Cable icing detection method, device and equipment based on laser radar and medium

Abstract

The invention discloses a cable icing detection method, device and equipment based on a laser radar and a medium. For two frames of point clouds to be registered, key points are extracted from each frame of point clouds to obtain key point clouds, the two frames of key point clouds are input into the registration network for processing, the registration network adaptively learns an overlapping region of the two frames of point clouds based on a space attention mechanism, predicts a relative pose of the two frames of point clouds, and registers the two frames of point clouds based on the relative pose. The method comprises the steps of obtaining a fusion point cloud, extracting an iced cable point cloud representing an iced cable from the fusion point cloud, determining the three-dimensional size of the iced cable based on the iced cable point cloud, and calculating the icing thickness based on the three-dimensional size of the iced cable. The attention weight mechanism enables the network to adaptively learn an overlapping region of continuous point cloud frames, thereby realizing rapid and effective end-to-end registration of a large-scale point cloud scene, providing a good basis for a fine registration algorithm, improving registration efficiency and accuracy, and further improving icing detection accuracy.

Description

Technical Field

[0001] The present invention relates to cable monitoring technology, and in particular to a method, device, equipment and medium for detecting cable icing based on laser radar. Background Art

[0002] Distribution network icing monitoring is crucial in ensuring the stability and safety of the power system. Snowy weather may increase the load on wires and equipment, causing power outages and equipment damage. By monitoring icing in real time, preventive measures can be taken in time to reduce the occurrence of faults and ensure the normal power supply of residents and economic activities. Therefore, the establishment of an efficient icing monitoring system can provide reliable data support under extreme weather conditions to ensure the safe operation of the distribution network.

[0003] Traditional ice monitoring methods often require the disassembly or direct contact of equipment, which increases safety hazards and operational complexity. Non-invasive monitoring, on the other hand, can obtain the ice status of wires and equipment in real time through advanced sensors and data analysis technology, avoiding interference and damage to the equipment. This method is particularly important in snowy weather, and can identify potential risks in a timely manner, ensure the continuity and reliability of power supply, thereby effectively protecting residents' lives and economic activities, and improving the intelligent management level of distribution networks. As a new method of non-invasive ice monitoring, LiDAR scanning uses laser beam emission and reception to quickly obtain three-dimensional data on the surface of distribution network equipment, accurately measure the thickness and distribution of ice, and has the characteristics of high precision and high efficiency. Compared with traditional methods, LiDAR does not need to contact equipment or lines, reducing human intervention and safety risks. At the same time, LiDAR can monitor under various climatic conditions, provide real-time data, and help operation and maintenance personnel quickly assess risks and take corresponding measures. The application of this technology provides an efficient and safe monitoring method for the power industry, which will significantly improve the monitoring capability of distribution networks under extreme weather conditions and enhance the safety and reliability of power systems.

[0004] In the process of acquiring point cloud data by laser radar scanning, due to the limited field of view of the sensor, it is necessary to rely on the registration algorithm to stitch the local point clouds together to generate a complete 3D scene point cloud of the large-scale distribution network line. The shape of the ice on the distribution network is complex, and the laser radar point cloud is an effective measurement tool for evaluating the thickness and shape of the ice. However, for the laser radar point cloud in large-scale space, accurate registration is the key. Point cloud registration mainly involves estimating the Euclidean transformation matrix between the two frames of scanned point clouds. After obtaining the transformation matrix, the point cloud data captured by different sensors can be converted to a unified world coordinate system for combination. With the rapid development of deep learning technology, learning-based methods have gradually replaced traditional manual features and can perform point cloud registration tasks faster and more accurately. However, existing point cloud registration methods are mostly used for stitching small-scale 3D scenes, such as indoor or object-level point clouds. In large-scale distribution network scenarios, due to the ranging errors and noise in the laser radar scanning data and the sparsity of the point cloud, the performance of traditional registration algorithms is often difficult to meet actual needs, which may lead to long registration time or failure. Summary of the invention

[0005] The present invention provides a method, device, equipment and medium for detecting cable icing based on laser radar, so as to improve the efficiency and accuracy of alignment, and further improve the accuracy of icing detection.

[0006] In a first aspect, the present invention provides a method for detecting cable ice coating based on laser radar, comprising:

[0007] Get two frames of point cloud to be registered;

[0008] Extract key points from the point cloud of each frame to obtain a key point cloud of the point cloud of each frame;

[0009] Inputting the key point clouds of the two frames into the registration network for processing, the registration network adaptively learns the overlapping areas of the point clouds of the two frames based on the spatial attention mechanism, and predicts the relative poses of the point clouds of the two frames;

[0010] The two frames of point clouds are registered based on their relative poses to obtain a fused point cloud;

[0011] Extracting an ice-covered cable point cloud representing the ice-covered cable from the fused point cloud;

[0012] Determining a three-dimensional size of the ice-covered cable based on the ice-covered cable point cloud;

[0013] The ice coating thickness is calculated based on the three-dimensional dimensions of the ice-coated cable.

