Railway scene point cloud segmentation method and system based on mutual attention

Abstract

The invention discloses a railway scene point cloud segmentation method and system based on mutual attention, and relates to three-dimensional point cloud processing, and the method comprises the steps: employing a laser radar to collect the point cloud data of different railway track scenes; constructing a railway scene point cloud segmentation network model based on mutual attention and point cloud serialization, and performing point cloud feature extraction; performing model training on the railway scene point cloud segmentation network model according to the point cloud data to obtain a trained model weight; and applying the trained model weight, performing model testing according to the point cloud data, and generating a segmentation result of the railway scene point cloud. According to the method, the segmentation accuracy of the railway scene point cloud in the real environment is improved, and the current situation of railway scene point cloud segmentation in the real environment is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional point cloud processing, and in particular to a railway scene point cloud segmentation method and system based on mutual attention. Background Art

[0002] At present, a large number of LiDAR-based 3D point cloud segmentation (PCS) research results have been achieved, but these methods are mainly focused on urban road scenes, and their application in railway environments still faces some unique challenges. Compared with road environments, the typical targets and spatial layouts of railway scenes are particular, and existing 3DPCS methods are often difficult to transplant directly, or the results are not ideal. Although these methods can effectively capture dense point cloud features at close range, thereby accurately identifying and segmenting objects in urban environments, in railway scenes, especially at long distances of more than 100 meters, the density of point clouds is significantly reduced, resulting in the perception range of these methods being insufficient to cover a large enough space, making it difficult to capture sufficient contextual information, affecting the accuracy of segmentation.

[0003] In addition, as the distance increases, the point cloud data becomes more sparse, which makes it difficult for traditional methods to establish the dependencies between the internal features of the point cloud in such a sparse environment, because they are mostly designed to process dense point clouds. In the long-distance rail scene, because the appearance features of the object are not significant enough, the ordinary 3DPCS method is difficult to effectively distinguish the rail from other surrounding elements, further limiting its application effect.

[0004] First, some methods use columnar segmentation to deal with the variable density characteristics of point clouds. Although this method improves the feature representation of near-distance and long-distance point clouds to a certain extent, it mainly optimizes the uneven density distribution of local point clouds in the vertical and horizontal directions. However, in scenes with linear structures such as railroad tracks, this segmentation method still has difficulty coping with the extreme sparsity problem caused by long distances. Another type of method divides the point cloud space into radial windows based on spherical coordinates and combines attention mechanisms to better capture global context information. In theory, this method can improve the understanding of long-distance point clouds, but in actual railway scene applications, the attention mechanism may still have difficulty extracting effective features from point clouds with low information density when faced with highly sparse data. Since long-distance point clouds do not have obvious features, even traditional attention mechanisms find it difficult to establish effective information associations between these sparse points, thus affecting their segmentation effect. This makes it a major challenge to effectively extract and utilize point cloud features in railway scenes, especially under long-distance conditions. Therefore, it is necessary to design a network model that can effectively extract features from long-distance sparse point clouds.

[0005] Secondly, there are obvious differences between railway scenes and urban road scenes, mainly reflected in many aspects such as environmental structure, target type and point cloud density. These differences make the traditional urban road point cloud segmentation method perform poorly in the railway environment. Therefore, in order to meet these challenges, it is urgent to design a network model with high generalization ability that can adapt to the particularity of railway scenes. This model must not only deal with the sparsity of point clouds in long-distance situations, but also work stably in various complex environments to ensure accurate identification and segmentation of key targets in railway scenes. This requires the model to have stronger contextual understanding capabilities and robustness under different environmental conditions to cope with the unique scene requirements of railways.

[0006] To this end, a 3D point cloud segmentation network is designed in this paper, which relies on point cloud information as input. At the same time, an improved method is used to improve the robustness and accuracy of the segmentation results of long-distance sparse point cloud data in railway scenes. Experiments have shown that the model has good adaptability and performance, and provides an effective point cloud segmentation solution for safe and efficient train autonomous driving operation. Summary of the invention

[0007] The purpose of this section is to summarize some aspects of embodiments of the present invention and to briefly introduce some preferred embodiments.

