A detection method and detection system for offshore wind power facility targets

Abstract

The present invention discloses a method and system for detecting offshore wind power facility targets. The method comprises the following steps: obtaining a satellite remote sensing image to be detected; pre-processing the satellite remote sensing image into blocks to obtain a plurality of block satellite remote sensing images; clustering the plurality of block satellite remote sensing images into regions of interest; cropping the obtained clustered regions of interest and inputting them into an offshore wind power facility detection network to detect independent wind power facility targets in the regions; and integrating the detected block satellite remote sensing images to obtain a final wind power facility target detection result. The present invention detects the target location of offshore wind power facilities based on satellite remote sensing technology, enabling long-term and continuous management and control of relevant marine engineering projects in the sea area.

Description

Technical Field

[0001] The present invention relates to the field of sea area related marine engineering management and control, and in particular to a detection method and a detection system for offshore wind power facility targets. Background Art

[0002] In recent years, remote sensing technology has become increasingly intertwined with economic development, the ecological environment, and marine resource regulation. It has been widely applied in agriculture, forestry, oceanography, geological and mineral exploration, meteorology, hydrology, environmental protection, and other fields, gradually forming a multi-level, multi-angle, and multi-domain observation system for detecting the Earth's environment and resources. Remote sensing technology, with its advantages of wide coverage, real-time performance, objectivity, and accuracy, can be used to rapidly acquire high-precision marine monitoring information in key sea areas, conduct real-time tracking and dynamic marine monitoring, promptly formulate and implement treatment measures, minimize losses, monitor the use of sea areas and islands, and protect the marine environment. Furthermore, the complex and ever-changing marine environment requires maritime surveillance departments to meet highly specialized and targeted application requirements.

[0003] Given the current demand for long-term, continuous control of relevant marine projects, an effective method for detecting offshore wind power facilities is urgently needed. By clustering regions of interest in satellite remote sensing images to be detected, more accurate target locations can be obtained, thereby strengthening the continuous control of long-term series of marine projects related to the sea area, conducting monitoring of key areas in the sea area, and promptly grasping illegal and irregular activities within the jurisdiction of the city, regulating the order of sea area use, and comprehensively improving the technical support for the legal use of marine resources. Summary of the Invention

[0004] (1) Purpose of the invention

[0005] The purpose of the present invention is to propose a detection technology solution for offshore wind power facility targets based on satellite remote sensing technology in response to the changing marine environmental conditions and the current need for monitoring of sea-related projects.

[0006] (2) Technical solution

[0007] To solve the above problems, the first aspect of the present invention provides a method for detecting offshore wind power facility targets, comprising: obtaining a satellite remote sensing image to be detected; performing block preprocessing on the satellite remote sensing image to obtain a plurality of block satellite remote sensing images; clustering the plurality of block satellite remote sensing images into regions of interest in turn; cropping the obtained clustered regions of interest in turn and inputting them into an offshore wind power facility detection network to detect independent wind power facility targets in the region; and integrating the detected block satellite remote sensing images to obtain a final detection result of the wind power facility target.

[0008] Preferably, in the detection method, the region of interest clustering region cropping includes: if the candidate frames of the two segmented satellite remote sensing images satisfy the following formula:

[0009] IoU(box1,box2)>0

[0010] The two candidate boxes are merged and cropped to obtain a region of interest; wherein box1 and box2 represent candidate boxes of the two segmented satellite remote sensing images respectively.

[0011] Preferably, the detection method and the offshore wind power facility detection network include: a feature encoder, a feature fusion module and a detection head.

[0012] Preferably, in the detection method, the feature encoder includes a convolution layer, a feature fusion layer and a fast spatial pyramid pooling layer, the convolution layer performs a convolution operation on each of the regions of interest; the feature fusion layer splits the region of interest into two parts, the first part is input into two bottleneck layers, the second part is spliced ​​with the output of the two bottleneck layers, and the information of the two parts is fused using a convolution layer with predetermined parameters; the fast spatial pyramid pooling layer performs a pooling operation on the regions of interest of different sizes and proportions of the input.

[0013] Preferably, in the detection method, the feature fusion module adopts a bidirectional design mode to perform fusion and splicing from the highest-level feature map to the lower-level feature map, and then performs the same fusion operation from the lowest level to the higher level.