[0014] Optionally, extracting key points from the point cloud of each frame to obtain a key point cloud of the point cloud of each frame includes:

[0015] Performing a rotation compensation transformation on the point cloud of each frame to obtain a compensated transformed point cloud;

[0016] Extracting key points from the transformed point cloud to obtain an initial key point cloud composed of key points;

[0017] The key points in the initial key point cloud are subjected to rotation compensation inverse transformation to obtain the key point cloud of each frame of the point cloud.

[0018] Optionally, performing a rotation compensation transformation on the point cloud of each frame to obtain a compensated transformed point cloud includes:

[0019] Down-sampling the point cloud of each frame to obtain a sparse point cloud;

[0020] Extracting a first point cloud representing the ice-covered cable from the sparse point cloud;

[0021] Calculating the angle between the first point cloud and the normal vector of the horizontal plane;

[0022] Determine a rotation compensation transformation matrix based on the angle;

[0023] The point cloud is multiplied by the rotation compensation transformation matrix to obtain a compensated transformed point cloud.

[0024] Optionally, each frame of the key point cloud includes a surface key point cloud and a corner point cloud, and the registration network includes two feature encoders and a feature decoder with a spatial attention weighting mechanism. The two frames of the key point clouds are input into the registration network for processing. The registration network adaptively learns the overlapping area of ​​the two frames of the point clouds based on the spatial attention mechanism and predicts the relative pose of the two frames of the point clouds, including:

[0025] Inputting the surface key point cloud of the first frame key point cloud and the surface key point cloud of the second frame key point cloud into the first feature encoder for processing, obtaining the surface spatial attention features of the first frame key point cloud and the surface spatial attention features of the second frame key point cloud;

[0026] Inputting the corner point cloud of the key point cloud of the first frame and the corner point cloud of the key point cloud of the second frame into the second feature encoder for processing, obtaining the corner point spatial attention features of the key point cloud of the first frame and the corner point spatial attention features of the key point cloud of the second frame;

[0027] Fusion of the surface spatial attention feature and the corner spatial attention feature to obtain a spatial attention fusion feature;

[0028] The spatial attention fusion feature is input into the feature decoder for decoding to obtain the relative pose of the point cloud of the two frames.

[0029] Optionally, the surface key point cloud of the first frame key point cloud and the surface key point cloud of the second frame key point cloud are input into a first feature encoder for processing to obtain the surface spatial attention features of the first frame key point cloud and the surface spatial attention features of the second frame key point cloud, including:

[0030] For each of the surface key point clouds, a multi-layer perceptron is used to extract global features of the surface key point cloud;

[0031] Input the global feature into the spatial attention module for processing, and obtain a spatial attention score matrix composed of the spatial attention scores of each element in the global feature;

[0032] Normalizing the spatial attention score matrix to obtain a spatial attention weight matrix;

[0033] The product of the global feature and the spatial attention weight matrix is ​​calculated to obtain the surface spatial attention feature.

[0034] Optionally, the feature decoder includes a fully connected layer, and the spatial attention fusion feature is input into the feature decoder for decoding to obtain the relative position and posture of the two frames of the point cloud, including:

[0035] The fully connected layer performs a fully connected mapping on the spatial attention fusion feature to obtain a relative pose vector representing the relative pose of the point clouds of the two frames.

[0036] Optionally, before obtaining the two frames of point clouds to be registered, the following steps are also included:

[0037] Extracting key point clouds of training samples, wherein the training samples include source frame point clouds and target point clouds;

[0038] The key point cloud of the training sample is input into the registration network for processing to obtain the relative pose of the source frame point cloud and the target point cloud;

[0039] Extracting a non-ground target point cloud in the source frame point cloud and a non-ground target point cloud in the target point cloud;

[0040] Based on the relative pose of the source frame point cloud and the target point cloud, the non-ground target point cloud in the source frame point cloud is converted to the target point cloud coordinate system to obtain a converted point cloud;

[0041] Calculating the chamfer distance loss between the non-ground target point cloud and the converted point cloud in the target point cloud;

[0042] The network parameters of the registration network are updated based on the chamfer distance loss until the chamfer distance loss is less than a preset value.

[0043] In a second aspect, the present invention further provides a cable ice detection device based on laser radar, comprising:

[0044] Point cloud acquisition module, used to acquire two frames of point clouds to be registered;

[0045] A key point extraction module is used to extract key points from the point cloud of each frame to obtain a key point cloud of the point cloud of each frame;

[0046] A relative pose prediction module is used to input the key point clouds of the two frames into a registration network for processing. The registration network adaptively learns the overlapping areas of the point clouds of the two frames based on a spatial attention mechanism to predict the relative pose of the point clouds of the two frames;

[0047] Point cloud registration module, used to register two frames of point clouds based on their relative poses to obtain a fused point cloud;

[0048] An ice-covered cable point cloud extraction module, used to extract an ice-covered cable point cloud representing the ice-covered cable from the fused point cloud;

[0049] A three-dimensional size determination module, used to determine the three-dimensional size of the ice-covered cable based on the ice-covered cable point cloud;

[0050] An ice coating thickness calculation module is used to calculate the ice coating thickness based on the three-dimensional size of the ice-coated cable.

