Tower greening identification method and system, electronic device and computer storage medium

Abstract

This disclosure relates to a method, system, electronic device, and computer storage medium for identifying green areas around a tower base. The method includes acquiring UAV images and initial images after shadow detection; identifying a disturbance zone within the initial image based on preset tower base design data and the UAV images, where the disturbance zone represents the area within the temporary construction land area; calculating a vegetation index based on the image of the disturbance zone, and stacking the vegetation index and multiple bands from the image of the disturbance zone to obtain a multi-channel image; classifying the channel image using preset sample data to generate a classification probability map, where the classification probability map represents the probability of vegetation and non-vegetation; and calculating the green coverage rate based on the classification probability map. This application can quickly and accurately identify the green area around the tower base and calculate the green coverage rate.

Description

Technical Field

[0001] This disclosure relates to the field of image recognition technology, and more specifically, to a method, system, electronic device, and computer storage medium for identifying greenery at the base of a tower. Background Technology

[0002] During the completion phase of power transmission line projects, the vegetation restoration (i.e., greening) of the tower base and surrounding construction disturbance areas is a core indicator for environmental protection acceptance.

[0003] Traditional manual on-site inspection methods are inefficient, lack comprehensive coverage, and lack objective quantitative standards, easily leading to acceptance disputes. Existing remote sensing identification methods often rely solely on simple vegetation indices for rough classification, making it difficult to accurately distinguish between artificially restored vegetation and natural weeds within the tower base area, resulting in inaccurate environmental protection acceptance. Summary of the Invention

[0004] This disclosure provides a method, system, electronic device, and computer storage medium for identifying green areas at the base of a tower, which can quickly and accurately identify green areas within an image region and obtain information on the green coverage.

[0005] Firstly, this disclosure relates to a method for identifying greening at the base of a power transmission line. The method includes acquiring a drone image and an initial image after shadow detection. The initial image is an image of the location of the target transmission line before greening restoration after construction is completed. The time of the drone image acquisition and the acquisition time of the initial image are within a preset time range. Based on preset base design data and the drone image, a base disturbance zone is identified within the initial image. The base design data includes the design coordinates of the base and vector data of the temporary construction land boundary established during the construction of the base. The base disturbance zone represents the area within the scope of the temporary construction land. Based on the image of the base disturbance zone, a vegetation index is calculated, and the vegetation index and multiple bands in the image of the base disturbance zone are stacked to obtain a multi-channel image. Using preset sample data, the channel image is classified and identified to generate a classification probability map, which represents the probability of vegetation and non-vegetation. Based on the classification probability map, the green coverage rate is calculated.

[0006] The tower base greening identification method of this application, based on acquired UAV images and preset tower base design data, can accurately identify tower base disturbance areas from the initial image. Furthermore, since cloud cover or other obstructions exist in the initial image after shadow detection, the UAV image can be used to replace the portion of the initial image obscured by clouds, thus enabling the identification of precisely defined tower base disturbance areas. Based on a portion of the initial image within the tower base disturbance area, and using the calculated vegetation index and sample data, a classification probability map representing the probability of vegetation and non-vegetation can be generated. This allows for direct determination of the probability of each pixel's location being vegetation from the classification probability map. Therefore, the prepared vegetation coverage rate can be calculated based on the classification probability map to determine whether the artificial vegetation meets the acceptance criteria.

[0007] In some embodiments, identifying the tower foundation disturbance zone within the initial image based on preset tower foundation design data and the UAV image includes: acquiring historical images, which are images of the location of the target transmission line before the start of construction; comparing the historical images with the initial image to obtain a change intensity image, which represents changes in the ground surface; and determining the tower foundation disturbance zone from the change intensity image based on the tower foundation design data.

[0008] In some embodiments, determining the tower base disturbance zone from the intensity variation map based on the tower base design data includes: identifying the initial region where the tower base is located in the initial image based on the tower base design data; determining the tower base evaluation zone from the intensity variation map based on the initial region, wherein the tower base evaluation zone is the region in the actual construction process; obtaining the shadow region of the area where the tower base is located within the tower base evaluation zone in the initial image; and replacing the shadow region with the UAV image when the detected shadow region is larger than a preset threshold to obtain the tower base disturbance zone.

