at least two different scene features, identify whether the redrawing prompt word contains a scene description prompt word, wherein the scene description prompt word is a description prompt word corresponding to any scene feature of the at least two different scene features; When the redrawing prompt word includes the scene description prompt word, determining the corresponding redrawing content based on the scene description prompt word; When the redrawing prompt word does not include the scene description prompt word, the corresponding historical training data is obtained based on the scene feature, and the corresponding target historical scene description prompt word is determined based on the historical training data, and the corresponding redrawing content is determined based on the target historical scene description prompt word, and the historical training data includes the scene description prompt word corresponding to each scene feature in the historical time period.

[0012] By adopting the above technical scheme, since the redrawing content corresponding to the same redrawing prompt word may be different under different scene features, the scene features contained in the redrawing area image are analyzed, and when the scene features are different, whether the redrawing prompt word contains a limiting description of the scene features is checked and analyzed, so as to improve the accuracy in determining the redrawing content. In addition, when the redrawing area image does not contain a limiting description of the scene features, the historical scene description words are analyzed and the corresponding redrawing content is determined based on the analysis results, so as to improve the adaptability between the redrawing content and the original scene image, thereby facilitating the improvement of the effectiveness in determining the change detection training data set.

[0013] In a possible implementation manner, when the number of scene features included in the redrawing area image is higher than a preset threshold, the method further includes: Determine multiple scene features as associated scene features, and determine the historical scene description prompt word corresponding to each associated scene feature based on the historical training data set; Determine the associated redrawing content corresponding to the associated scene feature based on each historical scene description prompt word, and match each associated redrawing content to obtain a morphological matching value; When the morphology matching value is lower than a preset morphology matching value, determining the associated redrawing content corresponding to each associated scene feature based on the historical scene description prompt word corresponding to each associated scene feature; A corresponding associated result scene image is determined based on each associated redrawing content, and an associated relationship of each associated result scene image in the change detection training data set is established.

[0014] By adopting the above technical solution, when the redrawn area image contains multiple scene features, the associated redrawn content corresponding to each associated scene feature is matched to facilitate viewing and analysis of the differences between different associated redrawn contents. In addition, by establishing an association relationship between the associated result scene images, the logic and generalization of the hidden danger identification model can be improved when the hidden danger identification model adopts the change detection training data set for model training, thereby facilitating improving the accuracy of determining the safety hidden danger monitoring results.

[0015] In one possible implementation, it also includes: Identifying a scene feature included in the original scene image, and when the scene feature is a preset scene feature, determining a scene prompt word corresponding to the preset scene feature based on a mapping relationship between the preset scene feature and a preset scene prompt word, wherein the preset scene prompt word mapping relationship is a corresponding relationship between the preset scene feature and the scene prompt word; The redrawing prompt word is updated based on the scene prompt word to obtain an updated redrawing prompt word, and then the corresponding redrawing content is determined based on the updated redrawing prompt word.

[0016] By adopting the above technical solution, the preset scene features contained in the original scene image are analyzed to determine the scene prompt words corresponding to the original scene image, and then the redrawing prompt words are optimized or enriched based on the scene prompt words, so as to improve the adaptability between the updated redrawing prompt words and the original scene image, thereby facilitating improving the accuracy of determining the redrawing content.

[0017] In a second aspect, the present application provides a production system, which adopts the following technical solution: A production system, the production system comprising: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned local redrawing control method based on the power transmission and transformation scenario.

[0018] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the above-mentioned local redrawing control method based on power transmission and transformation scenarios.

[0019] In a fourth aspect, the present application provides a computer program product, which adopts the following technical solution: A computer program product includes a computer program, and when the computer program is executed by a processor, the local redrawing control method based on the power transmission and transformation scenario is implemented.

[0020] In summary, the present application includes at least one of the following beneficial technical effects: By analyzing the redrawing instruction information, it is convenient to improve the accuracy of determining the redrawing area image. In addition, after analyzing the redrawing features contained in the redrawing prompt words, the corresponding redrawing content is determined based on the redrawing features, rather than determining the redrawing content according to fixed rules. This facilitates the adaptability between the redrawing content and the redrawing prompt words, and also facilitates the richness of the redrawing content, thereby facilitating the improvement of the richness of the change detection training data set. By generating a local redrawn image based on the scene resolution of the reference original scene image, it is convenient to improve the consistency between the local redrawn image and the original scene image, that is, it is convenient to improve the consistency between the result scene image and the original scene image, thereby facilitating the improvement of the quality and effectiveness of the change detection training data set. Finally, the change detection training data set is jointly constructed based on the original scene image and the result scene image, so as to improve the training effect of the hidden danger identification model, thereby improving the generalization ability and recognition accuracy of the hidden danger identification model in practical applications, and then facilitating the improvement of the accuracy of the safety hidden danger monitoring results.

