Distributed photovoltaic installed capacity calculation method, device, equipment and medium

Abstract

The application relates to the technical field of new energy, and discloses a distributed photovoltaic installed capacity calculation method, device, equipment and medium, the distributed photovoltaic installed capacity calculation method comprises the following steps: acquiring orthographic projection image data of a satellite under a preset spatial scale; performing photovoltaic module segmentation on the orthographic projection image data to obtain a plurality of segmentation images containing various distributed photovoltaic modules; performing edge detection on each segmentation image to obtain a target area corresponding to each distributed photovoltaic module; performing photovoltaic module identification on the target area based on a preset target detection rule to obtain a photovoltaic module type corresponding to each target area; performing distributed photovoltaic installed capacity calculation on the area of the target area corresponding to each photovoltaic module type and the capacity corresponding to each photovoltaic module type to obtain a capacity calculation result; the distributed photovoltaic installed capacity in a self-defined field can be intelligently and automatically evaluated, and the distributed photovoltaic can be conveniently managed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new energy, in particular to a distributed photovoltaic installed capacity calculation method and device, computer equipment and storage medium. BACKGROUND

[0002] Due to the scattered spatial distribution of distributed photovoltaic, and the small scale, as well as the problems of different sizes of components, whether the components are missing or not, it is difficult to systematically and accurately evaluate the distributed photovoltaic installed capacity in a region; when the distributed photovoltaic installed capacity cannot be accurately evaluated, it plays a crucial role in the scheduling arrangement of the photovoltaic power system, the advance planning of the photovoltaic power station and the management of new energy photovoltaic.

[0003] However, in the related art, the capacity calculation of distributed photovoltaic usually adopts a manual statistical method; the manual statistical method is time-consuming and prone to errors, and cannot meet the requirements of automatic scanning, range coverage and intelligent evaluation accuracy.

[0004] Therefore, it is urgent to propose a distributed photovoltaic installed capacity calculation method to solve the problems in the related art. SUMMARY

[0005] Therefore, the present application provides a distributed photovoltaic installed capacity calculation method, device, equipment and medium to solve the problems in the related art.

[0006] In a first aspect, the present application provides a distributed photovoltaic installed capacity calculation method, which comprises: obtaining orthographic image data of a satellite under a preset spatial scale; wherein the preset spatial scale includes the geographical position of each distributed photovoltaic component; performing photovoltaic component segmentation on the orthographic image data to obtain a plurality of segmented images containing each distributed photovoltaic component; performing edge detection on each segmented image to obtain a target area corresponding to each distributed photovoltaic component; wherein the boundary of the target area represents the contour edge of the distributed photovoltaic component; performing photovoltaic component identification on the target area based on a preset target detection rule to obtain a photovoltaic component type corresponding to each target area; wherein the target detection rule includes the corresponding relationship between the preset category features of each type of photovoltaic panel and the preset feature label; and performing distributed photovoltaic installed capacity calculation based on the area of the target area corresponding to each photovoltaic component type and the capacity corresponding to each photovoltaic component type to obtain a capacity calculation result.

[0007] As an exemplary embodiment, the target detection on the target region based on the preset target detection rule to obtain the component type corresponding to each target region comprises: obtaining a correspondence between each category feature and feature label in the preset target detection rule; performing target detection on the target region based on the category feature to obtain the component type corresponding to each target region.

[0008] As an exemplary embodiment, the edge detection on each segmented image to obtain the target region of each distributed photovoltaic component comprises: performing Gaussian filtering on each segmented image to obtain a filtered segmented image; performing gradient calculation on the filtered segmented image based on a Sobel operator to obtain a gradient calculation result; based on the gradient calculation result, performing non-maximum suppression and double-threshold hysteresis threshold processing on the filtered segmented image in sequence by using a Canny algorithm to obtain the target region.

[0009] As an exemplary embodiment, before the distributed photovoltaic installed capacity calculation based on each target region and the corresponding photovoltaic component type, the method further comprises: performing state detection on each target region to obtain a state detection result; and excluding an abnormal region in an abnormal state from the target region.

[0010] As an exemplary embodiment, the state detection on each target region to obtain a state detection result comprises: performing semantic recognition on the boundary of each target region to obtain actual semantic features of pixels constituting the boundary of each target region; comparing the actual semantic features with preset semantic features to obtain a comparison result; wherein the preset semantic features are used for photovoltaic component contours; calculating a normal pixel actual proportion of the photovoltaic component contour relative to the pixels constituting the boundary of each target region based on the comparison result; and marking a target region with an actual proportion not greater than a preset proportion as an abnormal region.