[0009] In some embodiments, after comparing the difference between the historical image and the initial image to obtain a change intensity image, the method further includes: binarizing the change intensity image to obtain a raster image, wherein the pixel value of each pixel in the raster image is used to indicate whether the location is a construction area; performing noise removal and boundary extraction processing on the raster image to obtain a construction boundary; and determining the tower base evaluation area from the change intensity image based on the initial area includes: spatially superimposing the initial area and the construction boundary to obtain the tower base evaluation area.

[0010] In some embodiments, after classifying and recognizing the channel image using preset sample data to generate a classification probability map, the method further includes: converting the classification probability map into a vector image and performing image processing on the vector image to obtain a base distribution map, wherein the base distribution map includes multiple patches, each patch corresponding to a set of spatial attributes and classification attributes, the classification attributes being used to indicate whether it is artificial vegetation, natural vegetation, non-vegetation, or water and soil flow; the step of calculating the green coverage rate based on the classification probability map includes: calculating the green coverage rate based on the spatial attributes and classification attributes corresponding to each patch in the base distribution map.

[0011] In some embodiments, calculating the green coverage rate based on the spatial attributes and classification attributes corresponding to each of the patches in the tower base distribution map includes: calculating the area of ​​artificial vegetation, the total area of ​​tower base disturbance, and the shaded area of ​​the shaded region based on the spatial attributes and classification attributes corresponding to each of the patches in the tower base distribution map; calculating the difference between the total area of ​​tower base disturbance and the shaded area; and using the quotient of the area of ​​artificial vegetation and the difference as the green coverage rate.

[0012] In some embodiments, after converting the classification probability map into a vector image and performing image processing on the vector image to obtain a base distribution map, the method further includes: determining artificial vegetation areas based on the spatial attributes and classification attributes corresponding to each patch in the base distribution map; performing rasterization processing on the image within the artificial vegetation area to obtain a vegetation raster map; calculating the vegetation coverage rate within each grid in the vegetation raster map; calculating the standard deviation and mean of multiple grids based on multiple vegetation coverage rates; using the quotient of the standard deviation and the mean as the coefficient of variation; generating a vegetation compliance result if the coefficient of variation is detected to be less than a preset coefficient; and generating a vegetation non-compliance result if the coefficient of variation is detected to be not less than the preset coefficient.

[0013] Secondly, this disclosure also relates to a tower base greening identification system, the system comprising: an acquisition module for acquiring drone images and an initial image after shadow detection, wherein the initial image is an image of the location of the target transmission line before greening restoration after the completion of engineering construction, and the acquisition time of the drone images and the acquisition time of the initial image are within a preset time range; an identification module for identifying tower base disturbance areas within the initial image based on preset tower base design data and the drone images, wherein the tower base design data includes the design coordinates of the tower base and vector data of the temporary construction land boundary line established during the construction of the tower base, and the tower base disturbance area represents the area within the scope of the temporary construction land; a first calculation module for calculating a vegetation index based on the image of the tower base disturbance area, and stacking the vegetation index and multiple bands in the image of the tower base disturbance area to obtain a multi-channel image; a classification module for classifying and identifying the channel images using preset sample data to generate a classification probability map, wherein the classification probability map represents the probability of vegetation and non-vegetation; and a second calculation module for calculating the green coverage rate based on the classification probability map.

[0014] Thirdly, this disclosure also relates to an electronic device, the electronic device comprising: a memory storing computer-readable instructions; and a processor executing the computer-readable instructions stored in the memory to implement the tower base greening identification method as described above.

[0015] Fourthly, this disclosure also relates to a computer storage medium storing computer-readable instructions, which are executed by a processor in an electronic device to implement the tower base greening identification method as described above.

[0016] The technical features of the tower base greening identification system in the second aspect, the electronic equipment in the third aspect, and the computer storage medium in the fourth aspect correspond one-to-one with the technical features of the tower base greening identification method in the first aspect, and the resulting technical effects are also the same, so they will not be elaborated here. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the steps of the tower base greening identification method according to an embodiment of this application.