[0014] Preferably, in the detection method, the detection head uses Wasserstein distance to evaluate the position accuracy of the central target of the wind power facility to be detected, wherein the Wasserstein distance is expressed by the following formula:

[0015]

[0016] By normalizing the formula in exponential form, we can obtain:

[0017]

[0018] Where C represents a constant coefficient, represents the Wasserstein distance, NWD(G1, G2) represents the normalized Wasserstein distance, G1 and G2 represent two different Gaussian distributions, respectively. represents the central abscissa of the inscribed ellipse of the Gaussian distribution G1 bounding box, represents the central ordinate of the inscribed ellipse of the Gaussian distribution G1 bounding box, w1 represents the width of the Gaussian distribution G1 bounding box, h1 represents the height of the Gaussian distribution G1 bounding box, The central abscissa of the inscribed ellipse of the Gaussian distribution G2 bounding box, represents the central ordinate of the inscribed ellipse of the Gaussian distribution G2 bounding box, w2 represents the width of the Gaussian distribution G2 bounding box, and h2 represents the height of the Gaussian distribution G2 bounding box.

[0019] Preferably, the detection method fits the position of the central target with the height and width of eight sampling points around the central target, and takes the average of multiple central target positions as the final independent wind power target.

[0020] Preferably, the detection method and the offshore wind power facility detection network further include a loss function calculation module, and the loss function adopts the following expression:

[0021] loss total =CrossLoss(p,q)+DFL(S i ,S i+1 )+L NWD (pred box ,gt box )+L NWD (pred center ,gt center )

[0022] Among them, loss total Represents the total loss function, CrossLoss(p,q) represents the improved cross entropy loss function, DFL(S i ,S i+1 ) represents the distribution focus loss function, L NWD (pred box ,gt box ) represents the loss function of the target box regression based on the Wasserstein distance, L NWD (pred center ,gt center ) represents the loss function for the target box center position regression based on the Wasserstein distance.

[0023] Preferably, the detection method integrates the detected block satellite remote sensing images, including: if there is a wind power facility target in the overlapping area of ​​two adjacent block satellite remote sensing images, a non-maximum suppression method is used to retain the detection result of one block satellite remote sensing image and delete the detection result of the other block satellite remote sensing image.

[0024] According to another aspect of the present invention, the present invention also proposes a detection system for offshore wind power facility targets, the detection system comprising: a remote sensing image acquisition module, which is used to acquire satellite remote sensing images to be detected; a remote sensing image blocking module, which is used to perform block preprocessing on the satellite remote sensing images to obtain a number of blocked satellite remote sensing images; a region of interest clustering module, which is used to cluster the several blocked satellite remote sensing images into regions of interest in turn; a wind power target detection module, which is used to crop the obtained region of interest cluster areas in turn and input them into an offshore wind power facility detection network to detect independent wind power facility targets in the area; a remote sensing image integration module, which is used to integrate the detected blocked satellite remote sensing images to obtain the final wind power facility target detection results.

[0025] (3) Beneficial effects

[0026] The above technical solution of the present invention has the following beneficial technical effects:

[0027] This invention proposes a method and system for detecting offshore wind power facility targets. This method addresses the current need for managing and controlling marine engineering projects in offshore areas. Using remote sensing satellite technology, the method clusters regions of interest (ROIs) within satellite remote sensing images to pinpoint the precise locations of offshore wind power targets. By strengthening long-term monitoring of relevant marine projects, it helps to promptly identify any violations at sea and regulate the use of the sea area. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 1 is a schematic diagram of the steps of a method for detecting an offshore wind power facility target according to an embodiment of the present invention;

[0029] Figure 2 1 is a schematic diagram of a workflow of a method for detecting an offshore wind power facility target according to an embodiment of the present invention;

[0030] Figure 3 It is a structural schematic diagram of a detection system for an offshore wind power facility target according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] To make the objectives, technical solutions, and advantages of the present invention more clearly understood, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present invention.

[0032] The accompanying drawings illustrate schematic diagrams of layer structures according to embodiments of the present invention. These figures are not drawn to scale; for clarity, some details are exaggerated and some details may be omitted. The shapes, relative sizes, and positional relationships of the various regions and layers shown in the figures are merely exemplary and may deviate in practice due to manufacturing tolerances or technical limitations. Those skilled in the art may design regions / layers with different shapes, sizes, and relative positions based on actual needs.

[0033] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0034] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0035] In recent years, remote sensing technology has become increasingly intertwined with economic development, the ecological environment, and marine resource regulation. It has been widely applied in agriculture, forestry, oceanography, geological and mineral exploration, meteorology, hydrology, environmental protection, and other fields, gradually forming a multi-level, multi-angle, and multi-domain observation system for detecting the Earth's environment and resources. Remote sensing technology, with its advantages of wide coverage, real-time performance, objectivity, and accuracy, can be used to rapidly acquire high-precision marine monitoring information in key sea areas, conduct real-time tracking and dynamic marine monitoring, promptly formulate and implement treatment measures, minimize losses, monitor the use of sea areas and islands, and protect the marine environment. Furthermore, the complex and ever-changing marine environment requires maritime surveillance departments to meet highly specialized and targeted application requirements.