[0008] In view of the above existing problems, the present invention is proposed.

[0009] Therefore, the present invention provides a railway scene point cloud segmentation method and system based on mutual attention, which can solve the problems mentioned in the background technology.

[0010] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0011] In a first aspect, the present invention provides a railway scene point cloud segmentation method based on mutual attention, which includes collecting point cloud data of different railway track scenes using a laser radar;

[0012] Build a railway scene point cloud segmentation network model based on mutual attention and point cloud serialization, and perform point cloud feature extraction;

[0013] Performing model training on the railway scene point cloud segmentation network model according to the point cloud data to obtain a trained model weight;

[0014] The trained model weights are applied, and a model test is performed based on the point cloud data to generate a segmentation result of the railway scene point cloud.

[0015] As a preferred solution of the railway scene point cloud segmentation method based on mutual attention of the present invention, wherein: the point cloud data of different railway track scenes collected includes:

[0016] Use lidar to collect data for different orbital scenarios;

[0017] Perform format conversion, filtering and data annotation processing on the collected point cloud data;

[0018] The point cloud data after data annotation is used as the training and testing data set for the point cloud segmentation network.

[0019] As a preferred solution of the railway scene point cloud segmentation method based on mutual attention of the present invention, wherein: the railway scene point cloud segmentation network model includes a point cloud preprocessing module, a point cloud feature extraction module and a point cloud feature reconstruction module;

[0020] The point cloud preprocessing module includes:

[0021] Voxelize the input point cloud to reduce the number of points and select an appropriate voxel size;

[0022] Serialize the voxelized point cloud to maintain the spatial proximity of the point cloud voxels;

[0023] The point cloud feature extraction module includes a bidirectional recursive attention module, a sparse spatial feature extraction module and a multi-view feature fusion module;

[0024] The point cloud feature extraction module includes:

[0025] Use the bidirectional recursive attention module and the sparse spatial feature extraction module to extract features from a single actual input point cloud;

[0026] The extracted point cloud features are input into the multi-view feature fusion module, and feature fusion is performed. After downsampling, the layer-by-layer feature point cloud is obtained, as follows:

[0027] pc1∈R4096×32

[0028] pc2∈R2048×64

[0029] pc3∈R1024×128

[0030] pc4∈R512×256

[0031] pc5∈R256×256

[0032] Through residual connection, different feature point clouds are upsampled and feature adjusted respectively to obtain pc′ 1，2，3，4，5 ∈R8192×32;

[0033] The output point cloud feature pc is obtained through the fully connected layer out ∈R8192×4.

[0034] As a preferred solution of the railway scene point cloud segmentation method based on mutual attention described in the present invention, the global feature extraction of the bidirectional recursive attention module includes:

[0035] Take serialized point cloud data as input;

[0036] Use bidirectional gated recurrent units to process serialized point cloud data and capture spatial sequence dependencies in the sequence;

[0037] Apply a multi-head cross-attention mechanism to capture the features of different subspaces by processing multiple attention heads in parallel;

[0038] After multi-head cross attention, normalization is performed and features are extracted through a multi-layer perceptron;

[0039] Perform multi-head cross attention, normalization and multi-layer perceptron operations again;

[0040] Add the features after multiple processing;

[0041] After the addition operation, multi-head cross attention, normalization and multi-layer perceptron operations are performed again to obtain the processed output features.