[0018] Figure 2 This is a flowchart illustrating the sub-steps of the tower base greening identification method according to an embodiment of this application.

[0019] Figure 3 This is a schematic diagram of the structure of the tower base greening identification system according to an embodiment of this application.

[0020] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0021] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0022] It should be understood that the various steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0023] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0024] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0025] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0026] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0027] This application provides a method, system, electronic device, and computer storage medium for identifying greenery at the base of a tower.

[0028] See Figure 1 As shown, Figure 1 This is a flowchart illustrating the steps of an embodiment of the tower base greening identification method of this application. Depending on different needs, the order of the steps in the flowchart can be changed, and some steps can be omitted. The tower base greening identification method may include the following steps.

[0029] Step 101: Acquire drone images and initial images after shadow detection.

[0030] The initial image is an image of the location of the target power transmission line before the greening restoration after the completion of the project. The time of the drone image shooting is within the preset time range of the initial image shooting time.

[0031] In this embodiment, the target transmission line includes multiple tower bases and construction areas and natural green areas surrounding each tower base. The initial image is a satellite image, which includes red, green, blue, and near-infrared bands, and is used to calculate the vegetation index later.

[0032] In the power sector, drones are often used to capture images during construction. Therefore, drone images can also be acquired simultaneously. When the initial images are obscured by clouds or when high-precision images are required, drone inspection fleets can be used to collect centimeter-level images. Furthermore, drone images are unaffected by clouds and can accurately reveal vegetation textures and micro-topography.

[0033] To ensure accurate identification of green areas, shadow detection needs to be performed on the acquired raw satellite images to obtain initial images. These raw satellite images include panchromatic and multispectral images.

[0034] The steps for performing shadow detection on the raw satellite image to obtain the initial image include: (1) Acquire elevation data and ground control data. Elevation data represents the undulation of the ground where the target transmission line is located, and ground control data is used to correct the coordinate values ​​of each pixel in the original satellite image. For example, ground control data may include the coordinates of the location of the tower base center pile and the coordinates of the location of the road intersection.

[0035] (2) Perform geometric correction on the panchromatic band image to obtain the first band image; perform geometric correction on the multispectral band image to obtain the second band image; and then perform atmospheric correction on the second band image to obtain the third band image.

[0036] (3) Perform shadow detection on the first band image and the third band image respectively, and fuse the first band image and the third band image after shadow detection to obtain the initial image.

[0037] The geometric correction, atmospheric correction, and shadow detection techniques in this embodiment can all refer to relevant content in the prior art, and will not be repeated here to avoid redundancy.

[0038] It is understandable that radiometric correction is performed on the original satellite images to obtain initial images with both high spatial resolution and rich spectral information, which facilitates the subsequent detailed identification of greenery.

[0039] Step 102: Based on the preset tower base design data and UAV images, identify the tower base disturbance zone in the initial image.

[0040] The tower base design data includes the design coordinates of the tower base and the vector data of the temporary construction land boundary line established during the construction of the tower base. The tower base disturbance zone represents the area within the scope of the temporary construction land.

[0041] In this embodiment, the design coordinates of the tower base refer to the actual geographical location of the tower base to be constructed. The vector data of the temporary construction land boundary line established during the construction of the tower base refers to the vector data of the area where relevant materials need to be placed around the geographical location of the tower base during the tower base construction process.

[0042] In this embodiment, the initial disturbance area within the initial image can be identified based on preset tower base design data. If cloud cover or severe shadows exist in the initial image, the range of the initial disturbance area is corrected using UAV imagery, thereby obtaining the tower base disturbance area. The specific steps are described in detail below and will not be repeated here.

[0043] Step 103: Calculate the vegetation index based on the image of the tower base disturbance area, and stack the vegetation index and the multi-band images of the tower base disturbance area to obtain a multi-channel image.

[0044] Specifically, the vegetation index is calculated based on a portion of the image within the disturbance zone of the tower base in the initial image. The vegetation index and the multi-band features from the portion of the image within the disturbance zone of the tower base in the initial image are then stacked to obtain a multi-channel image.