[0036] In response to the current requirement for long-term continuous monitoring of marine engineering projects in the sea area, the present invention proposes a detection method for offshore wind power facility targets based on remote sensing technology to achieve continuous control of related marine engineering projects.

[0037] Figure 1 Schematic diagram of the steps of the detection method of offshore wind power facility target according to the embodiment of the present invention. Figure 1 A schematic diagram illustrating steps of a method for detecting an offshore wind power facility target.

[0038] Step S110: Acquire a satellite remote sensing image to be detected;

[0039] Step S120: performing block preprocessing on the satellite remote sensing image to obtain a plurality of block satellite remote sensing images;

[0040] Step S130: clustering the regions of interest on the plurality of satellite remote sensing images in sequence;

[0041] Step S140: Cut the obtained region of interest cluster regions in sequence and input them into the offshore wind power facility detection network to detect independent wind power facility targets in the region;

[0042] Step S150: Integrate the detected block satellite remote sensing images to obtain the final detection result of the wind power facility target.

[0043] According to some optional embodiments, in step S110, satellite remote sensing images to be detected are obtained. First, a sample library is constructed using offshore wind power target remote sensing images, and then the offshore wind power target remote sensing images in the sample library are classified and labeled to obtain different types of satellite remote sensing images.

[0044] In one embodiment, the roLabelImg image annotation tool is used to annotate images in the sample library. Once the annotated images are completed, a .txt file is generated. This file contains various information related to the image classification, including the target category, the location of the target's center point in the image, and the width, height, and angle of the annotated target. By annotating the images in the sample library with the annotation tool, the location of offshore wind turbine targets can be intelligently retrieved.

[0045] In one embodiment, a data augmentation strategy is applied to the image to improve the accuracy of detecting target types. The use of data augmentation strategy can increase the diversity of training samples and improve the robustness of detection. The sample diversity is increased by expanding the training samples by horizontal flipping, vertical flipping, random rotation, random scaling, random cropping or expansion. In addition, the image also uses color jitter, including contrast adjustment, brightness adjustment, saturation adjustment and hue adjustment. The above strategy expands the richness of the detection target types, provides material for the deep learning offshore wind power target detection model to detect and identify the target, and can also provide evaluation data for the supervised learning algorithm.

[0046] After completing step S110 to obtain the satellite remote sensing image to be detected, the process proceeds to step S120 to perform block preprocessing on the satellite remote sensing image to obtain a plurality of block satellite remote sensing images.

[0047] In one embodiment, during the pre-processing of satellite remote sensing images, the TIFF format image file is first converted to the jpg format. The original image is then cropped using a 4096×4096 sliding window, so that each cropped image overlaps by 256 pixels. This window cropping method causes the top, bottom, left, and right boundaries of the current window to overlap with the images of adjacent windows, resulting in a number of segmented satellite remote sensing images.

[0048] Then, step S130 is performed to cluster the regions of interest in sequence for the plurality of satellite remote sensing images. The clustering of the regions of interest focuses on detecting the center point position of the region of interest and the width and height corresponding to the center point.

[0049] In one embodiment, during the ROI clustering process, an object detector capable of detecting the approximate location of an object is first trained. This object detector then performs a meanshift clustering operation on candidate boxes from the aforementioned multiple satellite remote sensing image blocks. If no candidate box is generated for any satellite remote sensing image, the detection process for that window is skipped. If a candidate box is generated, the two candidate boxes are merged and cropped to obtain the ROI.

[0050] The clipping of the cluster area of ​​interest includes:

[0051] If the candidate frames of two segmented satellite remote sensing images satisfy the following formula:

[0052] IoU(box1,box2)>0

[0053] The two candidate boxes are merged and cropped to obtain the region of interest. Box1 and box2 represent the candidate boxes of two segmented satellite remote sensing images respectively.

[0054] In one embodiment, ResNet50 is selected to extract feature maps at three scales, where the sizes of the output feature pyramids corresponding to the three feature maps are 128, 256, and 512, respectively. A top-down feature fusion method is then used to perform a bilinear interpolation operation on the features of the previous layer and a bitwise addition operation with the features of the next layer. Finally, the results of the top-down fusion of the pyramid are sequentially input into the prediction network to regress the cluster candidate box information at different scales. The candidate boxes with scores higher than the 0.5 threshold are then used as the input of the mean shift clustering algorithm to obtain the clustered areas of the region of interest.