[0051] In a third aspect, the present invention further provides an electronic device, comprising:

[0052] one or more processors;

[0053] A storage device for storing one or more programs;

[0054] When the one or more programs are executed by the one or more processors, the one or more processors implement the laser radar-based cable ice detection method provided in the first aspect of the present invention.

[0055] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the laser radar-based cable ice detection method provided in the first aspect of the present invention is implemented.

[0056] The cable ice detection method based on laser radar provided by the present invention extracts key points from each frame of point cloud for two frames of point cloud to be registered, obtains key point cloud of each frame of point cloud, inputs the two frames of key point cloud into the registration network for processing, the registration network adaptively learns the overlapping area of ​​the two frames of point cloud based on the spatial attention mechanism, predicts the relative position and posture of the two frames of point cloud, registers the two frames of point cloud based on the relative position and posture of the two frames of point cloud, obtains a fused point cloud, extracts the iced cable point cloud representing the iced cable from the fused point cloud, determines the three-dimensional size of the iced cable based on the iced cable point cloud, and calculates the ice thickness based on the three-dimensional size of the iced cable. The attention weight mechanism enables the network to adaptively learn the overlapping area of ​​continuous point cloud frames, thereby realizing fast and effective end-to-end registration of large-scale point cloud scenes, and provides a good foundation for the precise registration algorithm, improves the registration efficiency and accuracy, and thus improves the accuracy of ice detection.

[0057] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0059] Figure 1 A flow chart of a cable ice detection method based on laser radar provided by the present invention;

[0060] Figure 2 A schematic diagram of the structure of a registration network provided by the present invention;

[0061] Figure 3 A structural schematic diagram of a feature encoder provided by the present invention;

[0062] Figure 4 A schematic structural diagram of a cable ice detection device based on laser radar provided by the present invention;

[0063] Figure 5 The present invention provides a schematic structural diagram of an electronic device.

[0064] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0065] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0066] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0067] Figure 1 This is a flow chart of a cable ice detection method based on laser radar provided by the present invention. This embodiment is applicable to the registration of large-scale spatial point clouds and the case of cable ice detection. The method can be executed by a cable ice detection device based on laser radar provided by an embodiment of the present invention. The device can be implemented by software and / or hardware, and is usually configured in an electronic device, such as Figure 1 As shown, the cable ice detection method based on laser radar includes the following steps:

[0068] S101, obtaining two frames of point clouds to be registered.

[0069] In the embodiment of the present invention, the laser radar continuously scans the space to be detected to obtain continuous multi-frame point clouds. In the embodiment of the present invention, the laser radar may be a multi-line laser radar. The two frames of point clouds to be registered may be two continuous frames of point clouds.

[0070] S102, extracting key points from each frame of point cloud to obtain a key point cloud for each frame of point cloud.

[0071] For each frame of point cloud, key points are extracted from the frame of point cloud to obtain the key point cloud of each frame of point cloud. Point cloud key point extraction refers to extracting some important points from the point cloud data set for subsequent point cloud analysis and processing. These key points usually include high curvature points, edge points, corner points, etc., which have important feature information and can be used to describe the local shape and structure of the point cloud. Exemplarily, algorithms such as SIFT, Harris, NARF, ISS and SUSAN can be used to extract key points of point clouds, which is not limited in the embodiments of the present invention.

[0072] During the radar scanning process, if the radar itself moves in the opposite direction of rotation, the radar laser rotation angle will be smaller than the actual angle. This phenomenon is called rotation distortion. Specifically, when the radar is rotating, if the radar itself is also rotating, the points in the collected point cloud data will have position deviations due to the rotation, resulting in inaccurate or even failed subsequent key point extraction. In some embodiments of the present invention, in order to solve the problem of low robustness of existing point cloud key point extraction methods in distribution network cable linear strip scenes, an improved key point extraction method based on rotation compensation is proposed to solve the problem of inaccurate or even failed key point extraction when there is an inclination angle between the point cloud frame and the XOY plane (horizontal plane) of the laser radar. Rotation compensation refers to the technology of compensating for the distortion of point cloud data caused by the movement of the radar carrier during the laser radar data acquisition process. Specifically, point cloud rotation compensation mainly corrects the distortion generated by the radar during the rotation process to ensure the accuracy of subsequent key point extraction.

[0073] Specifically, the key point cloud extraction process is as follows:

[0074] 1. Perform rotation compensation transformation on each frame of point cloud to obtain the compensated transformed point cloud.