[0011] As an exemplary embodiment, the state detection on each target region to obtain a state detection result further comprises: obtaining a preset geometric feature of the photovoltaic component type corresponding to each target region; extracting an actual geometric feature of each target region; wherein the actual geometric feature is used to represent a boundary shape of the boundary constituting the target region; comparing the actual geometric feature with the preset geometric feature to obtain a comparison result; and based on the comparison result, marking a target region with an actual geometric feature not satisfying a preset geometric feature as an abnormal region.

[0012] As an exemplary embodiment, the state detection on each of the target regions to obtain a state detection result further includes: dividing pixels in each of the target regions based on semantic features of the pixels to obtain abnormal pixels that do not represent the semantic features of the photovoltaic module; calculating an actual abnormal proportion of the abnormal pixels in the target region; and marking a target region with an actual abnormal proportion greater than a preset abnormal proportion as being in an abnormal state.

[0013] In a second aspect, the present application provides a distributed photovoltaic installed capacity calculation device, comprising: a satellite data acquisition module, configured to acquire orthographic image data of a satellite at a preset spatial scale; wherein the preset spatial scale contains a geographical location where each of the distributed photovoltaic modules is located; an image segmentation module, configured to perform photovoltaic module segmentation on the orthographic image data to obtain a plurality of segmentation images containing each of the distributed photovoltaic modules; an edge detection module, configured to perform edge detection on each of the segmentation images to obtain a target region corresponding to each of the distributed photovoltaic modules; wherein the boundary of the target region is used to represent the contour edge of the distributed photovoltaic module; a photovoltaic module identification module, configured to perform photovoltaic module identification on the target region based on a preset target detection rule to obtain a photovoltaic module type corresponding to each of the target regions; wherein the target detection rule includes a correspondence relationship between a preset category feature of each type of photovoltaic panel and a preset feature label; and a capacity calculation module, configured to perform distributed photovoltaic installed capacity calculation based on an area of the target region corresponding to each of the photovoltaic module types and a capacity corresponding to each of the photovoltaic module types to obtain a capacity calculation result.

[0014] In a third aspect, the present application provides a computer device, comprising: a memory and a processor, which are communicatively connected to each other, and the memory stores computer instructions; the processor executes the computer instructions to perform the distributed photovoltaic installed capacity calculation method of the first aspect or any of the corresponding embodiments thereof.

[0015] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer instructions for causing a computer to perform the distributed photovoltaic installed capacity calculation method of the first aspect or any of the corresponding embodiments thereof.

[0016] The application provides a distributed photovoltaic installed capacity calculation method, which comprises the following steps: acquiring orthographic image data of satellites under a preset spatial scale; wherein the preset spatial scale comprises geographical positions where each distributed photovoltaic component is located; performing photovoltaic component segmentation on the orthographic image data to obtain a plurality of segmented images containing each distributed photovoltaic component; performing edge detection on each segmented image to obtain a target area corresponding to each distributed photovoltaic component; wherein the boundary of the target area is used to represent the contour edge of the distributed photovoltaic component; performing photovoltaic component identification on the target area based on a preset target detection rule to obtain a photovoltaic component type corresponding to each target area; wherein the target detection rule comprises a corresponding relationship between preset category characteristics of each type of photovoltaic panel and a preset feature label; performing distributed photovoltaic installed capacity calculation based on the area of the target area corresponding to each photovoltaic component type and the capacity corresponding to each photovoltaic component type to obtain a capacity calculation result; the above embodiment can extract the target area representing each distributed photovoltaic component from the orthographic image data of the geographical position where each distributed photovoltaic component is located through the feature of the distributed photovoltaic component; further, performing photovoltaic component identification on the target area based on a preset target detection rule to obtain a photovoltaic component type of each target area, and further, performing distributed photovoltaic installed capacity calculation based on the area of the target area corresponding to each photovoltaic component type and the capacity corresponding to each photovoltaic component type, which can intelligently and automatically evaluate the distributed photovoltaic installed capacity in the self-defined field, and facilitate the management of distributed photovoltaic. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the description of the specific embodiments or the prior art. Obviously, the drawings described below are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0018] Figure 1 FIG. 1 is a flow diagram of a distributed photovoltaic installed capacity calculation method according to an embodiment of the present application;

[0019] Figure 2 FIG. 2 is a structural block diagram of a distributed photovoltaic installed capacity calculation device according to an embodiment of the present application;

[0020] Figure 3 FIG. 3 is a hardware structure diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0022] According to the embodiments of the present application, a distributed photovoltaic installed capacity calculation method is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0023] In the present embodiment, a distributed photovoltaic installed capacity calculation method is provided, Figure 1 is a flowchart of the distributed photovoltaic installed capacity calculation method according to the embodiments of the present application, as Figure 1 shown, the flow includes the following steps:

[0024] Step S101, obtaining orthographic image data of a satellite under a preset spatial scale; wherein the preset spatial scale contains the geographical location of each distributed photovoltaic component.