[0055] Next, step S140 is performed to sequentially crop the resulting region of interest clusters and input them into the offshore wind turbine detection network to detect individual wind turbine targets within the region. In one embodiment, the offshore wind turbine detection network includes a feature encoder, a feature fusion module, and a detection head. This offshore wind turbine detection network addresses the challenges of detecting wind turbine targets, such as their small size, strong interference, and sensitivity to evaluation metrics. This network utilizes a modified YOLOv8 model structure to overcome these challenges.

[0056] Specifically, the feature encoder consists of a convolutional layer, a feature fusion layer, and a fast spatial pyramid pooling layer. The convolutional layer performs convolution operations on each region of interest. The feature fusion layer splits the region of interest into two parts. The first part is input to two bottleneck layers, and the second part is concatenated with the output of the two bottleneck layers. The convolutional layer uses predetermined parameters to fuse the information of the two parts. The fast spatial pyramid pooling layer performs pooling operations on regions of interest of different sizes and proportions.

[0057] In one embodiment, each convolution layer is composed of a 2D convolution, a layer normalization function, and a SiLU activation function. The calculation formula of SiLU is:

[0058] SiLU=x×sigmoid(x),

[0059] Because the region of interest (ROI) encompasses both offshore wind turbine targets and potential interfering targets within the offshore wind turbine scenario, convolution operations can be used to extract high-dimensional features from the ROI image, enhancing the distinction between wind turbine targets and interfering targets. Furthermore, inputting the ROI into the convolutional layer reduces computational complexity, further lowering the image resolution within the region of interest and extracting image features, facilitating subsequent feature decoding by the detection head. Furthermore, the convolutional layer improves the image's feature fitting capabilities. By learning the characteristic distribution of interfering factors in remote sensing images that share similar characteristics to wind turbine targets, the convolution operation strengthens the distinction between wind turbine targets and interfering factors, thereby enhancing the detection and anti-interference capabilities of the offshore wind turbine facility detection network.

[0060] In one embodiment, when passing through the feature fusion layer, the feature map is first input into the convolution layer to obtain the image features. The input feature map is then split into two equal parts using a channel splitting method. The first part is input into two bottleneck layers for channel dimensionality reduction and feature fusion. The second part is spliced ​​with the output of the two bottleneck layers to form a new feature map. The information of the two parts is then fused using a predetermined parameter convolution layer. The predetermined parameter convolution layer is a convolution layer with a convolution kernel and a stride of 1. This convolution layer does not share parameters with the convolution layer in the encoding stage, thereby improving the modeling capabilities of different features in the regional fusion stage and the encoding stage.

[0061] In one embodiment, a fast spatial pyramid pooling layer has a faster computation speed and fewer parameters. Its structure is to concatenate three serial MaxPool inputs, where the kernels of the three MaxPools are all 5×5.

[0062] The offshore wind power facility detection network also includes a feature fusion module, which adopts a bidirectional design mode to fuse and splice from the highest-level feature map to the lower-level feature map, and then performs the same fusion operation from the lowest level to the higher level.

[0063] In one embodiment, during the feature fusion phase, the feature fusion module employs a bidirectional design approach, encompassing both top-down and bottom-up approaches. The highest-level features are first upsampled to bring their feature maps to the same size as those of lower-level feature maps. These features are then channel-concatenated with the lower-level feature maps, and a feature fusion layer is used to learn feature relationships at different scales. This process continues until the bottom layer of the pyramid used by the detection head. The network then performs the same fusion operation starting from the bottom layer of the pyramid, and the results from each layer are sequentially fed into the detection head for wind turbine target detection and regression.

[0064] The offshore wind power facility detection network also includes a detection head, which uses the Wasserstein distance to evaluate the position accuracy of the center target of the wind power facility to be detected. The Wasserstein distance is expressed as follows:

[0065]

[0066] Normalizing the formula in exponential form, we get:

[0067]

[0068] Where C represents a constant coefficient, Represents Wasserstein distance, NWD(G1, G2) represents the normalized Wasserstein distance, G1 and G2 represent two different Gaussian distributions, represents the central abscissa of the inscribed ellipse of the Gaussian distribution G1 bounding box, represents the central ordinate of the inscribed ellipse of the Gaussian distribution G1 bounding box, w1 represents the width of the Gaussian distribution G1 bounding box, h1 represents the height of the Gaussian distribution G1 bounding box, The central abscissa of the inscribed ellipse of the Gaussian distribution G2 bounding box, represents the central ordinate of the inscribed ellipse of the Gaussian distribution G2 bounding box, w2 represents the width of the Gaussian distribution G2 bounding box, and h2 represents the height of the Gaussian distribution G2 bounding box.