[0075] Exemplarily, a rotation compensation transformation is performed on each frame of point cloud to correct the distortion caused by the radar during the rotation process, thereby obtaining a compensated transformed point cloud.

[0076] For example, for each frame point cloud P i Downsampling is performed to reduce the amount of data processing and obtain a sparse point cloud. The first point cloud φ representing the ice-covered cable is extracted from the sparse point cloud. R For example, a clustering algorithm or the like can be used to extract the first point cloud φ representing the ice-covered cable. R . Calculate the first point cloud φ R The angle θ with the normal vector of the XOY plane (horizontal plane) of the laser radar, and the rotation compensation transformation matrix is ​​determined based on the angle θ Then the point cloud P i Multiply by the rotation compensation transformation matrix Get the compensated transformed point cloud Pi′ .

[0077] For example, after obtaining the first point cloud φ R After the angle θ between the normal vector of the XOY plane (horizontal plane) of the laser radar, the rotation compensation transformation matrix It can be expressed as:

[0078]

[0079] 2. Extract key points from the transformed point cloud to obtain an initial key point cloud composed of key points.

[0080] For example, SIFT, Harris, NARF, ISS, and SUSAN algorithms can be used to transform the point cloud P i′ Extract key points from the , and get the initial key point cloud composed of key points The embodiments of the present invention are not limited here.

[0081] 3. Perform rotation compensation inverse transformation on the key points in the initial key point cloud to obtain the key point cloud of each frame point cloud.

[0082] For example, for the initial key point cloud The key points in the rotation compensation inverse transformation are used to obtain the key point cloud of each frame point cloud

[0083] S103, inputting the two frames of key point clouds into the registration network for processing. The registration network adaptively learns the overlapping area of ​​the two frames of point clouds based on the spatial attention mechanism and predicts the relative position and posture of the two frames of point clouds.

[0084] In an embodiment of the present invention, two frames of key point clouds are input into a pre-trained registration network for processing. The registration network adaptively learns the overlapping area of ​​the two frames of point clouds based on the spatial attention mechanism and predicts the relative pose of the two frames of point clouds.

[0085] Figure 2 A structural diagram of a registration network provided by the present invention, such as Figure 2 As shown, for example, each key point cloud of each frame includes a surface key point cloud Surf Keypoint Cloud and a corner key point cloud Corner Keypoint Cloud, and the registration network includes two feature encoders Encoders with a spatial attention weighting mechanism and a feature decoder Decoder. The two frames of key point clouds are input into the registration network for processing. The registration network adaptively learns the overlapping area of ​​the two frames of point clouds based on the spatial attention mechanism and predicts the relative pose of the two frames of point clouds, including:

[0086] 1. The surface key point cloud Surf Keypoint Cloud1 of the first frame key point cloud and the surface key point cloud Surf Keypoint Cloud2 of the second frame key point cloud are input into the first feature encoder Encoder1 for processing to obtain the surface spatial attention feature Surf Spatial Feature1 of the first frame key point cloud and the surface spatial attention feature Surf Spatial Feature2 of the second frame key point cloud.

[0087] Figure 3 A structural diagram of a feature encoder provided by the present invention, such as Figure 3 As shown in the figure, the feature encoder includes multi-layer perceptrons MLPs and spatial attention modules. The feature encoder processing process is as follows:

[0088] 1.1. For each surface keypoint cloud Surf Keypoint Cloud, multi-layer perceptrons (MLPs) are used to extract the global features of the surface keypoint cloud.

[0089] MLPs is similar to the PointNet architecture. By inputting the surface keypoint cloud Surf Keypoint Cloud into MLPs, the global features of the surface keypoint cloud Surf Keypoint Cloud can be output.

[0090] 1.2. Input the global features into the spatial attention module for processing to obtain a spatial attention score matrix composed of the spatial attention scores of each element in the global features.

[0091] Exemplarily, the global features are respectively input into the global maximum pooling layer (GMP) and the global average pooling layer (GAP) for processing to obtain the global maximum pooling features and the global average pooling features. The global maximum pooling features and the global average pooling features are spliced ​​in the channel dimension to obtain the spliced ​​features. The spliced ​​features are input into a convolution layer for convolution processing to obtain a spatial attention score matrix composed of the spatial attention scores of each element in the global features.

[0092] 1.3. Normalize the spatial attention score matrix to obtain the spatial attention weight matrix.

[0093] The spatial attention score matrix is ​​nonlinearly activated to obtain the spatial attention weight matrix of the global feature. Each element in the spatial attention weight matrix is ​​the spatial attention weight of the corresponding element in the global feature.

[0094] 1.4. Calculate the product of the global feature and the spatial attention weight matrix to obtain the surface spatial attention feature.

[0095] Calculate the product of the global feature and the spatial attention weight matrix, that is, multiply the global feature by the corresponding element of the spatial attention weight matrix to obtain the surface spatial attention feature Surf Spatial Feature.