[0025] Due to the spatial distribution of distributed photovoltaic is scattered and small in scale, and the problems of different size components, whether the components are missing or not, it is difficult to systematically and accurately evaluate the distributed photovoltaic installed capacity in a region; in order to include all the distributed photovoltaic to be evaluated in the orthographic image data, in the present embodiment, the orthographic image data of the satellite under the preset spatial scale is obtained, and the preset spatial scale contains the geographical location of each distributed photovoltaic component.

[0026] Exemplarily, the preset spatial scale can be defined by the operator in advance, and the defined preset spatial scale contains the geographical location of each distributed photovoltaic component.

[0027] Wherein, the orthographic image data of the satellite is RGB orthographic image data; exemplarily, the RGB orthographic image data can be obtained through Beijing No. 2 BJ-2, GF-2 or Google-earth high-definition satellite map.

[0028] Step S102, performing photovoltaic component segmentation on the orthographic image data to obtain a plurality of segmentation images containing each distributed photovoltaic component.

[0029] In the embodiment, the orthographic image data is segmented to obtain a plurality of segmented images of the distributed photovoltaic modules contained in the orthographic image data.

[0030] As a possible implementation, the segmentation of the photovoltaic module can be implemented by a deep learning-based image segmentation algorithm; specifically, the deep learning-based image segmentation algorithm can include MS-GeoNet, Double U-Net, or DeepLab, etc.

[0031] In step S103, edge detection is performed on each of the segmented images to obtain a target region corresponding to each of the distributed photovoltaic modules; wherein the boundary of the target region is used to represent the contour edge of the distributed photovoltaic module.

[0032] In the plurality of segmented images containing the photovoltaic module, in order to further determine the area of the photovoltaic module, edge detection is performed on each of the segmented images to obtain a target region corresponding to each of the distributed photovoltaic modules; the area of the target region is the area of the photovoltaic module.

[0033] Exemplarily, when performing edge detection on the segmented image, the Canny algorithm can be used; specifically, when performing edge detection on the segmented image using the Canny algorithm, first, a Gaussian filter is used to smooth the image to obtain a filtered segmented image to remove noise in the image; further, based on the Sobel operator, gradient calculation is performed on the filtered segmented image to obtain a gradient calculation result; further, based on the gradient calculation result, the Canny algorithm is used to sequentially perform non-maximum suppression and double-threshold hysteresis threshold processing on the filtered segmented image to obtain the target region.

[0034] In step S104, photovoltaic module recognition is performed on the target region based on a preset target detection rule to obtain a photovoltaic module type corresponding to each of the target regions; wherein the target detection rule includes a correspondence relationship between a preset category feature of each type of photovoltaic panel and a preset feature label.

[0035] The photovoltaic module type is divided into single-crystal photovoltaic modules, polycrystalline photovoltaic modules, thin-film photovoltaic modules, and multi-element compound photovoltaic modules. Since different photovoltaic modules correspond to different rated capacities, after obtaining the target region representing each distributed photovoltaic module, it is necessary to identify the type of the photovoltaic module, and further calculate the installed capacity of the distributed photovoltaic module according to the identified type of the photovoltaic module and the area of the corresponding target region.

[0036] In the embodiment, the identification of the component types of the photovoltaic components can be achieved through target detection; specifically, in the process of target detection, the photovoltaic component identification is performed on the target regions based on preset target detection rules to obtain the photovoltaic component types corresponding to each target region; wherein the target detection rules include the correspondence between the preset category features and the preset feature labels of photovoltaic panels of each type.

[0037] Exemplarily, the target detection rules include the correspondence between the preset category features and the preset feature labels of photovoltaic panels of monocrystalline photovoltaic components, polycrystalline photovoltaic components, thin-film photovoltaic components, and multi-element compound photovoltaic components.

[0038] Wherein, as a possible implementation, the preset target detection rules can be determined through pre-calibration; specifically, the preset segmentation images corresponding to the preset monocrystalline photovoltaic components, the preset polycrystalline photovoltaic components, the preset thin-film photovoltaic components, and the preset multi-element compound photovoltaic components are obtained; the distinguishing features of each of the preset segmentation images with respect to other segmentation images are extracted, and the distinguishing features are taken as the preset category features.