[0045] Vegetation indices can include the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EDI), and Soil-Regulated Vegetation Index (SRI). Processing images using vegetation indices can highlight vegetation information and suppress soil background interference.

[0046] In this embodiment, the multi-band image in the portion of the initial image within the tower base disturbance area includes red, green, blue, and near-infrared bands. The red, green, blue, and near-infrared bands are then stacked with the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EDI), and Soil-Regulated Vegetation Index (SRI) to obtain a multi-channel image. In other embodiments, the vegetation index may also include other indices besides the NDVI, EDI, and SRI. Specific image feature stacking techniques are also prior art and will not be elaborated upon here.

[0047] Step 104: Using preset sample data, classify and identify the channel images to generate a classification probability map.

[0048] In this embodiment, the preset sample data includes multiple images, each image comprising multiple sub-regions. Each sub-region is labeled as one of the following: artificially restored vegetation area, natural vegetation area, non-vegetation area, or soil erosion area. Artificially restored vegetation area consists of uniform, row-shaped artificial turf or shrubs with clear boundaries. Natural vegetation area consists of sparse, scattered natural weeds or shrubs. Non-vegetation area can include tower base platforms, construction access roads, exposed rocks, buildings, etc. Soil erosion area can include gullies, landslide surfaces, obvious runoff traces, exposed erosion surfaces, etc.

[0049] The process of labeling images based on multiple categories to obtain labeled images and thus sample data can be processed using existing image labeling and recognition technologies. To ensure the accuracy of subsequent greening identification, the images collected for obtaining sample data can cover images with different terrains, restoration ages, and lighting conditions, thereby ensuring the generalization ability of the models used in image labeling and recognition technologies.

[0050] At the same time, because images taken by drones are high-resolution, sample data can also be obtained from these images, thereby improving sample quality.

[0051] In this embodiment, based on preset sample data, a deep learning model is used to classify and recognize channel images, generating a classification probability map. The deep learning model can be a U-Net model, a DeepLabV3 model, or a SegFormer model; this application does not limit the specific technology of the deep learning model.

[0052] From the classification probability map in this embodiment, we can obtain a probability value corresponding to each pixel, which represents the probability that the location of the pixel is artificially restored vegetation, natural vegetation, non-vegetation, or soil erosion.

[0053] After completing step 104, in order to calculate the accurate green coverage rate after identifying the artificial greening areas, the following steps can be performed, specifically including: The classification probability map is converted into a vector image, and image processing is performed on the vector image to obtain the base distribution map. The base distribution map consists of multiple tiles, each corresponding to a set of spatial and classification attributes. The classification attributes indicate whether it is artificial vegetation, natural vegetation, non-vegetation, or water and soil flow. The spatial attributes include the vector boundary of the tile and the area size of the tile.

[0054] The image processing of the vector image includes removing small patches from the image and smoothing the edges of the removed vector image to obtain the base distribution map.

[0055] Step 105: Calculate the green coverage rate based on the classification probability map.

[0056] Specifically, the green coverage rate is calculated based on the spatial and classification attributes of each patch in the tower base distribution map. In this embodiment, the area of ​​artificial vegetation, the total area of ​​tower base disturbance, and the shaded area of ​​the shaded region are calculated based on the spatial and classification attributes of each patch in the tower base distribution map. The difference between the total area of ​​tower base disturbance and the shaded area is calculated, and the quotient of the artificial vegetation area and the difference is taken as the green coverage rate.

[0057] The green coverage rate can be used to determine the area of ​​artificial greening after the tower base is built, thus judging whether it meets the greening target.

[0058] However, after actual construction, there may be instances where the artificially planted green areas do not meet the greening standards. To check whether the artificially planted green areas meet the acceptance standards, the following steps can be performed. Details are as follows: (1) Convert the classification probability map into a vector image and perform image processing on the vector image to obtain the base distribution map.

[0059] (2) Based on the spatial and classification attributes of each patch in the base distribution map, determine the artificial vegetation area.

[0060] (3) Rasterize the images in the artificial vegetation area to obtain a vegetation raster map.