[0096] 2. The corner point cloud Corner Keypoint Cloud1 of the key point cloud of the first frame and the corner point cloud Corner Keypoint Cloud2 of the key point cloud of the second frame are input into the second feature encoder Encoder2 for processing to obtain the corner point spatial attention feature Corner Spatial Feature1 of the key point cloud of the first frame and the corner point spatial attention feature Corner Spatial Feature2 of the key point cloud of the second frame.

[0097] The structure and processing process of the second feature encoder are similar to those of the first feature encoder, and reference may be made to the structure and processing process of the first feature encoder in the aforementioned embodiment, which will not be described in detail in the embodiment of the present invention.

[0098] 3. Fuse the surface spatial attention features and corner spatial attention features to obtain the spatial attention fusion features.

[0099] like Figure 2 As shown in the figure, the two surface spatial attention features Surf Spatial Feature1 and Surf SpatialFeature1, and the two corner spatial attention features Corner Spatial Feature1 and Corner SpatialFeature2 are spliced ​​in dimension, and then the spliced ​​features are processed by global maximum pooling to obtain the spatial attention fusion feature Aggregated Feature.

[0100] 4. Input the spatial attention fusion feature into the feature decoder for decoding to obtain the relative pose of the two frames of point cloud.

[0101] In the embodiment of the present invention, Figure 2 As shown, the spatial attention fusion feature is input into the feature decoder for decoding to obtain the relative pose of the two frames of point clouds. Exemplarily, the feature decoder includes a fully connected layer with 7 hidden layers, and the fully connected layer performs a fully connected mapping on the spatial attention fusion feature to obtain a relative pose vector T representing the relative pose of the two frames of point clouds. final(1×7) , where the first four quantities represent the rotation quaternion q Tq=1, the last three quantities represent the translation vector

[0102] S104: registering the two frames of point clouds based on their relative poses to obtain a fused point cloud.

[0103] After obtaining the relative pose of the two frames of point clouds, the translation transformation matrix of the two frames of point clouds is determined according to the relative pose of the two frames of point clouds, and then the unified world coordinate system of the two frames of point clouds is combined based on the translation transformation matrix. Similarly, in the above-mentioned registration process of the present invention, the unified world coordinate system of all point clouds collected by the laser radar is combined to obtain a fused point cloud.

[0104] S105: extracting an ice-covered cable point cloud representing the ice-covered cable from the fused point cloud.

[0105] In the embodiment of the present invention, a clustering algorithm or a semantic segmentation algorithm is used to extract an ice-covered cable point cloud representing the ice-covered cable from the fused point cloud. The embodiment of the present invention does not limit the algorithm for extracting the ice-covered cable point cloud representing the ice-covered cable.

[0106] S106. Determine the three-dimensional size of the ice-covered cable based on the ice-covered cable point cloud.

[0107] In an embodiment of the present invention, a three-dimensional incremental modeling method may be used to model the ice-covered cable point cloud and determine the three-dimensional size of the ice-covered cable.

[0108] S107: Calculate ice thickness based on the three-dimensional size of the ice-covered cable.

[0109] In an embodiment of the present invention, after determining the three-dimensional size of the ice-covered cable, the ice thickness is calculated in combination with prior knowledge of the distribution network cable (such as the cable diameter, etc.). Exemplarily, the diameter of the ice-covered cable is subtracted from the cable diameter and divided by 2 to obtain the ice thickness.

[0110] The cable ice detection method based on laser radar provided by the present invention extracts key points from each frame of point cloud for two frames of point cloud to be registered, obtains key point cloud of each frame of point cloud, inputs the two frames of key point cloud into the registration network for processing, the registration network adaptively learns the overlapping area of ​​the two frames of point cloud based on the spatial attention mechanism, predicts the relative position and posture of the two frames of point cloud, registers the two frames of point cloud based on the relative position and posture of the two frames of point cloud, obtains a fused point cloud, extracts the iced cable point cloud representing the iced cable from the fused point cloud, determines the three-dimensional size of the iced cable based on the iced cable point cloud, and calculates the ice thickness based on the three-dimensional size of the iced cable. The attention weight mechanism enables the network to adaptively learn the overlapping area of ​​continuous point cloud frames, thereby realizing fast and effective end-to-end registration of large-scale point cloud scenes, and provides a good foundation for the precise registration algorithm, improves the registration efficiency and accuracy, and thus improves the accuracy of ice detection.

[0111] In some embodiments of the present invention, the registration network needs to be trained before it is applied. The existing training process usually requires a large amount of pose truth label data. In the actual scenario of ice coverage monitoring in the distribution network, obtaining real ground trajectory data is both complex and labor-intensive. In view of the problem of lack of pose truth label data for large-scale distribution network laser radar scanning point cloud registration, the present invention proposes an unsupervised training method, and the specific training process is:

[0112] 1. Prepare multiple training samples in advance, including source frame point cloud and target point cloud.