[0069] In one embodiment, the position of the central target is fitted with the height and width of eight sampling points around the central target, and the sampling points at 8 positions around the central point are used as positive sample points, and the rest are negative sample points, thereby enhancing the model's position regression capability. The average of multiple central target positions is used as the final independent wind power target. In the offshore wind power facility detection network, the target frame of the offshore wind power is usually characterized by the center point of the predicted target, the width and height of the target. However, this prediction method makes it difficult to accurately characterize the shape of the wind power target, which will result in ineffective learning of features. Here, the prediction of the offshore wind power target sampling points is changed from a single center point prediction problem to a multi-position fitting problem, which enriches the feature information of the wind power target, thereby improving the position regression capability and anti-interference capability of the offshore wind power facility detection network.

[0070] In one embodiment, the Wasserstein distance is introduced as a new metric for evaluating the position of central objects in multiple segmented satellite remote sensing images, replacing the IoU (Intersection of Union) as a measure of very small object detection performance. This improves the robustness of small object detection. Furthermore, this embodiment incorporates a number of data augmentation methods, including rotation, translation, random distortion, and HSV random fluctuations, to enhance the detector's robustness to varying atmospheric and lighting conditions.

[0071] In the embodiment of the present invention, the bounding boxes of the two segmented satellite remote sensing images are first modeled as a two-dimensional Gaussian distribution, with the center pixel having the largest weight and the weight decreasing toward the edge. If the current horizontal bounding box is:

[0072] R=(x,y,w,h)

[0073] Where x, y, w, and h represent the center point, width, and height of the bounding box, respectively. The inscribed ellipse of the bounding box can be expressed as:

[0074]

[0075] Among them, c x , c y , r x and r y Represent the center coordinates of the ellipse and the lengths along the x-axis and y-axis respectively. The mean μ and covariance X of the Gaussian distribution of any two block satellite remote sensing images obey:

[0076]

[0077] For two Gaussian distributions G1 = N(μ1, X1) and G2 = N(μ2, X2), their Wasserstein distance can be defined as:

[0078]

[0079] Furthermore, if we normalize it in exponential form, we can get:

[0080]

[0081] Among them, C is a constant coefficient, and its value is 4 in this system. represents the Wasserstein distance, NWD(G1, G2) represents the normalized Wasserstein distance, G1 and G2 represent two different Gaussian distributions, respectively. represents the central abscissa of the inscribed ellipse of the Gaussian distribution G1 bounding box, represents the central ordinate of the inscribed ellipse of the Gaussian distribution G1 bounding box, w1 represents the width of the Gaussian distribution G1 bounding box, h1 represents the height of the Gaussian distribution G1 bounding box, The central abscissa of the inscribed ellipse of the Gaussian distribution G2 bounding box, represents the central ordinate of the inscribed ellipse of the Gaussian distribution G2 bounding box, w2 represents the width of the Gaussian distribution G2 bounding box, and h2 represents the height of the Gaussian distribution G2 bounding box.

[0082] The offshore wind power facility detection network also includes a loss function calculation module. The loss function based on Wasserstein distance is:

[0083] loss total =CrossLoss(p,q)+DFL(S i ,S i+1 )+L NWD (pred box ,gt box )+L NWD (pred center ,gt center )

[0084] Among them, loss total Represents the total loss function, CrossLoss(p,q) represents the improved cross entropy loss function, DFL(S i ,S i+1 ) represents the distribution focus loss function, L NWD (pred box ,gt box ) represents the loss function of the target box regression based on the Wasserstein distance, L NWD (pred center ,gt center ) represents the loss function for the target box center position regression based on the Wasserstein distance.

[0085] In one embodiment, the loss function includes classification loss, target box regression loss, and target box center position regression loss. The classification loss uses the improved cross entropy function, the bounding box regression uses a combination of distributed focus loss (DFL) and Wasserstein distance loss, and the center position loss uses the Wasserstein distance loss function.

[0086] The calculation formula of the improved cross entropy loss function is as follows:

[0087]

[0088] q is the IoU (intersection over union) between the bbox (predicted box) and the ground truth box (gt). IoU is the intersection of the predicted and ground truth boxes divided by the union of the two boxes. p is the probability. α and γ are hyperparameters, set to 2.0 and 0.1 in this embodiment.