[0039] In an embodiment, the distinguishing features can be embodied by different colors represented by each photovoltaic component in the orthographic image data.

[0040] In an embodiment, the photovoltaic component identification based on the preset target detection rules on the target regions can be achieved through a deep learning target detection model; specifically, after obtaining the preset segmentation images corresponding to the preset monocrystalline photovoltaic components, the preset polycrystalline photovoltaic components, the preset thin-film photovoltaic components, and the preset multi-element compound photovoltaic components, the preset segmentation images are labeled to obtain the preset category features corresponding to each preset segmentation image; the preset segmentation images with the labeled preset category features are taken as input features, and the photovoltaic component types corresponding to each preset segmentation image are taken as labels as a training set, which is input into a pre-constructed deep learning target detection model for model training; in the process of model training, the model parameters are constantly adjusted, so that the deep learning target detection model can extract the preset category features and output the corresponding photovoltaic component types based on the preset category features, to obtain the deep learning target detection model.

[0041] Exemplarily, the deep learning target detection model can be constructed based on YOLOv8 or RetinaNet.

[0042] Step S105, based on the area of the target region corresponding to each photovoltaic component type and the capacity corresponding to each photovoltaic component type, the distributed photovoltaic installed capacity is calculated to obtain the capacity calculation result.

[0043] In the embodiment, after the target area corresponding to each type of photovoltaic module is obtained, the capacity calculation result is obtained by calculating the area of the target area and the rated capacity corresponding to the photovoltaic module.

[0044] The embodiment calculates the distributed photovoltaic installed capacity by a method, which comprises: obtaining orthographic image data of a satellite under a preset spatial scale; wherein the preset spatial scale contains geographical positions of each distributed photovoltaic module; performing photovoltaic module segmentation on the orthographic image data to obtain a plurality of segmented images containing each distributed photovoltaic module; performing edge detection on each segmented image to obtain a target area corresponding to each distributed photovoltaic module; wherein the boundary of the target area represents the contour edge of the distributed photovoltaic module; performing photovoltaic module identification on the target area based on a preset target detection rule to obtain a photovoltaic module type corresponding to each target area; wherein the target detection rule comprises a corresponding relationship between a preset category feature of each type of photovoltaic panel and a preset feature label; performing distributed photovoltaic installed capacity calculation based on the area of the target area corresponding to each photovoltaic module type and the capacity corresponding to each photovoltaic module type to obtain a capacity calculation result; the above embodiment can extract a target area representing each distributed photovoltaic module from the orthographic image data of the geographical position of each distributed photovoltaic module by feature extraction of the distributed photovoltaic module; further, performing photovoltaic module identification on the target area based on a preset target detection rule to obtain a photovoltaic module type of each target area, and further performing distributed photovoltaic installed capacity calculation based on the area of the target area corresponding to each photovoltaic module type and the capacity corresponding to each photovoltaic module type, which can intelligently and automatically evaluate the distributed photovoltaic installed capacity in a custom field, and facilitate the management of distributed photovoltaic.

[0045] As an exemplary embodiment, the target detection on the target area based on the preset target detection rule to obtain a module type corresponding to each target area comprises: obtaining a corresponding relationship between each category feature and feature label in the preset target detection rule; performing target detection on the target area based on the category feature to obtain a module type corresponding to each target area.

[0046] In the embodiment, the corresponding relationship between each category feature and feature label in the preset target detection rule can be obtained by pre-calibration; specifically, obtaining a preset segmented image corresponding to a preset single-crystal photovoltaic module, a preset polycrystalline photovoltaic module, a preset thin-film photovoltaic module and a preset multi-element compound photovoltaic module; extracting a distinguishing feature of each preset segmented image with respect to other segmented images, and taking the distinguishing feature as the category feature.

[0047] As an exemplary embodiment, the edge detection on each of the segmented images to obtain the target region of each of the distributed photovoltaic modules comprises: performing Gaussian filtering on each of the segmented images to obtain a filtered segmented image; performing gradient calculation on the filtered segmented image based on a Sobel operator to obtain a gradient calculation result; and performing non-maximum suppression and double-threshold hysteresis threshold processing on the filtered segmented image based on the gradient calculation result and using a Canny algorithm in sequence to obtain the target region.

[0048] In the embodiment, when the Canny algorithm is used to perform edge detection on the segmented image, Gaussian filtering is first used to smooth the image to obtain a filtered segmented image to remove noise of the image; further, gradient calculation is performed on the filtered segmented image based on a Sobel operator to obtain a gradient calculation result; further, non-maximum suppression and double-threshold hysteresis threshold processing are performed on the filtered segmented image based on the gradient calculation result and using a Canny algorithm in sequence to obtain the target region.