[0021] Since the same redrawing prompt word may correspond to different redrawing contents under different scene features, the scene features contained in the redrawing area image are analyzed, and when the scene features are different, whether the redrawing prompt word contains a limiting description of the scene features is checked and analyzed, so as to improve the accuracy in determining the redrawing content. In addition, when the redrawing area image does not contain a limiting description of the scene features, the historical scene description words are analyzed and the corresponding redrawing content is determined based on the analysis results, so as to improve the adaptability between the redrawing content and the original scene image, thereby improving the effectiveness in determining the change detection training data set. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flowchart of a method for preparing a data set for detecting power transmission and transformation scene changes in an embodiment of the present application; Figure 2 is a schematic diagram of a process for determining redrawing content in an embodiment of the present application; Figure 3 It is a structural schematic diagram of a production system in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following is combined with Figure 1-3 This application is described in further detail.

[0024] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0027] Specifically, the embodiment of the present application provides a method for producing a data set for detecting changes in power transmission and transformation scenarios, which is executed by a production system, and the production system can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiment of the present application does not limit this.

[0028] refer to Figure 1 , Figure 1 1 is a flow chart of a method for preparing a data set for detecting a change in a power transmission and transformation scenario in an embodiment of the present application. The method includes steps S110 to S150, wherein: Step S110: obtaining redrawing instruction information, wherein the redrawing instruction information includes target position information and redrawing prompt words, and the target position information includes a target redrawing center point and a redrawing area size.

[0029] Specifically, the redrawing instruction information can be uploaded by the user to the production system through the preset annotation software, or the user can operate in the annotation box in the corresponding display interface of the production system. The specific acquisition method is not specifically limited in the embodiment of the present application. Among them, the preset annotation software can establish a communication connection with the production system through http request, and the production system can be deployed using ComfyUI.

[0030] The target redrawing center point and redrawing area size contained in the redrawing instruction information can be identified by semantic recognition, wherein the target redrawing center point is the position where the user needs to perform a partial redrawing in the original scene image, and the redrawing area size is the area range where the partial redrawing operation needs to be performed. The target redrawing center point can be described by coordinates or pixels. The redrawing prompt word can also be called a redrawing guide word, which is used to describe the content that the user needs to redraw. For example, the redrawing prompt word can be "crane, yellow" to indicate that the corresponding redrawing content can be a large yellow crane. The redrawing prompt word can be composed of multiple phrases or sentences, and the specific number of phrases or sentences is not specifically limited in the embodiments of the present application.

[0031] Step S120: extracting a corresponding redrawing area image from the original scene image based on the target position information.

[0032] Specifically, the redrawn area image is a partial image of the original scene image, that is, the redrawn area image is obtained by intercepting the original scene image based on the target position information, the area size corresponding to the redrawn area image is consistent with the redrawn area size in the target information, and the center point of the redrawn area image is the target redrawing center point. The original scene image can be any power transmission and transformation scene image, which can be uploaded to the production system by the user.

[0033] Step S130: identifying the redrawing features contained in the redrawing prompt word, and determining the corresponding redrawing content based on the redrawing features.

[0034] Specifically, when the redrawing prompt word only contains phrases, each phrase can be determined as a redrawing feature. When the redrawing prompt word contains sentences, the redrawing prompt word can be subjected to keyword extraction through a semantic recognition algorithm, and the redrawing feature can be determined based on the keyword extraction result. For example, the redrawing prompt word is "On a sunny summer afternoon, a little girl chases a colorful butterfly in a golden wheat field." After keyword extraction, the keywords obtained can be "little girl", "wheat field" and "colorful butterfly". At this time, "little girl", "wheat field" and "colorful butterfly" can be determined as redrawing features. After determining the redrawing features contained in the redrawing prompt word, the redrawing features can be combined to determine the corresponding redrawing content. The Stable Diffusion model's own generation capability can be used to determine the corresponding redrawing content based on the redrawing features. The Stable Diffusion model is an image generation model that uses deep learning technology, and the corresponding redrawing content can be determined based on different redrawing features.