[0113] 2. Extract key point clouds of training samples. The process of extracting key point clouds can refer to the aforementioned embodiments of the present invention and will not be described in detail here.

[0114] 3. Input the key point cloud of the training sample into the registration network for processing to obtain the relative pose of the source frame point cloud and the target point cloud. The processing process of the registration network can refer to the above-mentioned embodiment of the present invention, which will not be described in detail here.

[0115] 4. Extract the non-ground target point cloud in the source frame point cloud and the non-ground target point cloud in the target point cloud.

[0116] That is, the ground point cloud is removed from the source frame point cloud and the target point cloud, and the non-ground target point cloud is retained.

[0117] 5. Based on the relative pose of the source frame point cloud and the target point cloud, the non-ground target point cloud in the source frame point cloud is converted to the target point cloud coordinate system to obtain the converted point cloud.

[0118] Exemplarily, the non-ground target point cloud of the source frame point cloud is multiplied by the relative pose vector output by the registration network to obtain the converted point cloud.

[0119] 6. Calculate the chamfer distance loss between the non-ground target point cloud and the converted point cloud in the target point cloud.

[0120] Chamfer distance loss is a measure used to evaluate the similarity between two sets of point clouds. In the embodiment of the present invention, in order to make the registration network more robust and converge faster, a dynamic overlap rate coefficient γ is used to correct the chamfer distance loss in real time. For example, the calculation formula of the chamfer distance loss is:

[0121]

[0122] in, is the non-ground target point cloud in the target point cloud, is the converted point cloud, γ is the dynamic overlap rate coefficient, x is the midpoint of the converted point cloud, is a point in the target point cloud, size() means finding the number of points in the point cloud in brackets, mean() means finding the mean value in brackets, std() means finding the standard deviation in brackets, and min() means finding the minimum value.

[0123] 7. Update the network parameters of the registration network based on the chamfer distance loss until the chamfer distance loss is less than the preset value.

[0124] Exemplarily, the chamfer distance loss corresponding to the sample is compared with the loss threshold. If the chamfer distance loss is greater than the loss threshold, the network parameters of the registration network are updated, and new training samples are obtained to repeat the above training process until the chamfer distance loss is less than or equal to the loss threshold, or the number of iterations reaches a preset number.

[0125] Figure 4 A schematic diagram of the structure of a cable ice detection device based on laser radar provided by the present invention is shown in FIG. Figure 4 As shown, the cable ice detection device based on laser radar includes:

[0126] Point cloud acquisition module 201, used to acquire two frames of point clouds to be registered;

[0127] A key point extraction module 202 is used to extract key points from the point cloud of each frame to obtain a key point cloud of each frame of the point cloud;

[0128] The relative pose prediction module 203 is used to input the key point clouds of the two frames into the registration network for processing. The registration network adaptively learns the overlapping area of ​​the point clouds of the two frames based on the spatial attention mechanism to predict the relative pose of the point clouds of the two frames;

[0129] A point cloud registration module 204 is used to register the two frames of point clouds based on their relative positions and poses to obtain a fused point cloud;

[0130] An ice-covered cable point cloud extraction module 205 is used to extract an ice-covered cable point cloud representing the ice-covered cable from the fused point cloud;

[0131] A three-dimensional size determination module 206, configured to determine the three-dimensional size of the ice-covered cable based on the ice-covered cable point cloud;

[0132] The ice coating thickness calculation module 207 is used to calculate the ice coating thickness based on the three-dimensional size of the ice-coated cable.

[0133] In some embodiments of the present invention, the key point extraction module 202 includes:

[0134] A rotation compensation submodule, used for performing rotation compensation transformation on the point cloud of each frame to obtain a compensated transformed point cloud;

[0135] A key point extraction submodule, used to extract key points from the transformed point cloud to obtain an initial key point cloud composed of key points;

[0136] The inverse transformation submodule is used to perform rotation compensation inverse transformation on the key points in the initial key point cloud to obtain the key point cloud of each frame of the point cloud.

[0137] In some embodiments of the present invention, the rotation compensation submodule includes:

[0138] A downsampling unit, used for downsampling the point cloud of each frame to obtain a sparse point cloud;

[0139] A first point cloud extraction unit, configured to extract a first point cloud representing an ice-covered cable from the sparse point cloud;

[0140] An angle calculation unit, used to calculate the angle between the first point cloud and the normal vector of the horizontal plane;

[0141] A transformation matrix determining unit, used to determine a rotation compensation transformation matrix based on the included angle;

[0142] The compensation transformation unit is used to multiply the point cloud by the rotation compensation transformation matrix to obtain a compensated transformed point cloud.