[0061] In this embodiment, image rasterization is a prior art technique and will not be elaborated upon here. It is understood that the vegetation raster map includes multiple grids, each corresponding to a vegetation coverage rate.

[0062] (4) Calculate the vegetation coverage in each grid of the vegetation raster map, and calculate the standard deviation and mean of multiple grids based on multiple vegetation coverages. The quotient of the standard deviation and the mean is used as the coefficient of variation.

[0063] (5) If the coefficient of variation is less than the preset coefficient, generate a vegetation compliance result. If the coefficient of variation is not less than the preset coefficient, generate a vegetation non-compliance result.

[0064] In this embodiment, the preset coefficient of variation can be 0.3. When the coefficient of variation is less than 0.3, it indicates that the greening is relatively uniform, and the generated vegetation compliance result is generated. Otherwise, it indicates that the vegetation distribution is uneven, with obvious bald patches or large areas of missing vegetation, resulting in poor quality and generating non-compliant vegetation result.

[0065] Compared with the prior art, the embodiments of this application have at least the following advantages: The tower base greening identification method of this application, on the one hand, can accurately identify tower base disturbance areas from the initial image based on acquired UAV images and preset tower base design data. Furthermore, since cloud cover or other obstructions exist in the initial image after shadow detection, the UAV image can be used to replace the cloud-covered portion of the initial image, thus enabling the identification of precisely defined tower base disturbance areas. Then, based on a portion of the initial image within the tower base disturbance area, and using calculated vegetation indices and sample data, a classification probability map representing the probability of vegetation and non-vegetation can be generated. This allows for direct determination of the probability of each pixel's location being vegetation from the classification probability map. Therefore, the planned vegetation coverage rate can be calculated based on the classification probability map to determine whether the artificial vegetation meets the acceptance criteria.

[0066] On the other hand, a base distribution map containing spatial and classification attributes can be obtained based on the classification probability map. The precise artificial vegetation area can then be determined by analyzing the spatial and classification attributes corresponding to each tile in the base distribution map. The images within the artificial vegetation area are then rasterized. The coefficient of variation is calculated using the vegetation coverage rate within each grid of the resulting rasterized vegetation map to further confirm the uniformity of vegetation within the artificial greening area, thereby improving the acceptance standard.

[0067] like Figure 2 The diagram shows the sub-step flowchart of the tower base greening identification method. Figure 2 The detailed steps of step 102 include: Step 201: Obtain historical images. The historical images are images of the location of the target transmission line before the start of construction.

[0068] In this embodiment, the historical images are also images captured by satellite. Among them, historical images can be selected from cloudless or low-cloud images of the land surface in its original state, serving as the baseline image for subsequent change detection.

[0069] Before performing step 202, in order to ensure the accuracy of the subsequently determined tower base disturbance area, it is necessary to perform geometric fine correction and atmospheric correction on the historical images and the initial images respectively, so that the two have the same spatial resolution and geographic coordinates, and ensure pixel-level comparability.

[0070] Step 202: Compare the historical image and the initial image by difference to obtain the change intensity image, which represents the changes on the land surface.

[0071] Understandably, historical images show the location of the target transmission line before its construction. Initial images show the location of the target transmission line after its construction.

[0072] During actual construction, activities such as construction machinery compaction, material stockpiling, and the creation of temporary access roads often extend beyond the design boundary, making it impossible to cover the actual disturbed area solely based on the design boundary. Therefore, it is necessary to utilize historical images from before construction (i.e., historical images) and as-built images (i.e., initial images) to automatically extract the actual surface disturbance range using change detection technology.

[0073] Therefore, by comparing the difference between historical and initial images, the areas of change in the two images can be obtained from the intensity variation image. That is, after the construction of the target transmission line, some of the original green areas at the location of the target transmission line will be destroyed to store construction materials, or some areas will be designated as tower foundation installation areas. Therefore, changes will be observed after comparing the historical and initial images. The intensity variation image is a grayscale image.