[0049] The embodiments of the distributed photovoltaic installed capacity calculation method can realize calculation of the distributed photovoltaic installed capacity; however, in the actual use of the distributed photovoltaic, there are some photovoltaic modules in abnormal states such as broken, blocked, broken, missing and the like due to hail, branches, aging and other factors in the use process. When the above photovoltaic modules in the damaged state are used as normal states to participate in the photovoltaic installed capacity calculation, the calculation result will deviate, and therefore, it is necessary to exclude the above distributed photovoltaic modules in the abnormal state when the photovoltaic installed capacity calculation is performed.

[0050] Therefore, as an exemplary embodiment, before the distributed photovoltaic installed capacity calculation based on each of the target regions and the corresponding photovoltaic module type, the method further comprises: performing state detection on each of the target regions to obtain a state detection result; and excluding an abnormal region in an abnormal state from the target regions.

[0051] In an embodiment, for the photovoltaic modules in the abnormal states such as broken, blocked, broken, missing and the like, there are characteristics of incomplete edges or missing photovoltaic modules in the regions; therefore, the state detection can be performed on each of the target regions based on the above characteristics to obtain a state detection result, and further, an abnormal region in an abnormal state can be excluded from the target regions.

[0052] Exemplarily, after edge detection is performed on each of the segmented images to obtain a target region corresponding to each of the distributed photovoltaic modules, whether the photovoltaic module corresponding to the target region is complete can be determined by judging the region boundary of the target region, and the target region in which the photovoltaic module is incomplete is marked as an abnormal region.

[0053] Specifically, when the photovoltaic panel is blocked, the boundary of the photovoltaic panel is affected, and the actual semantic feature of the boundary pixel does not exhibit the preset semantic feature representing the contour of the photovoltaic module. Based on this, after obtaining the target region corresponding to each of the distributed photovoltaic modules, the semantic feature of the pixel constituting the boundary of each target region can be obtained by performing semantic recognition on the boundary of each target region. Further, the actual semantic feature is compared with the preset semantic feature representing the contour of the photovoltaic module to obtain a comparison result. Based on the comparison result, the actual proportion of the normal pixel representing the contour of the photovoltaic module with respect to the pixel constituting the boundary of each target region is calculated. The target region in which the actual proportion is not greater than a preset proportion is marked as an abnormal region.

[0054] In an embodiment, since the photovoltaic module in a normal state usually has a fixed geometric shape, the geometric feature of the boundary of the photovoltaic module in an abnormal state due to, for example, breaking, blocking, breaking, missing, etc. is different from the photovoltaic module in a normal state. For example, the photovoltaic module in a normal state usually has a shape such as a rectangle, and the flatness of the boundary is relatively flat. Therefore, after obtaining the target region corresponding to each of the distributed photovoltaic modules, whether the photovoltaic module corresponding to the target region is complete can be determined according to the geometric feature of the boundary of the target region.

[0055] Specifically, after obtaining the target region corresponding to each of the distributed photovoltaic modules, photovoltaic module recognition can be further performed on the target region based on a preset target detection rule to obtain the type of photovoltaic module corresponding to each of the target regions. The preset geometric feature is determined based on the type of photovoltaic module. The preset geometric feature is obtained by collecting the photovoltaic module in a normal and non-missing state. Further, the actual geometric feature of each of the target regions is extracted. The actual geometric feature is compared with the preset geometric feature, and the target region in which the actual geometric feature does not satisfy the preset geometric feature is marked as an abnormal region.

[0056] In an embodiment, whether the photovoltaic module corresponding to the target region is complete can also be determined by detecting the semantic feature contained in the pixel in the target region.

[0057] Specifically, after obtaining the target region corresponding to each of the distributed photovoltaic components, the pixels constituting each of the target regions are subjected to semantic recognition to obtain semantic features of each of the pixels; the pixels in each of the target regions are divided based on the semantic features of the pixels to obtain abnormal pixels whose semantic features do not represent photovoltaic components; the actual abnormal proportion of the abnormal pixels in the target region is calculated; a preset abnormal proportion is determined based on the photovoltaic component type of the target region; and the target region whose actual included angle does not satisfy the preset included angle is marked as an abnormal state.

[0058] Based on this, as an exemplary embodiment, the state detection on each of the target regions to obtain a state detection result includes: performing semantic recognition on the boundaries of each of the target regions to obtain actual semantic features of the pixels constituting the boundaries of each target region; comparing the actual semantic features with preset semantic features to obtain a comparison result; wherein the preset semantic features are used for photovoltaic component contours; calculating an actual proportion of normal pixels representing photovoltaic component contours with respect to the pixels constituting the boundaries of each target region based on the comparison result; and marking the target region whose actual proportion is not greater than a preset proportion as an abnormal region.