[0143] In some embodiments of the present invention, the key point cloud of each frame includes a surface key point cloud and a corner point cloud, the registration network includes two feature encoders with a spatial attention weighting mechanism and a feature decoder, and the relative pose prediction module 203 includes:

[0144] A surface space attention feature extraction submodule is used to input the surface key point cloud of the first frame key point cloud and the surface key point cloud of the second frame key point cloud into the first feature encoder for processing, so as to obtain the surface space attention features of the first frame key point cloud and the surface space attention features of the second frame key point cloud;

[0145] A corner point spatial attention feature extraction submodule is used to input the corner point cloud of the first frame key point cloud and the corner point cloud of the second frame key point cloud into the second feature encoder for processing, so as to obtain the corner point spatial attention features of the first frame key point cloud and the corner point spatial attention features of the second frame key point cloud;

[0146] A feature fusion submodule, used to fuse the surface spatial attention feature and the corner spatial attention feature to obtain a spatial attention fusion feature;

[0147] The decoding submodule is used to input the spatial attention fusion feature into the feature decoder for decoding to obtain the relative pose of the point cloud of the two frames.

[0148] In some embodiments of the present invention, the surface spatial attention feature extraction submodule includes:

[0149] A global feature extraction unit, configured to extract global features of each of the surface key point clouds using a multi-layer perceptron;

[0150] An attention processing unit, used for inputting the global feature into a spatial attention module for processing, and obtaining a spatial attention score matrix composed of the spatial attention scores of each element in the global feature;

[0151] A normalization unit, used for normalizing the spatial attention score matrix to obtain a spatial attention weight matrix;

[0152] A product unit is used to calculate the product of the global feature and the spatial attention weight matrix to obtain a surface spatial attention feature.

[0153] In some embodiments of the present invention, the feature decoder includes a fully connected layer, and the decoding submodule includes:

[0154] A fully connected mapping unit is used for the fully connected layer to perform fully connected mapping on the spatial attention fusion feature to obtain a relative posture vector representing the relative posture of the point clouds of two frames.

[0155] In some embodiments of the present invention, the cable ice detection device based on laser radar further includes:

[0156] A sample key point cloud extraction module is used to extract the key point cloud of the training sample before obtaining the two frames of point cloud to be registered, wherein the training sample includes the source frame point cloud and the target point cloud;

[0157] The sample relative pose prediction module is used to input the key point cloud of the training sample into the registration network for processing to obtain the relative pose of the source frame point cloud and the target point cloud;

[0158] A non-ground target point cloud extraction module is used to extract the non-ground target point cloud in the source frame point cloud and the non-ground target point cloud in the target point cloud;

[0159] A point cloud conversion module, used to convert the non-ground target point cloud in the source frame point cloud to the target point cloud coordinate system based on the relative pose of the source frame point cloud and the target point cloud, to obtain a converted point cloud;

[0160] A loss calculation module, used to calculate the chamfer distance loss between the non-ground target point cloud in the target point cloud and the converted point cloud;

[0161] A parameter updating module is used to update the network parameters of the registration network based on the chamfer distance loss until the chamfer distance loss is less than a preset value.

[0162] The above-mentioned laser radar-based cable ice detection device can execute the laser radar-based cable ice detection method provided by the aforementioned embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the laser radar-based cable ice detection method.

[0163] Figure 5 A schematic diagram of the structure of an electronic device provided by the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0164] like Figure 5 As shown, the electronic device includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0165] A number of components in the electronic device are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0166] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a cable ice detection method based on a laser radar.

[0167] In some embodiments, the cable ice detection method based on laser radar can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the cable ice detection method based on laser radar described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the cable ice detection method based on laser radar in any other appropriate manner (for example, by means of firmware).

[0168] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0169] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0170] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0171] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0172] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0173] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0174] An embodiment of the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the laser radar-based cable ice detection method provided in any embodiment of the present application.

[0175] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0176] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0177] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A cable ice detection method based on laser radar, characterized in that: include: Get two frames of point cloud to be registered; Extract key points from the point cloud of each frame to obtain a key point cloud of the point cloud of each frame; Inputting the key point clouds of the two frames into the registration network for processing, the registration network adaptively learns the overlapping areas of the point clouds of the two frames based on the spatial attention mechanism, and predicts the relative poses of the point clouds of the two frames; The two frames of point clouds are registered based on their relative poses to obtain a fused point cloud; Extracting an ice-covered cable point cloud representing the ice-covered cable from the fused point cloud; Determining a three-dimensional size of the ice-covered cable based on the ice-covered cable point cloud; The ice coating thickness is calculated based on the three-dimensional dimensions of the ice-coated cable.

2. The cable ice detection method based on laser radar according to claim 1 is characterized in that: Extracting key points from the point cloud of each frame to obtain a key point cloud of the point cloud of each frame includes: Performing a rotation compensation transformation on the point cloud of each frame to obtain a compensated transformed point cloud; Extracting key points from the transformed point cloud to obtain an initial key point cloud composed of key points; The key points in the initial key point cloud are subjected to rotation compensation inverse transformation to obtain the key point cloud of each frame of the point cloud.