[0089] The calculation formula for DFL is:

[0090] DFL(S i ,S i+1 )=-((y i+1 -y)log(S i )+(yy i )log(S i+1 ))

[0091] Among them, y represents the true predicted value, y i and y i+1 Represents two predicted values ​​near the true value, S i and S i+1 is the probability corresponding to the predicted value.

[0092] The total loss function formula is:

[0093] loss total =CrossLoss(p,q)+DFL(S i ,S i+1 )+L NWD (pred box ,gt box )+L NWD (pred center ,gt center )

[0094] Finally, step S150 is performed to integrate the detected segmented satellite remote sensing images to obtain a final wind power facility target detection result. The integration of the detected segmented satellite remote sensing images includes: if a wind power facility target exists in the overlapping area of ​​two adjacent segmented satellite remote sensing images, a non-maximum suppression method is used to retain the detection result of one segmented satellite remote sensing image and delete the detection result of the other segmented satellite remote sensing image.

[0095] Figure 2 This is a schematic diagram of the workflow of the method for detecting offshore wind power facility targets according to an embodiment of the present invention. Figure 2 The workflow of the detection method for offshore wind power facility targets is described.

[0096] First, the satellite remote sensing images to be detected are obtained, and a sample library is constructed using the offshore wind power target remote sensing images. The images in the sample library are classified and labeled to obtain different types of satellite remote sensing images.

[0097] Then, the acquired satellite remote sensing images are pre-processed into blocks using the window cropping method to obtain several block satellite remote sensing images, which are then clustered into regions of interest. The cropped regions of interest include: if the candidate frames of the two block satellite remote sensing images satisfy the following formula:

[0098] IoU(box1,box2)>0

[0099] The two candidate boxes are merged and cropped to obtain a region of interest, wherein box1 and box2 represent candidate boxes of the two segmented satellite remote sensing images respectively.

[0100] The obtained regions of interest are then cut and input into the offshore wind power facility detection network to detect the independent wind power facility targets in the region. The offshore wind power facility detection network includes: feature encoder, feature fusion module and detection head.

[0101] Specifically, the feature encoder includes a convolutional layer, a feature fusion layer, and a fast spatial pyramid pooling layer. The convolutional layer performs a convolution operation on each of the regions of interest. The feature fusion layer splits the region of interest into two parts. The first part is input into two bottleneck layers, and the second part is concatenated with the output of the two bottleneck layers. The convolutional layer uses predetermined parameters to fuse the information from the two parts. The fast spatial pyramid pooling layer performs a pooling operation on the input regions of interest of different sizes and proportions.

[0102] The feature fusion module adopts a bidirectional design mode to fuse and splice from the highest-level feature map to the lower-level feature map, and then performs the same fusion operation from the lowest level to the higher level.

[0103] The detection head uses the Wasserstein distance to evaluate the position accuracy of the center target of the wind power facility to be detected. The Wasserstein distance is expressed as follows:

[0104]

[0105] Normalizing the formula in exponential form, we get:

[0106]

[0107] Where C represents a constant coefficient, Represents Wasserstein distance, NWD(G1, G2) represents the normalized Wasserstein distance, G1 and G2 represent two different Gaussian distributions, represents the central abscissa of the inscribed ellipse of the Gaussian distribution G1 bounding box, represents the central ordinate of the inscribed ellipse of the Gaussian distribution G1 bounding box, w1 represents the width of the Gaussian distribution G1 bounding box, h1 represents the height of the Gaussian distribution G1 bounding box, The central abscissa of the inscribed ellipse of the Gaussian distribution G2 bounding box, The vertical coordinate of the center of the inscribed ellipse of the Gaussian distribution G2 bounding box is represented by w2, the width of the Gaussian distribution G2 bounding box is represented by h2, and the height of the Gaussian distribution G2 bounding box is represented by h2. The height and width of the eight sampling points around the central target are fitted to the position of the central target, and the average of the multiple central target positions is used as the final independent wind power target.

[0108] In addition, the offshore wind power facility detection network also includes a loss function calculation module, and the loss function uses the following expression:

[0109] loss total =CrossLoss(p,q)+DFL(S i ,S i+1 )+L NWD (pred box ,gt box )+L NWD (pred center ,gt center )

[0110] Among them, loss total Represents the total loss function, CrossLoss(p,q) represents the improved cross entropy loss function, DFL(S i ,S i+1 ) represents the distribution focus loss function, L NWD (pred box ,gt box) represents the loss function of target box regression based on Wasserstein distance, L NWD (pred center ,gt center ) represents the loss function for target box center position regression based on Wasserstein distance.