[0035] In addition, the corresponding redrawing content can also be determined by using the preset feature mapping relationship and the redrawing features contained in the redrawing prompt word, wherein the preset feature mapping relationship contains the redrawing content corresponding to different redrawing feature combinations, and the specific content of the preset feature mapping relationship is not specifically limited in the embodiment of the present application, and can be determined by relevant staff based on historical experimental data and uploaded to the production system. The method of determining the corresponding redrawing content based on the redrawing feature is not specifically limited in the embodiment of the present application, as long as the determined redrawing content contains the redrawing feature.

[0036] Step S140: identifying the scene resolution corresponding to the original scene image, and determining the local redrawn image based on the scene resolution, the redrawn area image, and the redrawn content.

[0037] Specifically, a preset image viewer can be used to identify the scene resolution corresponding to the original scene image, wherein the preset image viewer can be Adobe Photoshop, GIMP, Windows Photo Viewer, etc. The specific image viewer is not specifically limited in the embodiment of the present application, and the scene resolution corresponding to the original scene image can also be determined by performing metadata analysis on the original scene image. By referring to the scene resolution corresponding to the original scene image in the process of generating a local redrawn image, it is convenient to improve the degree of fit between the local redrawn image and the original scene image, and to reduce the probability of imbalance in the local redrawn image. After determining the scene resolution corresponding to the original scene image, the redrawn area image and the redrawn content can be imported into the Stable Diffusion model, and the scene resolution can be used as a limiting condition to generate the corresponding local redrawn image, that is, the local redrawn image adds the redrawn content on the basis of the redrawn area image. The resolution difference between the redrawn resolution corresponding to the local redrawn image and the scene resolution is not higher than the preset resolution difference, wherein the specific preset resolution difference is not specifically limited in the embodiment of the present application, and can be set by relevant technical personnel.

[0038] Step S150: determining a result scene image based on the local redrawn image and the original scene image, and determining a change detection training data set based on the result scene image and the original scene image.

[0039] Specifically, after determining the local redrawn image, the local redrawn image can be superimposed or pasted back to the original scene image based on the target redrawing center point to obtain a result scene image, and a change detection data pair is generated based on the original scene image and the result scene image. The change detection training data set contains multiple change detection data pairs.

[0040] For the embodiments of the present application, by analyzing the redrawing instruction information, it is convenient to improve the accuracy in determining the redrawing area image. In addition, by analyzing the redrawing features contained in the redrawing prompt words, the corresponding redrawing content is determined based on the redrawing features, rather than determining the redrawing content according to fixed rules, it is convenient to improve the adaptability between the redrawing content and the redrawing prompt words, and it is also convenient to improve the richness of the redrawing content, thereby facilitating the improvement of the richness of the change detection training data set. By generating a local redrawn image based on the scene resolution of the reference original scene image, it is convenient to improve the consistency between the local redrawn image and the original scene image, that is, it is convenient to improve the consistency between the result scene image and the original scene image, thereby facilitating the improvement of the quality and effectiveness of the change detection training data set. Finally, a change detection training data set is jointly constructed based on the original scene image and the result scene image, so as to improve the training effect of the hidden danger identification model, thereby improving the generalization ability and recognition accuracy of the hidden danger identification model in practical applications, and then facilitating the improvement of the accuracy of the safety hidden danger monitoring results.

[0041] Furthermore, in order to reduce the difference between the partial redrawn image and the original scene image, the method provided in the embodiment of the present application further includes, before determining the result scene image based on the partial redrawn image and the original scene image: Identify the redrawing feature information contained in the local redrawn image, the redrawing feature information includes texture redrawing features, color redrawing features, lighting redrawing features, and feature values ​​corresponding to each redrawing feature; identify the original feature information contained in the original scene image, the original feature information includes texture original features, color original features, lighting original features, and feature values ​​corresponding to each original feature; match the redrawing feature information with the original feature information to obtain a feature matching value between the local redrawn image and the original scene image.