[0042] As a preferred solution of the railway scene point cloud segmentation method based on mutual attention of the present invention, the multi-feature fusion process of the multi-view feature fusion module includes:

[0043] Receiving output features from the bidirectional recursive attention module and the sparse spatial feature extraction module;

[0044] A multi-head cross-attention mechanism is applied to the two input features respectively, capturing features of different subspaces by processing multiple attention heads in parallel;

[0045] Normalize the features processed by multi-head cross attention, and then extract features again through multi-layer perceptron;

[0046] The normalized and multi-layer perceptron processed features are sent to another multi-layer perceptron for further processing and then added to the original features;

[0047] Pass the features to the next module or layer through residual connections;

[0048] After the above processing, the final result is obtained, which combines the output features of the bidirectional recursive attention module and the sparse spatial feature extraction module.

[0049] As a preferred solution of the railway scene point cloud segmentation method based on mutual attention of the present invention, the training of the railway scene point cloud segmentation network model includes:

[0050] Using bidirectional gated recurrent units to enhance the model’s understanding of sparse variations in point clouds;

[0051] Improve feature expression capabilities and capture subspace features through multi-head cross-attention mechanism;

[0052] Apply layer normalization operations for training and accelerating convergence;

[0053] Use a multi-layer perceptron to perform addition operations on features.

[0054] As a preferred solution of the railway scene point cloud segmentation method based on mutual attention of the present invention, wherein: the segmentation result of generating the railway scene point cloud includes:

[0055] Use the trained model weights to perform point cloud data segmentation tests on railway scenes;

[0056] Output and verify the accuracy of segmentation results and model performance;

[0057] The accuracy of the segmentation results and the model performance are verified as follows:

[0058] The point cloud containing multi-scale segmentation features output by the railway scene point cloud segmentation network model is input into a fully connected layer to obtain the probability value of each point in the railway scene point cloud for each classification;

[0059] If the classification corresponding to the highest probability of a point is consistent with the actual classification, the prediction is considered correct;

[0060] The segmentation accuracy of the entire point cloud is calculated by the ratio of the number of correctly predicted points to the total number of points, and the segmentation intersection-union ratio is calculated by comparing the ratio of the number of correctly predicted points to the actual number of points in the point cloud and the union of the prediction results.

[0061] In a second aspect, the present invention provides a railway scene point cloud segmentation system based on mutual attention, which includes: a data acquisition module, a model construction module, a model training module and a model verification module;

[0062] The data acquisition module is used to collect point cloud data of different railway track scenes using laser radar;

[0063] The model building module is used to build a railway scene point cloud segmentation network model based on mutual attention and point cloud serialization, and perform point cloud feature extraction;

[0064] The model training module is used to perform model training on the railway scene point cloud segmentation network model according to the point cloud data to obtain the trained model weight;

[0065] The model verification module is used to apply the trained model weights and perform model testing based on the point cloud data to generate a segmentation result of the railway scene point cloud.

[0066] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, the steps of a railway scene point cloud segmentation method based on mutual attention are implemented.

[0067] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, the steps of a railway scene point cloud segmentation method based on mutual attention are implemented.