3. The cable ice detection method based on laser radar according to claim 2 is characterized in that: Performing a rotation compensation transformation on the point cloud of each frame to obtain a compensated transformed point cloud includes: Down-sampling the point cloud of each frame to obtain a sparse point cloud; Extracting a first point cloud representing the ice-covered cable from the sparse point cloud; Calculating the angle between the first point cloud and the normal vector of the horizontal plane; Determine a rotation compensation transformation matrix based on the angle; The point cloud is multiplied by the rotation compensation transformation matrix to obtain a compensated transformed point cloud.

4. The cable ice detection method based on laser radar according to claim 1 is characterized in that: Each frame of the key point cloud includes a surface key point cloud and a corner point cloud. The registration network includes two feature encoders with a spatial attention weighting mechanism and a feature decoder. The two frames of the key point clouds are input into the registration network for processing. The registration network adaptively learns the overlapping area of ​​the two frames of the point clouds based on the spatial attention mechanism and predicts the relative position and posture of the two frames of the point clouds, including: Inputting the surface key point cloud of the first frame key point cloud and the surface key point cloud of the second frame key point cloud into the first feature encoder for processing, obtaining the surface spatial attention features of the first frame key point cloud and the surface spatial attention features of the second frame key point cloud; Inputting the corner point cloud of the key point cloud of the first frame and the corner point cloud of the key point cloud of the second frame into the second feature encoder for processing, thereby obtaining the corner point spatial attention features of the key point cloud of the first frame and the corner point spatial attention features of the key point cloud of the second frame; Fusion of the surface spatial attention feature and the corner spatial attention feature to obtain a spatial attention fusion feature; The spatial attention fusion feature is input into the feature decoder for decoding to obtain the relative pose of the point cloud of the two frames.

5. The cable ice detection method based on laser radar according to claim 4 is characterized in that: The surface key point cloud of the first frame key point cloud and the surface key point cloud of the second frame key point cloud are input into the first feature encoder for processing, and the surface spatial attention features of the first frame key point cloud and the surface spatial attention features of the second frame key point cloud are obtained, including: For each of the surface key point clouds, a multi-layer perceptron is used to extract global features of the surface key point cloud; Input the global feature into the spatial attention module for processing, and obtain a spatial attention score matrix composed of the spatial attention scores of each element in the global feature; Normalizing the spatial attention score matrix to obtain a spatial attention weight matrix; The product of the global feature and the spatial attention weight matrix is ​​calculated to obtain the surface spatial attention feature.

6. The cable ice detection method based on laser radar according to claim 4 is characterized in that: The feature decoder includes a fully connected layer, and the spatial attention fusion feature is input into the feature decoder for decoding to obtain the relative position of the point cloud of two frames, including: The fully connected layer performs a fully connected mapping on the spatial attention fusion feature to obtain a relative pose vector representing the relative pose of the point clouds of the two frames.

7. The cable ice detection method based on laser radar according to claim 1 is characterized in that: Before obtaining the two frames of point clouds to be registered, it also includes: Extracting key point clouds of training samples, wherein the training samples include source frame point clouds and target point clouds; The key point cloud of the training sample is input into the registration network for processing to obtain the relative pose of the source frame point cloud and the target point cloud; Extracting a non-ground target point cloud in the source frame point cloud and a non-ground target point cloud in the target point cloud; Based on the relative pose of the source frame point cloud and the target point cloud, the non-ground target point cloud in the source frame point cloud is converted to the target point cloud coordinate system to obtain a converted point cloud; Calculating the chamfer distance loss between the non-ground target point cloud and the converted point cloud in the target point cloud; The network parameters of the registration network are updated based on the chamfer distance loss until the chamfer distance loss is less than a preset value.

8. A cable ice detection device based on laser radar, characterized in that: include: Point cloud acquisition module, used to acquire two frames of point clouds to be registered; A key point extraction module is used to extract key points from the point cloud of each frame to obtain a key point cloud of the point cloud of each frame; A relative pose prediction module is used to input the key point clouds of the two frames into a registration network for processing. The registration network adaptively learns the overlapping areas of the point clouds of the two frames based on a spatial attention mechanism to predict the relative pose of the point clouds of the two frames; Point cloud registration module, used to register two frames of point clouds based on their relative poses to obtain a fused point cloud; An ice-covered cable point cloud extraction module, used to extract an ice-covered cable point cloud representing the ice-covered cable from the fused point cloud; A three-dimensional size determination module, used to determine the three-dimensional size of the ice-covered cable based on the ice-covered cable point cloud; An ice coating thickness calculation module is used to calculate the ice coating thickness based on the three-dimensional size of the ice-coated cable.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the laser radar-based cable ice detection method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the cable ice detection method based on laser radar as described in any one of claims 1 to 7 is implemented.

Images