[0042] Specifically, before determining the result scene image based on the partial redrawn image, the partial redrawn image may be checked, and whether the partial redrawn image needs to be updated and adjusted may be determined based on the check result, wherein the redrawn feature information corresponding to the partial redrawn image may be feature matched with the original feature information corresponding to the original scene image to determine whether the partial redrawn image is unbalanced. Among them, the texture redrawing feature, color redrawing feature, and illumination redrawing feature corresponding to the partial redrawn image may be respectively identified from the partial redrawn image through the feature recognition algorithm, and the texture original feature, color original feature, and illumination original feature corresponding to the original scene image may be identified from the original scene image. The specific feature recognition method is not specifically limited in the embodiment of the present application and may be set by relevant staff.

[0043] Since texture is an important manifestation of the surface features of objects in an image, it determines the texture and details of the image. If the redrawn texture in the partially redrawn image is too different from the original texture in the original scene image, when the partially redrawn image is superimposed or pasted back to the original scene image, it may cause obvious splicing marks, affecting the overall beauty and authenticity of the resulting scene image; color is one of the key factors in the visual effect of an image. If the redrawn color in the partially redrawn image is too different from the original color in the original scene image, when the partially redrawn image is superimposed or pasted back to the original scene image, the color may be abrupt or inconsistent; lighting is an important means of expressing the shape and contour of an object in an image. If the redrawn lighting in the partially redrawn image is too different from the original lighting in the original scene image, when the partially redrawn image is superimposed or pasted back to the original scene image, it may cause an unnatural lighting effect. Therefore, in the application embodiment, the partially redrawn image is checked based on texture, color and lighting, but the specific features contained in the redrawn feature information are not limited in the embodiment of the present application, and can be adjusted by relevant technical personnel according to actual needs.

[0044] When the feature matching value is lower than the preset matching value, the edge expansion information corresponding to the feature difference is determined based on the feature difference between the feature matching value and the preset matching value and the preset edge expansion information mapping relationship, the preset edge expansion information mapping relationship is the corresponding relationship between the feature difference and the edge expansion information, and the edge expansion information includes the edge expansion size and the edge expansion transparency; based on the edge expansion information, the redrawn area image is adjusted to obtain an updated redrawn area image, and then the updated local redrawn image is determined based on the updated redrawn area image.

[0045] Specifically, when the feature matching value is not lower than the preset matching value after the redrawn feature information corresponding to the local redrawn image is matched with the original feature information corresponding to the original scene image, it indicates that there is no need to perform edge expansion processing on the local redrawn image, that is, there is no need to perform edge expansion processing on the redrawn area image corresponding to the local redrawn image, and the step of determining the result scene image based on the local redrawn image and the original scene image can be performed. When the feature matching value is lower than the preset matching value, it indicates that there is a need to perform edge expansion processing on the local redrawn image, that is, it is necessary to perform edge expansion processing on the redrawn area image corresponding to the local redrawn image to reduce or eliminate the splicing marks, wherein the preset matching value can be 80% or 90%, and the specific preset matching value is not specifically limited in the embodiment of the present application.

[0046] When it is determined that the redrawn area image needs to be expanded, random expansion can be performed, that is, as long as the size of the redrawn area image obtained after the expansion is larger than the size of the redrawn area before the expansion. The redrawn area image can also be expanded in a fixed expansion manner, that is, as long as it is determined that the redrawn area image needs to be expanded, the redrawn area image is expanded according to a preset fixed ratio. The specific preset fixed ratio can be 2 times or 1.2 times. The specific preset fixed ratio is not specifically limited in the embodiment of the present application. For example, when the preset fixed ratio is 1.2 times, the corresponding size of the redrawn area image is 400*400, and the corresponding size after the expansion is 480*480.

[0047] In addition, the corresponding edge expansion information, that is, the edge expansion strategy, can also be determined based on the feature difference and the preset edge expansion information mapping relationship. The preset edge expansion information mapping relationship contains edge expansion information corresponding to different feature differences. The specific content is not specifically limited in the embodiment of the present application, and can be determined by relevant staff based on historical experimental data and uploaded to the production system. The edge expansion information includes the edge expansion size and the edge expansion transparency. The edge expansion size is added on the basis of the redrawing area size, that is, the edge expansion area corresponding to the edge expansion size is superimposed on the redrawing area image to adjust the redrawing area size of the redrawing area image. The difference between the local redrawing image and the original scene image can also be further reduced by reducing the transparency of the edge expansion area. The specific method of determining the updated local redrawing image based on the updated redrawing area image can refer to the method of determining the corresponding local redrawing image based on the redrawing area image in the above embodiment, which will not be repeated here.