[0059] In this embodiment, the detection of the abnormal region is realized by performing semantic recognition on the boundaries of each of the target regions.

[0060] Wherein, as a possible implementation, the preset proportion is 0.95.

[0061] As an exemplary embodiment, the state detection on each of the target regions to obtain a state detection result further includes: obtaining a preset geometric feature of a photovoltaic component type corresponding to each of the target regions; extracting an actual geometric feature of each of the target regions; wherein the actual geometric feature is used to represent a boundary shape of the boundaries constituting the target region; comparing the actual geometric feature with the preset geometric feature to obtain a comparison result; and based on the comparison result, marking the target region whose actual geometric feature does not satisfy the preset geometric feature as an abnormal region.

[0062] In this embodiment, the detection of the abnormal region is realized by detecting the geometric features of each of the target regions.

[0063] As a possible implementation, when the photovoltaic panel is in the state of being broken, blocked, broken, or missing, the boundary of the photovoltaic panel is affected and cannot maintain the original flatness, therefore, in an embodiment, the geometric feature includes the actual flatness of the boundary of the target region; specifically, the actual geometric feature of each target region can be obtained by calculating the actual flatness of the boundary of each target region, further, a preset flatness is determined as a preset geometric feature based on the type of the photovoltaic component of the target region, and finally, the actual flatness and the preset flatness are compared, and the target region whose actual flatness does not satisfy the preset flatness is marked as an abnormal state.

[0064] As another possible implementation, the state of each target region is detected, when the photovoltaic panel is in the state of being broken, blocked, broken, or missing, the boundary of the photovoltaic panel is affected and cannot maintain the original angle, therefore, in an embodiment, the geometric feature includes the actual included angle of two intersecting region boundaries in the target region; specifically, the actual geometric feature of each target region can be obtained by calculating the actual included angle of two intersecting region boundaries in each target region; further, a preset included angle is determined based on the type of the photovoltaic component of the target region; finally, the actual included angle and the preset included angle are compared, and the target region whose actual flatness does not satisfy the preset flatness is marked as an abnormal state.

[0065] As an exemplary embodiment, the state of each target region is detected to obtain a state detection result, and the method further includes: dividing the pixels in each target region based on the semantic features of the pixels to obtain abnormal pixels whose semantic features do not represent photovoltaic components; calculating the actual abnormal proportion of the abnormal pixels in the target region; determining a preset abnormal proportion based on the type of the photovoltaic component of the target region; and marking the target region whose actual included angle does not satisfy the preset included angle as an abnormal state.

[0066] The embodiment provides a distributed photovoltaic installed capacity calculation device, as shown in the accompanying drawings, which comprises: Figure 2

[0067] A satellite data acquisition module 201 is configured to acquire orthographic image data of a satellite at a preset spatial scale; wherein the preset spatial scale contains geographical positions of each distributed photovoltaic component;

[0068] An image segmentation module 202 is configured to perform photovoltaic component segmentation on the orthographic image data to obtain a plurality of segmentation images containing each distributed photovoltaic component;

[0069] ​The edge detection module 203 is used to perform edge detection on each of the segmented images to obtain the target region corresponding to each of the distributed photovoltaic modules; wherein, the boundary of the target region is used to represent the contour edge of the distributed photovoltaic module;

[0070] The photovoltaic module identification module 204 is used to identify photovoltaic modules in the target area based on preset target detection rules, and obtain the photovoltaic module type corresponding to each target area; wherein, the target detection rules include the correspondence between preset category features and preset feature labels of each type of photovoltaic panel;

[0071] The capacity calculation module 205 is used to calculate the distributed photovoltaic installed capacity based on the area of ​​the target area corresponding to each photovoltaic module type and the capacity corresponding to each photovoltaic module type, and to obtain the capacity calculation result.

[0072] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments.

[0073] It should be noted that the above modules, as part of the device, can be implemented in software or hardware, with the hardware environment including the network environment.

[0074] This invention also provides a computer device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory is used to store computer programs; and the processor is used to execute the methods described in any of the above embodiments by running the computer programs stored in the memory.

[0075] Figure 3 This is a structural block diagram of an optional computer device according to an embodiment of this application, such as... Figure 3 As shown, it includes a processor 10, a communication interface 20, a memory 30, and a communication bus 40. The processor 10, communication interface 20, and memory 30 communicate with each other via the communication bus 40.