[0111] Finally, the detected block satellite remote sensing images are integrated to obtain the final wind power facility target detection results. If wind power facility targets exist in the overlapping area of ​​two adjacent block satellite remote sensing images, the non-maximum suppression method is used to retain the detection results of one block satellite remote sensing image and delete the detection results of the other block satellite remote sensing image.

[0112] Based on the above-mentioned detection method for offshore wind power facility targets, an embodiment of the present invention further provides a detection system for offshore wind power facility targets. The system uses the above-mentioned detection method to detect offshore wind power facility targets.

[0113] Figure 3 This is a schematic diagram of the structure of the detection system for offshore wind power facilities according to the embodiment of the present invention. Figure 3 To illustrate the various components and functions of the detection system for offshore wind power facility targets.

[0114] like Figure 3 As shown, the offshore wind power facility target detection system provided by the embodiment of the present invention includes a remote sensing image acquisition module 10, a remote sensing image segmentation module 20, a region of interest clustering module 30, a wind power target detection module 40, and a remote sensing image integration module 50. Specifically, the remote sensing image acquisition module 10 is used to acquire the satellite remote sensing image to be detected. The remote sensing image segmentation module 20 is used to perform block preprocessing on the satellite remote sensing image to obtain a plurality of block satellite remote sensing images. The region of interest clustering module 30 is used to cluster the plurality of block satellite remote sensing images into regions of interest in turn. The wind power target detection module 40 is used to crop the obtained region of interest cluster regions in turn and input them into the offshore wind power facility detection network to detect independent wind power facility targets in the region. The remote sensing image integration module 50 is used to integrate the detected block satellite remote sensing images to obtain the final wind power facility target detection result.

[0115] The process of each module realizing its function in the offshore wind power facility target detection system provided by the embodiment of the present invention is the same as the steps in the offshore wind power facility target detection method provided by the above embodiment of the present invention, and its repeated description will be omitted here.

[0116] The present invention relates to a method and system for detecting offshore wind power facility targets. Based on satellite remote sensing technology, the system conducts focused monitoring of suspicious areas in the sea. By clustering regions of interest from multiple segmented satellite remote sensing images and detecting offshore wind power facility detection networks, the system locks in the final detection results of offshore wind power facility targets. This allows for timely detection of illegal and irregular activities within the jurisdictional sea area, enabling long-term and continuous control of relevant projects in the sea area and regulating the order of sea area use.

[0117] It should be understood that the above-described specific embodiments of the present invention are merely illustrative or illustrative of the principles of the present invention and do not constitute limitations of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included within the scope of protection of the present invention. In addition, the appended claims are intended to cover all variations and modifications that fall within the scope and metes and bounds of the appended claims, or equivalents thereof.

[0118] The present invention has been described above with reference to the embodiments thereof. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. The scope of the present invention is defined by the appended claims and their equivalents. Those skilled in the art may make various substitutions and modifications without departing from the scope of the present invention, and such substitutions and modifications are intended to fall within the scope of the present invention.

[0119] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0120] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

Claims

1. A method for detecting an offshore wind power facility target, characterized in that: include: Acquire satellite remote sensing images to be detected; Performing block preprocessing on the satellite remote sensing image to obtain a plurality of block satellite remote sensing images; Clustering the regions of interest of a plurality of block satellite remote sensing images in sequence; the region of interest clustering is used to detect the center point position of the region of interest and the width and height corresponding to the center point; The obtained clustered regions of interest are clipped in turn and input into the offshore wind power facility detection network to detect independent wind power facility targets in the region; Integrate the detected block satellite remote sensing images to obtain the final detection results of the wind power facility target; The offshore wind power facility detection network is based on an improved YOLOv8 model structure and includes: a feature encoder, a feature fusion module and a detection head; The detection head uses Wasserstein distance to evaluate the position accuracy of the central target of the wind power facility to be detected, wherein the Wasserstein distance is expressed as the following formula: By normalizing the formula in exponential form, we can obtain: Where C represents a constant coefficient, represents the Wasserstein distance, NWD(G1, G2) represents the normalized Wasserstein distance, G1 and G2 represent two different Gaussian distributions, respectively. represents the central abscissa of the inscribed ellipse of the Gaussian distribution G1 bounding box, represents the central ordinate of the inscribed ellipse of the Gaussian distribution G1 bounding box, w1 represents the width of the Gaussian distribution G1 bounding box, h1 represents the height of the Gaussian distribution G1 bounding box, The central abscissa of the inscribed ellipse of the Gaussian distribution G2 bounding box, represents the central ordinate of the inscribed ellipse of the Gaussian distribution G2 bounding box, w2 represents the width of the Gaussian distribution G2 bounding box, and h2 represents the height of the Gaussian distribution G2 bounding box; Fitting the position of the central target with the heights and widths of eight sampling points around the central target, and taking the average of the multiple central target positions as the final independent wind power facility target; The offshore wind power facility detection network also includes a loss function calculation module, and the loss function includes classification loss, target frame regression loss and target frame center position regression loss.