[0048] Furthermore, in order to improve the coordination between the local redrawn image and the original scene image, the redrawn region image is adjusted based on the edge expansion information to obtain an updated redrawn region image, including: Identify the redrawn edge information corresponding to the redrawn content, and determine the discrete level of the edge points corresponding to the redrawn content based on the redrawn edge information; determine the edge expansion type based on the discrete level of the edge points, and the edge expansion type includes balanced edge expansion and unbalanced edge expansion; when the edge expansion type is balanced edge expansion, determine the updated redrawn area image based on the target redrawn center point and the edge expansion information. When the edge expansion type is unbalanced edge expansion, identify the content center point corresponding to the redrawn content, adjust the target redrawn center point based on the content center point, obtain the updated target redrawn center point, and determine the updated redrawn area image based on the updated target redrawn center point and the edge expansion information.

[0049] Specifically, the redrawn edge information corresponding to the redrawn content can be identified from the local redrawn image based on the edge recognition algorithm. At this time, the local redrawn image is the local redrawn image before the edge expansion process. The edge recognition algorithm can be a Sobel operator detection algorithm, a Canny edge detection algorithm, and a Prewitt operator detection algorithm. The specific edge recognition algorithm is not specifically limited in the embodiments of the present application, as long as the redrawn edge information corresponding to the redrawn content can be identified from the local redrawn image.

[0050] The redrawn edge information includes the coordinate information of each edge point. By performing discrete analysis on the redrawn edge information, the discrete level of the edge points corresponding to the redrawn content can be determined. The redrawn edge information can be discretely analyzed by calculating the standard deviation or variance, calculating the average distance, using a clustering algorithm, etc. The specific discrete analysis method is not specifically limited in the embodiment of the present application. When the standard deviation or variance is used to measure the discrete level of the edge point, the standard deviation or variance of the edge point in the X coordinate and the Y coordinate can be calculated respectively to evaluate the degree of discreteness of the edge point in the horizontal and vertical directions. The larger the standard deviation or variance value, the higher the discrete level of the edge point in this direction, that is, the sparser the distribution of the edge points; conversely, it means that the edge points are distributed more densely.

[0051] After determining the edge point discrete level corresponding to the redrawn content, the edge point discrete level can be compared with the preset discrete level. When the edge point discrete level is lower than the preset discrete level, the corresponding edge expansion type can be determined to be balanced edge expansion; when the edge point discrete level is not lower than the preset discrete level, the corresponding edge expansion type can be determined to be unbalanced edge expansion, wherein the specific preset discrete level is not specifically limited in the embodiment of the present application and can be set by relevant technical personnel.

[0052] Different edge expansion types correspond to different edge expansion methods. When the edge expansion type is balanced edge expansion, the edge expansion process can be directly performed based on the target redrawing center point and the edge expansion information. The center point corresponding to the redrawing area image obtained after the edge expansion process is still the target redrawing center point. When the edge expansion type is unbalanced edge expansion, it is necessary to adjust the target redrawing center point based on the content center point corresponding to the redrawing content to obtain the updated target redrawing center point, and then perform edge expansion based on the updated target redrawing center point and the edge expansion information. The updated target redrawing center point may be the content center point, or it may be any point between the content center point and the target redrawing center point.

[0053] After determining the edge expansion information, the redrawn edge information of the redrawn content can be analyzed to determine the edge expansion method that is compatible with the redrawn content, and the redrawn area image is expanded based on the adapted edge expansion method to improve the coordination between the local redrawn image and the original scene image, thereby improving the effectiveness of the resulting scene image.

[0054] Further, in order to improve the adaptability between the redrawn content and the original scene image, after extracting the corresponding redrawn area image from the original scene image based on the target position information, the method provided in the embodiment of the present application further includes steps S1 to S3, such as Figure 2 As shown, where: Step S1: Identify scene features contained in the redrawn area image. When the redrawn area image contains at least two different scene features, identify whether the redrawn prompt word contains a scene description prompt word, where the scene description prompt word is a description prompt word corresponding to any scene feature of the at least two different scene features.