[0074] After performing step 202, in order to obtain a tower base disturbance zone with accurate boundaries after processing in step 203, image preprocessing can be performed on the intensity change image. The specific steps include: The intensity variation image is binarized to obtain a raster image. The pixel value of each pixel in the raster image is used to indicate whether its location is within a construction area. Noise removal and boundary extraction are then performed on the raster image to obtain the construction boundary.

[0075] In this embodiment, since the raster image is a binary image, for example, in the raster image, the area with a pixel value of 1 can be represented as the "preliminary determined disturbance area", and the area with a pixel value of 0 can be represented as the "non-disturbance area".

[0076] Small isolated variation areas in the raster image are filtered out, while continuous large-area disturbance patches are retained. This is to remove isolated variation pixels caused by accidental factors such as registration errors, shadow boundaries, movement of individual trees, and small animals, so as to retain continuous construction disturbance areas that are of engineering significance.

[0077] Next, the boundary is extracted from the raster image after noise removal. The raster-form disturbance area is converted into a vector polygon and smoothed to form the construction boundary representing the "actual disturbance boundary". This facilitates analysis in subsequent steps.

[0078] Step 203: Based on the tower base design data, determine the tower base disturbance zone from the intensity variation map.

[0079] In this embodiment, step 203 specifically includes: (1) Based on the tower base design data, identify the initial region where the tower base is located in the initial image.

[0080] As mentioned earlier, the tower base design data includes the design coordinates of the tower base and the vector data of the temporary construction land boundary line established during the construction of the tower base.

[0081] By using the tower base design data, the initial region where the tower base is located in the initial image can be initially identified, and the initial region can be used as a reference benchmark for subsequently determining the tower base disturbance zone.

[0082] (2) Based on the initial area, the tower base assessment area is determined from the intensity change map. The tower base assessment area is the area in the actual construction process.

[0083] In this embodiment, the initial area and the construction boundary are spatially superimposed to obtain the tower base evaluation area.

[0084] (3) In the initial image, obtain the shadow area of ​​the tower base within the evaluation area. If the detected shadow area is larger than a preset threshold, replace the shadow area with the UAV image to obtain the tower base disturbance area.

[0085] In this embodiment, the preset threshold can be set according to the actual situation. For example, the preset threshold can be 10%. This application does not limit the specific value of the preset threshold.

[0086] If the detected shadow area is no larger than a preset threshold, it indicates that there is almost no cloud cover or other issues in the initial image, so there is no need to replace the shadow area with drone images to obtain the tower base disturbance area.

[0087] The initial image is used for cloud cover and shadow detection. If the cloud coverage area in the tower base assessment area exceeds a preset threshold (e.g., 10%), or the shadow area is too large and cannot be recovered after compensation, the process of replacing the shadow area with the UAV image is triggered. This allows for a more accurate determination of the tower base disturbance area.

[0088] For example, the perturbation boundary extracted from UAV images is fused with the boundary extracted from the initial image. For areas where the initial image is clear and cloudless, the boundary extraction results from the satellite image are retained; for areas where the initial image is affected by clouds or shadows, the perturbation boundary results extracted from the UAV are directly replaced. If the entire tower base area is covered by clouds, the boundary extracted from the UAV image is used entirely as the final perturbation assessment area (i.e., the tower base perturbation area).

[0089] Furthermore, since drones are frequently used to inspect construction progress in power projects, using drone images to assist in processing initial images to determine the precise tower foundation disturbance zone not only does not increase processing costs but also makes efficient use of resources to determine the precise boundary of the tower foundation disturbance zone.

[0090] like Figure 3The diagram shown is a structural schematic of the tower base greening identification system of this application. The tower base greening identification system 200 includes an acquisition module 210, an identification module 220, a first calculation module 230, a classification module 240, and a second calculation module 250.

[0091] The acquisition module 210 is used to acquire drone images and initial images after shadow detection. The initial image is an image of the location of the target power transmission line before the greening restoration after the completion of the project construction. The shooting time of the drone images and the shooting time of the initial images are within a preset time range.

[0092] The identification module 220 is used to identify the tower base disturbance area in the initial image based on the preset tower base design data and the UAV image. The tower base design data includes the design coordinates of the tower base and the vector data of the temporary construction land boundary line established when constructing the tower base. The tower base disturbance area represents the area within the scope of the temporary construction land.