[0076] Memory 30 is used to store computer programs;

[0077] When the processor 10 executes the computer program stored in the memory 30, it implements the distributed photovoltaic installed capacity calculation method as described in any of the above embodiments.

[0078] Optionally, in this embodiment, the communication bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0079] The communication interface is used for communication between the aforementioned computer equipment and other devices.

[0080] The memory may include RAM, or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0081] The processors mentioned above can be general-purpose processors, including but not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; they can also be DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0082] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated here.

[0083] Those skilled in the art will understand that Figure 3 The structure shown is for illustrative purposes only. The device that implements any of the methods in the above embodiments can be a terminal device, such as a smartphone (e.g., an Android phone, an iOS phone), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, or other terminal devices. Figure 3 This does not limit the structure of the aforementioned electronic device. For example, the terminal device may also include components that are more... Figure 3 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 3Different configurations are shown.

[0084] Those skilled in the art can understand that all or part of the steps of various methods in the above embodiments can be completed by instructing the terminal device related hardware through a program, and the program can be stored in a computer readable storage medium, which can include a flash disk, a ROM, a RAM, a magnetic disk or an optical disk, etc.

[0085] As an exemplary embodiment, the present application also provides a computer readable storage medium, which stores a computer program, wherein the computer program is configured to execute the method steps of any one of the embodiments when running.

[0086] Optionally, in the embodiment, the storage medium can be used for the program code for executing the method steps of the embodiments of the present application.

[0087] Optionally, in the embodiment, the storage medium can be located on at least one of the network devices in the network shown in the above embodiments.

[0088] Optionally, in the embodiment, the storage medium is configured to store the method for executing the above embodiments.

[0089] Optionally, the specific examples in the embodiment can refer to the examples described in the above embodiments, and the embodiment will not be described here.

[0090] Optionally, in the embodiment, the storage medium can include but is not limited to a U disk, a ROM, a RAM, a mobile hard disk, a magnetic disk or an optical disk, etc. various media that can store program codes.

[0091] The serial number of the above embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments.

[0092] The integrated units in the above embodiments, if realized in the form of software function units and sold or used as independent products, can be stored in the above computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or the whole or part of the technical solutions can be embodied in the form of software products, and the computer software products are stored in the storage medium, including a plurality of instructions for making one or more computer devices (which can be personal computers, servers or network devices, etc.) execute all or part of the steps of the methods in the above embodiments.

[0093] In several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other manners. Of course, the described apparatus embodiments are merely schematic, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, units or modules, and can be in electrical, mechanical or other forms.

[0094] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the solutions provided in the embodiments.

[0095] In addition, each functional unit in the embodiments of the present application can be integrated in a processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware, or in the form of a software functional unit.

[0096] In the above-described embodiments of the present application, the description of each embodiment is focused on different aspects, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0097] The above are only the preferred embodiments of the present application, and it should be pointed out that, for those of ordinary skill in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A method for distributed photovoltaic installed capacity calculation, characterized in that, The distributed photovoltaic installed capacity calculation method comprises: obtaining orthographic image data of a satellite under a preset spatial scale; wherein the preset spatial scale contains geographical positions of each distributed photovoltaic component; performing photovoltaic component segmentation on the orthographic image data to obtain a plurality of segmented images containing each distributed photovoltaic component; performing edge detection on each segmented image to obtain a target area corresponding to each distributed photovoltaic component; wherein a boundary of the target area is used to represent a contour edge of a distributed photovoltaic component; performing photovoltaic component identification on the target area based on a preset target detection rule to obtain a photovoltaic component type corresponding to each target area; the photovoltaic component type is divided into single-crystal photovoltaic components, polycrystalline photovoltaic components, thin-film photovoltaic components and multi-element compound photovoltaic components; wherein the target detection rule includes a correspondence relationship between preset category features of each type of photovoltaic panel and a preset feature label, and the preset target detection rule can be determined by pre-calibration, including obtaining preset segmented images corresponding to preset single-crystal photovoltaic components, preset polycrystalline photovoltaic components, preset thin-film photovoltaic components and preset multi-element compound photovoltaic components; extracting a distinguishing feature of each preset segmented image with respect to other segmented images, and taking the distinguishing feature as the preset category feature, the distinguishing feature being embodied by different colors represented by photovoltaic components in the orthographic image data; performing distributed photovoltaic installed capacity calculation based on areas of the target area corresponding to each photovoltaic component type and capacities of each photovoltaic component type to obtain a capacity calculation result.