[0055] Specifically, the scene features may be an uphill road, a downhill road, a flat road or a lake, etc. Different scene features are displayed differently in the redrawn area image. The scene features contained therein may be identified from the redrawn area image by feature recognition. The specific feature recognition method is not specifically limited in the embodiments of the present application. When the redrawing area image contains two or more scene features, it may affect the accuracy of determining the redrawing content. For example, when the redrawing prompt word is a yellow crane and the redrawing area image contains both uphill and downhill roads, it is necessary to add a yellow crane to the redrawing area image. However, since the parking forms of the yellow crane on the uphill road and the downhill road may be different, when the model is trained based on the change detection data of different parking forms, the corresponding training content may also be different. Therefore, it is necessary to check whether the redrawing prompt word contains the scene description prompt word. The scene description prompt word can be to add a yellow crane on the side of the uphill road. When the redrawing instruction information is semantically recognized, the scene description prompt word may be mistakenly eliminated as invalid data. Therefore, when the redrawing area image contains at least two different scene features, it is necessary to re-identify whether the redrawing prompt word contains the scene description prompt word.

[0056] Step S2: when the redrawing prompt word includes the scene description prompt word, determining the corresponding redrawing content based on the scene description prompt word.

[0057] Specifically, when it is determined that the redrawing prompt words contain scene description prompt words, the corresponding redrawing content is redetermined according to the scene description prompt words to ensure that the redrawing content is compatible with the scene description prompt words. The method of redetermining the corresponding redrawing content according to the scene description prompt words can refer to the method of identifying the redrawing features contained in the redrawing prompt words, and then determining the corresponding redrawing content based on the redrawing features in the above-mentioned embodiment, which will not be elaborated here.

[0058] Step S3: When the redrawing prompt words do not include scene description prompt words, the corresponding historical training data is obtained based on the scene features, and the corresponding target historical scene description prompt words are determined based on the historical training data, and the corresponding redrawing content is determined based on the target historical scene description prompt words, and the historical training data contains the scene description prompt words corresponding to each scene feature in the historical time period.

[0059] Specifically, when the redrawing prompt word does not include the scene description prompt word, the corresponding redrawing content is not determined randomly, but the historical training data needs to be analyzed in order to determine the corresponding target historical scene description prompt word from the historical training data, wherein the historical training data is all the redrawing instruction information and the corresponding original scene image in the historical time period, and by analyzing the number of descriptions of each scene feature including the corresponding scene description prompt word in the historical training data, the scene feature with the most descriptions can be determined as the target scene feature, and the target historical scene description word is determined based on the scene description prompt word and the redrawing prompt word corresponding to the target scene feature, wherein the historical time period can be a period of time before the current moment, and the duration corresponding to the historical time period can be 20 hours or 25 hours. The specific duration is not specifically limited in the embodiment of the present application. The original scene image in the historical training data is a scene image that contains at least two scene features at the same time. By analyzing the historical training data, the scene features that the relevant staff are more concerned about can be determined. For example, there are two scene features, namely uphill road and downhill road. According to historical training data, it can be determined that there are 10 original scene images in the historical time period that contain both uphill road and downhill road, and 8 redrawing instruction information corresponding to the 10 original scene images contain scene description prompt words about uphill road, and 2 redrawing instruction information contain scene description prompt words about downhill road. At this time, uphill road can be determined as the target scene feature. When the redrawing prompt words contain "yellow crane" and the determined target scene feature is uphill road, the corresponding target historical scene description prompt words can be determined as "add a yellow crane on the side of the uphill road". By analyzing the historical scene description words and determining the corresponding redrawing content based on the analysis results, it is convenient to improve the adaptability between the redrawing content and the original scene image, thereby facilitating the improvement of the effectiveness of determining the change detection training data set.

[0060] Furthermore, when the number of scene features contained in the redrawn area image is higher than a preset threshold, the method provided in the embodiment of the present application further includes: Determine multiple scene features as associated scene features, and determine the historical scene description prompt word corresponding to each associated scene feature based on the historical training data set; determine the associated redrawing content corresponding to the associated scene feature based on each historical scene description prompt word, and match each associated redrawing content to obtain a morphological matching value; when the morphological matching value is lower than a preset morphological matching value, determine the associated redrawing content corresponding to each associated scene feature based on the historical scene description prompt word corresponding to each associated scene feature; determine the corresponding associated result scene image based on each associated redrawing content, and establish an association relationship between each associated result scene image in the change detection training data set.