[0093] The first calculation module 230 is used to calculate the vegetation index based on the image of the tower base disturbance area, and stack the vegetation index and multiple bands in the image of the tower base disturbance area to obtain a multi-channel image.

[0094] The classification module 240 is used to classify and identify the channel image using preset sample data and generate a classification probability map, wherein the classification probability map represents the probability of vegetation and non-vegetation.

[0095] The second calculation module 250 is used to calculate the green coverage rate based on the classification probability map.

[0096] The advantages of the Tower Base Greening Identification System 200 are the same as those of the Tower Base Greening Identification Method, and will not be repeated here.

[0097] Figure 4 This is a schematic diagram of an embodiment of the electronic device of this application. The electronic device 100 includes a memory 20, a processor 30, and a computer program 40 stored in the memory 20 and executable on the processor 30. When the processor 30 executes the computer program 40, it implements the steps in the above-described method embodiments.

[0098] The electronic device 100 is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, processors, microprogrammed control units (MCUs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0099] For example, computer program 40 can also be divided into one or more modules / units, which are stored in memory 20 and executed by processor 30. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 40 in electronic device 100.

[0100] Those skilled in the art will understand that the schematic diagram is merely an example of the electronic device 100 and does not constitute a limitation on the electronic device 100. It may include more or fewer components than shown in the diagram, or combine certain components, or different components. For example, the electronic device 100 may also include input / output devices, network access devices, buses, etc.

[0101] Processor 30 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors, single-chip microcomputers, or any conventional processor.

[0102] The memory 20 can be used to store computer programs 40 and / or modules / units. The processor 30 implements various functions of the electronic device 100 by running or executing the computer programs and / or modules / units stored in the memory 20 and by calling data stored in the memory 20. The memory 20 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device 100 (such as audio data), etc. In addition, the memory 20 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0103] If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0104] This application also provides a computer-readable storage medium, which may include the above-described electronic device.

[0105] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the electronic device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and other division methods may be used in actual implementation.

[0106] Furthermore, the functional units in the various embodiments of this application can be integrated into the same processing unit, or each unit can exist physically separately, or two or more units can be integrated into the same unit. The integrated units described above can be implemented in hardware or in the form of hardware plus software functional modules.

[0107] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and not restrictive in all respects. Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or electronic devices recited in the electronic device claims may also be implemented by the same unit or electronic device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A method for identifying greenery at the base of a tower, characterized in that, The method for identifying greenery at the tower base includes: Acquire drone images and initial images after shadow detection. The initial images are images of the location of the target power transmission line before greening restoration after the completion of engineering construction. The time of capturing the drone images and the time of capturing the initial images are within a preset time range. Based on the preset tower base design data and the UAV image, the tower base disturbance zone in the initial image is identified. The tower base design data includes the design coordinates of the tower base and the vector data of the temporary construction land boundary line established when the tower base is constructed. The tower base disturbance zone represents the area within the scope of the temporary construction land. Based on the image of the tower base disturbance area, the vegetation index is calculated, and the vegetation index and the multi-band images of the tower base disturbance area are stacked to obtain a multi-channel image. Using preset sample data, the channel images are classified and identified to generate a classification probability map, which represents the probability of vegetation and non-vegetation. The green coverage rate is calculated based on the classification probability map.

2. The method for identifying greenery at the base of a tower according to claim 1, characterized in that, The process of identifying tower base disturbance zones within the initial image based on preset tower base design data and the UAV image includes: Acquire historical images, which are images of the location of the target transmission line before the start of construction. The historical image and the initial image are compared by difference to obtain a change intensity image, which represents the changes in the land surface. Based on the tower base design data, the tower base disturbance zone is determined from the intensity variation diagram.