2. The detection method according to claim 1, wherein The region of interest clustering region clipping includes: If the candidate frames of the two segmented satellite remote sensing images satisfy the following formula: IoU(box1,box2)>0 Then the two candidate frames are merged and cropped to obtain the region of interest; Among them, box1 and box2 respectively represent the candidate boxes of the two block satellite remote sensing images.

3. The detection method according to claim 1, wherein The feature encoder includes a convolutional layer, a feature fusion layer and a fast spatial pyramid pooling layer. The convolution layer performs a convolution operation on each of the regions of interest; The feature fusion layer splits the region of interest into two parts, the first part is input into two bottleneck layers, the second part is concatenated with the outputs of the two bottleneck layers, and the information of the two parts is fused using a convolutional layer with predetermined parameters; The fast spatial pyramid pooling layer performs a pooling operation on the input regions of interest of different sizes and scales.

4. The detection method according to claim 1, wherein The feature fusion module adopts a bidirectional design mode to fuse and splice from the highest-level feature map to the lower-level feature map, and then performs the same fusion operation from the lowest level to the higher level.

5. The detection method according to claim 1, wherein The offshore wind power facility detection network further includes a loss function calculation module, and the loss function adopts the following expression: loss total =CrossLoss(p,q)+DFL(S i ,S i+1 )+L NWD (pred box ,gt box )+L NWD (pred center ,gt center ) Among them, loss total Represents the total loss function, CrossLoss(p,q) represents the improved cross entropy loss function, DFL(S i ,S i+1 ) represents the distribution focus loss function, L NWD (pred box ,gt box ) represents the loss function of the target box regression based on the Wasserstein distance, L NWD (pred center ,gt center ) represents the loss function for the target box center position regression based on the Wasserstein distance.

6. The detection method according to claim 1, characterized in that Integrate the detected block satellite remote sensing images, including: If there is a wind power facility target in the overlapping area of ​​two adjacent block satellite remote sensing images, the non-maximum suppression method is used to retain the detection result of one block satellite remote sensing image and delete the detection result of the other block satellite remote sensing image.

7. A detection system for offshore wind power facility targets, characterized in that: The detection system comprises: A remote sensing image acquisition module, which is used to acquire satellite remote sensing images to be detected; A remote sensing image segmentation module is used to perform segmentation preprocessing on the satellite remote sensing image to obtain a plurality of segmented satellite remote sensing images; A region of interest clustering module is used to sequentially cluster a number of segmented satellite remote sensing images into regions of interest; the region of interest clustering is used to detect the center point position of the region of interest and the width and height corresponding to the center point; A wind power target detection module is used to sequentially crop the obtained region of interest clustering regions and input them into the offshore wind power facility detection network to detect independent wind power facility targets in the region; A remote sensing image integration module is used to integrate the detected block satellite remote sensing images to obtain the final detection results of the wind power facility target; The offshore wind power facility detection network includes: a feature encoder, a feature fusion module and a detection head; The detection head uses Wasserstein distance to evaluate the position accuracy of the central target of the wind power facility to be detected, wherein the Wasserstein distance is expressed as the following formula: By normalizing the formula in exponential form, we can obtain: Where C represents a constant coefficient, represents the Wasserstein distance, NWD(G1, G2) represents the normalized Wasserstein distance, G1 and G2 represent two different Gaussian distributions, respectively. represents the central abscissa of the inscribed ellipse of the Gaussian distribution G1 bounding box, represents the central ordinate of the inscribed ellipse of the Gaussian distribution G1 bounding box, w1 represents the width of the Gaussian distribution G1 bounding box, h1 represents the height of the Gaussian distribution G1 bounding box, The central abscissa of the inscribed ellipse of the Gaussian distribution G2 bounding box, represents the central ordinate of the inscribed ellipse of the Gaussian distribution G2 bounding box, w2 represents the width of the Gaussian distribution G2 bounding box, and h2 represents the height of the Gaussian distribution G2 bounding box; Fitting the position of the central target with the heights and widths of eight sampling points around the central target, and taking the average of the multiple central target positions as the final independent wind power facility target; The offshore wind power facility detection network also includes a loss function calculation module, and the loss function includes classification loss, target frame regression loss and target frame center position regression loss.

Images