[0061] Specifically, the preset threshold value may be 3 or 4. The specific threshold value is not specifically limited in the embodiments of the present application and may be set by relevant technical personnel. When the number of scene features contained in the redrawn area image is large, the contents disclosed in the above embodiments may be used to determine the historical scene description prompt words corresponding to each scene feature and determine the corresponding redrawn content based on the historical scene description prompt words. The specific process is not described in detail here. For ease of description, multiple scene features may be determined as associated scene features, and the redrawn content corresponding to each associated scene feature may be determined as associated redrawn content.

[0062] Each associated redrawing content is matched to analyze and evaluate the differences between different associated redrawing contents. When the morphological matching value is lower than the preset morphological matching value, it indicates that the similarity between the associated redrawing contents corresponding to different associated scene features is low. At this time, if only one of the associated scene features is selected to determine the redrawing content, and then the change detection data pair is determined based on the redrawing content, the richness of the change detection data set may be reduced. Therefore, the associated redrawing content of each associated scene feature can be determined separately to enrich the change detection data set, thereby facilitating the improvement of the recognition effect of the hidden danger identification model on the same object or equipment in similar scene features. The specific preset morphological matching value is not specifically limited in the embodiment of the present application and can be set by relevant staff.

[0063] By adding associated links in the associated result scene images, the connection between the associated result scene images can be established, so as to facilitate intuitive comparison of the training results generated by the hidden danger identification model when training different associated result scene images. In addition, by establishing the association relationship between the associated result scene images, it is also convenient to improve the logic and generalization of the hidden danger identification model when the hidden danger identification model uses the change detection training data set for model training, thereby facilitating the improvement of the accuracy of determining the safety hidden danger monitoring results.

[0064] Furthermore, in order to improve the accuracy of determining the redrawn content, the method provided in the embodiment of the present application also includes: Identify the scene features contained in the original scene image. When the scene features are preset scene features, determine the scene prompt words corresponding to the preset scene features based on the mapping relationship between the preset scene features and the preset scene prompt words, where the preset scene prompt word mapping relationship is the corresponding relationship between the preset scene features and the scene prompt words; update the redrawing prompt words based on the scene prompt words to obtain updated redrawing prompt words, and then determine the corresponding redrawing content based on the updated redrawing prompt words.

[0065] Specifically, the preset scene features may be road maintenance, road collapse, etc. The specific preset scene features may be determined by relevant staff based on historical survey data and then uploaded to the production system, wherein different preset scene features correspond to different scene prompt words, and the preset scene prompt word mapping relationship includes scene prompt words corresponding to different preset scene features. The scene prompt words may be “please avoid maintenance sections” or “please avoid collapsed sections”. The specific content of the preset scene prompt word mapping relationship is not specifically limited in the embodiment of the present application, and may be determined by relevant staff based on historical experimental data and then uploaded to the production system.

[0066] The redrawing prompt words are updated based on the scene prompt words, that is, description and limitation are performed on the basis of the redrawing prompt words. When the corresponding redrawing content is determined based on the updated redrawing prompt words, the adaptability between the updated redrawing prompt words and the original scene image can be improved, thereby reducing the probability of generating invalid local redrawing images, thereby improving the quality of the change detection dataset.

[0067] The present application embodiment provides a production system, such as Figure 3 As shown, Figure 3 The production system 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the production system 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the production system 300 does not constitute a limitation on the embodiments of the present application.

[0068] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0069] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The fact that only one line is used in the diagram does not mean that there is only one bus or only one type of bus.

[0070] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0071] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0072] The production system includes, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The production system shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0073] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0074] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method in any of the above embodiments is implemented.

[0075] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0076] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for preparing a data set for detecting power transmission and transformation scene changes, characterized in that: include: Obtaining redraw instruction information, wherein the redraw instruction information includes target position information and redraw prompt words, and the target position information includes a target redraw center point and a redraw area size; Extracting a corresponding redrawing area image from the original scene image based on the target position information; Identifying the redrawing features contained in the redrawing prompt word, and determining the corresponding redrawing content based on the redrawing features; Identifying a scene resolution corresponding to the original scene image, and determining a local redrawn image based on the scene resolution, the redrawn area image, and the redrawn content; A result scene image is determined based on the partial redrawn image and the original scene image, and a change detection training data set is determined based on the result scene image and the original scene image.