3. The method for identifying greenery at the base of a tower according to claim 2, characterized in that, The process of determining the tower foundation disturbance zone from the intensity variation map based on the tower foundation design data includes: Based on the tower base design data, identify the initial region where the tower base is located within the initial image; Based on the initial region, the tower base assessment area is determined from the intensity change map, and the tower base assessment area is the area in the actual construction process; Within the tower base evaluation area in the initial image, the shadow region of the area where the tower base is located is obtained; If the detected shadow area is larger than a preset threshold, the shadow area is replaced with the drone image to obtain the tower base disturbance area.

4. The method for identifying greenery at the base of a tower according to claim 3, characterized in that, After comparing the historical image and the initial image by difference to obtain a change intensity image, the method further includes: The intensity change image is binarized to obtain a raster image, and the pixel value of each pixel in the raster image is used to indicate whether the location is a construction area; The raster image is subjected to noise removal and boundary extraction processing to obtain the construction boundary; The process of determining the tower base assessment area from the change intensity map based on the initial region includes: The initial area and the construction boundary are spatially superimposed to obtain the tower base evaluation area.

5. The method for identifying greenery at the base of a tower according to claim 3, characterized in that, After classifying and recognizing the channel images using preset sample data to generate a classification probability map, the method further includes: The classification probability map is converted into a vector image, and the vector image is processed to obtain a base distribution map. The base distribution map includes multiple patches, each of which corresponds to a set of spatial attributes and classification attributes. The classification attributes are used to indicate whether it is artificial vegetation, natural vegetation, non-vegetation, or water and soil flow. The calculation of green coverage rate based on the classification probability map includes: The green coverage rate is calculated based on the spatial attributes and classification attributes corresponding to each of the patches in the tower base distribution map.

6. The method for identifying greenery at the base of a tower according to claim 5, characterized in that, The calculation of the green coverage rate based on the spatial attributes and classification attributes corresponding to each patch in the tower base distribution map includes: Based on the spatial and classification attributes corresponding to each of the blocks in the tower base distribution map, calculate the area of ​​artificial vegetation, the total area of ​​tower base disturbance, and the shaded area of ​​the shaded region; Calculate the difference between the total area of ​​the tower base disturbance and the area of ​​the shadow; The quotient of the artificial vegetation area and the difference is taken as the green coverage rate.

7. The method for identifying greenery at the base of a tower according to claim 5, characterized in that, After converting the classification probability map into a vector image and performing image processing on the vector image to obtain the base distribution map, the method further includes: Based on the spatial and classification attributes corresponding to each of the patches in the tower base distribution map, artificial vegetation zones are determined. The images within the artificial vegetation area are rasterized to obtain a vegetation raster map; Calculate the vegetation coverage rate within each grid of the vegetation raster map; Based on multiple vegetation coverage rates, calculate the standard deviation and mean of multiple grids; The quotient of the standard deviation and the mean is used as the coefficient of variation; If the coefficient of variation is found to be less than a preset coefficient, a vegetation compliance result is generated; If the coefficient of variation is detected to be not less than the preset coefficient, a vegetation non-compliance result is generated.

8. A tower base greening identification system, characterized in that, The system includes: The acquisition module is used to acquire drone images and initial images after shadow detection. The initial images are images of the location of the target power transmission line before the greening is restored after the completion of the project construction. The time of the drone image acquisition and the time of the initial image acquisition are within a preset time range. The identification module is used to identify the tower base disturbance area in the initial image based on the preset tower base design data and the UAV image. The tower base design data includes the design coordinates of the tower base and the vector data of the temporary construction land boundary line established when the tower base is constructed. The tower base disturbance area represents the area within the scope of the temporary construction land. The first calculation module is used to calculate the vegetation index based on the image of the tower base disturbance area, and stack the vegetation index and the multi-band images of the tower base disturbance area to obtain a multi-channel image. The classification module is used to classify and identify the channel images using preset sample data and generate a classification probability map, which represents the probability of vegetation and non-vegetation. The second calculation module is used to calculate the green coverage rate based on the classification probability map.

9. An electronic device, characterized in that, The electronic device includes: a memory storing computer-readable instructions; and a processor executing the computer-readable instructions stored in the memory to implement the tower base greening identification method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which are executed by a processor in an electronic device to implement the tower base greening identification method as described in any one of claims 1 to 7.

Images