2. The method for distributed photovoltaic installed capacity calculation according to claim 1, characterized in that, The target detection based on the preset target detection rule on the target area to obtain a component type corresponding to each target area comprises: obtaining a correspondence relationship between each category feature and feature label in the preset target detection rule; performing target detection on the target area based on the category feature to obtain a component type corresponding to each target area.

3. The method for distributed photovoltaic installed capacity calculation according to claim 1, wherein, The edge detection on each segmented image to obtain a target area of each distributed photovoltaic component comprises: performing Gaussian filtering on each segmented image to obtain a filtered segmented image; performing gradient calculation on the filtered segmented image based on a Sobel operator to obtain a gradient calculation result; based on the gradient calculation result, sequentially performing non-maximum suppression and double-threshold hysteresis threshold processing on the filtered segmented image using a Canny algorithm to obtain the target area.

4. The method for distributed photovoltaic installed capacity calculation according to claim 1, wherein, Before performing distributed photovoltaic installed capacity calculation based on each target area and a corresponding photovoltaic component type, the method further comprises: performing state detection on each target area to obtain a state detection result; eliminating an abnormal area in an abnormal state from the target area.

5. The method for distributed photovoltaic installed capacity calculation according to claim 4, wherein, The state detection on each target area to obtain a state detection result comprises: performing semantic recognition on a boundary of each target area to obtain an actual semantic feature of a pixel constituting the boundary of each target area; comparing the actual semantic feature with a preset semantic feature to obtain a comparison result; wherein the preset semantic feature is used for photovoltaic component contour. Calculate the actual proportion of normal pixels representing the profile of the photovoltaic module relative to the pixels constituting the boundary of each target region based on the comparison result; Mark the target region with an actual proportion not greater than the preset proportion as an abnormal region.

6. The method for distributed photovoltaic installed capacity calculation according to claim 4, wherein, The state detection of each target region obtains a state detection result, and further includes: Obtain the preset geometric feature of the photovoltaic module type corresponding to each target region; Extract the actual geometric feature of each target region; wherein the actual geometric feature is used to represent the boundary shape constituting the boundary of the target region; Compare the actual geometric feature with the preset geometric feature to obtain a comparison result; Based on the comparison result, mark the target region with an actual geometric feature that does not meet the preset geometric feature as an abnormal region.

7. The distributed photovoltaic installed capacity calculation method of any one of claims 5 or 6, wherein, The state detection of each target region obtains a state detection result, and further includes: Based on the semantic feature of the pixels in each target region, divide the pixels to obtain abnormal pixels whose semantic feature does not represent a photovoltaic module; Calculate the actual abnormal proportion of the abnormal pixels in the target region; Mark the target region with an actual abnormal proportion greater than the preset abnormal proportion as an abnormal state.

8. A distributed photovoltaic installed capacity computing device, characterized by, The distributed photovoltaic installed capacity calculation device includes: A satellite data acquisition module is configured to acquire orthographic image data of a satellite at a preset spatial scale; wherein the preset spatial scale includes the geographical location of each distributed photovoltaic module; An image segmentation module is configured to perform photovoltaic module segmentation on the orthographic image data to obtain a plurality of segmentation images containing each distributed photovoltaic module; An edge detection module is configured to perform edge detection on each segmentation image to obtain a target region corresponding to each distributed photovoltaic module; wherein the boundary of the target region represents the profile edge of the distributed photovoltaic module; A photovoltaic module identification module is configured to identify the photovoltaic module in the target region based on a preset target detection rule to obtain the photovoltaic module type corresponding to each target region; the photovoltaic module type includes monocrystalline photovoltaic module, polycrystalline photovoltaic module, thin-film photovoltaic module, and multi-compound photovoltaic module; wherein the target detection rule includes the correspondence between the preset category feature and the preset feature label of each type of photovoltaic panel; the preset target detection rule can be determined by pre-calibration, including: obtaining the preset segmentation image corresponding to the preset monocrystalline photovoltaic module, the preset polycrystalline photovoltaic module, the preset thin-film photovoltaic module, and the preset multi-compound photovoltaic module; extracting the distinguishing feature of each preset segmentation image relative to other segmentation images, and taking the distinguishing feature as the preset category feature, which is embodied by different colors represented by the photovoltaic module in the orthographic image data A capacity calculation module is configured to calculate the distributed photovoltaic installed capacity based on the area of the target region corresponding to each photovoltaic module type and the capacity corresponding to each photovoltaic module type to obtain a capacity calculation result.

9. A computer device, comprising: It includes: A memory and a processor, which are connected in communication with each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method for calculating distributed photovoltaic installed capacity according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing a computer to perform the method for calculating distributed photovoltaic installed capacity according to any one of claims 1 to 7.

Images