2. The method for preparing a data set for detecting power transmission and transformation scene changes according to claim 1, characterized in that: Before determining the result scene image based on the local redrawn image and the original scene image, the method further includes: Identifying redrawing feature information contained in the partial redrawn image, wherein the redrawing feature information includes texture redrawing features, color redrawing features, illumination redrawing features, and feature values ​​corresponding to each redrawing feature; Identify original feature information contained in the original scene image, wherein the original feature information includes texture original features, color original features, illumination original features, and feature values ​​corresponding to each original feature; Matching the redrawn feature information with the original feature information to obtain a feature matching value between the local redrawn image and the original scene image; When the feature matching value is lower than the preset matching value, based on the feature difference between the feature matching value and the preset matching value and the preset edge expansion information mapping relationship, determining the edge expansion information corresponding to the feature difference, wherein the preset edge expansion information mapping relationship is a corresponding relationship between the feature difference and the edge expansion information, and the edge expansion information includes an edge expansion size and an edge expansion transparency; The redrawing region image is adjusted based on the edge expansion information to obtain an updated redrawing region image, and then an updated partial redrawing image is determined based on the updated redrawing region image.

3. The method for preparing a data set for detecting power transmission and transformation scene changes according to claim 2, characterized in that: The adjusting the redrawing area image based on the edge expansion information to obtain an updated redrawing area image includes: Identifying redrawn edge information corresponding to the redrawn content, and determining an edge point discrete level corresponding to the redrawn content based on the redrawn edge information; Determining an edge expansion type based on the discrete level of the edge points, wherein the edge expansion type includes balanced edge expansion and unbalanced edge expansion; When the edge expansion type is balanced edge expansion, determining an updated redrawing area image based on the target redrawing center point and the edge expansion information; When the edge expansion type is non-balanced edge expansion, the content center point corresponding to the redrawn content is identified, the target redrawing center point is adjusted based on the content center point to obtain an updated target redrawing center point, and an updated redrawing area image is determined based on the updated target redrawing center point and the edge expansion information.

4. The method for preparing a data set for detecting power transmission and transformation scene changes according to claim 1, characterized in that: After extracting the corresponding redrawing area image from the original scene image based on the target position information, the method further includes: Identify the scene features contained in the redrawing area image, and when the redrawing area image contains at least two different scene features, identify whether the redrawing prompt word contains a scene description prompt word, wherein the scene description prompt word is a description prompt word corresponding to any scene feature of the at least two different scene features; When the redrawing prompt word includes the scene description prompt word, determining the corresponding redrawing content based on the scene description prompt word; When the redrawing prompt word does not include the scene description prompt word, the corresponding historical training data is obtained based on the scene feature, and the corresponding target historical scene description prompt word is determined based on the historical training data, and the corresponding redrawing content is determined based on the target historical scene description prompt word, and the historical training data includes the scene description prompt word corresponding to each scene feature in the historical time period.

5. The method for preparing a data set for detecting power transmission and transformation scene changes according to claim 4, characterized in that: When the number of scene features included in the redrawn area image is higher than a preset threshold, the method further includes: Determine multiple scene features as associated scene features, and determine the historical scene description prompt word corresponding to each associated scene feature based on the historical training data set; Determine the associated redrawing content corresponding to the associated scene feature based on each historical scene description prompt word, and match each associated redrawing content to obtain a morphological matching value; When the morphology matching value is lower than a preset morphology matching value, determining the associated redrawing content corresponding to each associated scene feature based on the historical scene description prompt word corresponding to each associated scene feature; A corresponding associated result scene image is determined based on each associated redrawing content, and an associated relationship of each associated result scene image in the change detection training data set is established.

6. The method for preparing a data set for detecting power transmission and transformation scene changes according to claim 1, characterized in that: Also includes: Identifying a scene feature included in the original scene image, and when the scene feature is a preset scene feature, determining a scene prompt word corresponding to the preset scene feature based on a mapping relationship between the preset scene feature and a preset scene prompt word, wherein the preset scene prompt word mapping relationship is a corresponding relationship between the preset scene feature and the scene prompt word; The redrawing prompt word is updated based on the scene prompt word to obtain an updated redrawing prompt word, and then the corresponding redrawing content is determined based on the updated redrawing prompt word.

7. A production system, characterized in that: The production system includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a method for producing a power transmission and transformation scene change detection data set as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that: include: A computer program is stored which can be loaded by a processor and executes a method for producing a data set for detecting changes in power transmission and transformation scenarios as described in any one of claims 1-6.

9. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the steps of a method for producing a data set for detecting changes in power transmission and transformation scenarios according to any one of claims 1 to 6.

Images