[0068] Compared with the prior art, the beneficial effect of the present invention is that based on the research of the existing mainstream point cloud datasets, the dataset of the railway scene is improved; on the one hand, for the situation where it is difficult to use the camera synchronously in the railway scene, it is hoped that the detection of the railway and the obstacles ahead can be completely dependent on the lidar, and the single-path orientation feature is selected as the point cloud feature finally retained; this method is more in line with the actual needs of the railway scene; on the other hand, since the high-frequency radar scanning is prone to cause ghosting when the train is running at high speed, in order to adapt to this situation, the sparse point cloud generated at a low scanning frequency is selected as the input of the model, thereby reducing the interference of ghosting and improving the accuracy of detection; on this basis, a point cloud segmentation network for railway scenes based on mutual attention and point cloud serialization is constructed; in the point cloud segmentation network, by combining the application of the overall fusion mechanism of local feature extraction and global feature extraction, the structural information of the long-distance sparse point cloud is retained as much as possible, and the features of the input point cloud are effectively learned, reducing the influence of a large amount of interference on the accuracy of the point cloud segmentation of the sparse track scene in an unrestricted environment. Generating serialized point clouds through voxelization and serialization processing helps to maintain spatial context information during deep learning; the bidirectional recursive attention module can effectively capture the contextual dependencies in spatial sequence data and strengthen the representation of important features by utilizing bidirectional gated recursive units and cross-attention mechanisms; the sparse spatial feature extraction module can effectively extract key spatial structure information and enhance the model's understanding of complex scenes by efficiently encoding spatial features of point clouds; the multi-view feature fusion module can deeply integrate features from different perspectives and modalities, so that the railway scene point cloud segmentation network model can learn richer and more robust scene representations; the network structure is based on a symmetric framework, and through five downsampling and upsampling processes, multi-scale spatial features are extracted and fused, thereby enhancing the model's ability to process global context information and improving the model's feature extraction capability and segmentation efficiency; in summary, the railway scene point cloud segmentation network model proposed in the present invention improves the segmentation accuracy of railway scene point clouds in real environments, and effectively improves the current status of railway scene point cloud segmentation in real environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0070] Figure 1 A method flow chart of a railway scene point cloud segmentation method and system based on mutual attention provided by an embodiment of the present invention;

[0071] Figure 2An internal structure diagram of a computer device for a railway scene point cloud segmentation method and system based on mutual attention provided by an embodiment of the present invention;

[0072] Figure 3 A schematic diagram of global feature extraction of a railway scene point cloud segmentation method and system based on mutual attention provided by an embodiment of the present invention;

[0073] Figure 4 A multi-feature fusion flow chart of a railway scene point cloud segmentation method and system based on mutual attention is provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0074] In order to make the above-mentioned purposes, features and advantages of the present invention more understandable, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0075] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0076] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0077] Example 1

[0078] Reference Figure 1-Figure 4 , which is the first embodiment of the present invention, and provides a railway scene point cloud segmentation method based on mutual attention, comprising:

[0079] Before describing the embodiments of the present application in detail, some related concepts are first explained for the sake of clarity.

[0080] Voxelization: Voxelization is a process of converting 3D point cloud data into a voxel grid. Each voxel is a 3D cube that represents a small area in the point cloud. Through voxelization, dense point cloud data can be simplified into a more easily processed format while retaining important spatial information. Voxelization can reduce the number of point clouds, reduce computational complexity, and improve processing efficiency.

[0081] Bidirectional Recurrent Attention Module: The Bidirectional Recurrent Attention Module is a network module that combines the Bidirectional Gated Recurrent Unit (BiGRU) and the multi-head cross-attention mechanism. It processes point cloud sequence data in both forward and reverse directions to capture the spatial sequence dependencies in the point cloud. The multi-head cross-attention mechanism captures the features of different subspaces by processing multiple attention heads in parallel, thereby enhancing the expressiveness of features and the focus of the model.

[0082] Multi-head Cross Attention Mechanism: The multi-head cross attention mechanism is a variant of the attention mechanism. It captures the features of different subspaces by processing multiple attention heads in parallel. Each attention head can focus on different aspects of the point cloud data, thereby improving the expressiveness of the features. The multi-head cross attention mechanism can process multiple features at the same time and perform cross-attention, allowing different input features to be fused with each other and considering the correlation between the two.

[0083] Layer Normalization: Layer normalization is a regularization technique used to improve the training speed and stability of deep learning models. By normalizing the activation values ​​of each layer in the network, the internal covariate shift can be reduced, making the training process smoother and accelerating the convergence of the model. Layer normalization helps stabilize the training process and improve the generalization ability of the model.

[0084] Residual Connection: Residual connection is a technique used in deep neural networks. It forms a "shortcut" by adding the output of the previous layer directly to the output of the subsequent layer. This connection method can ensure the direct transmission of information and avoid the gradient vanishing problem. Especially in deep networks, residual connection helps to maintain the integrity of information flow and improve the training effect and performance of the model.

[0085] This application provides a method that can effectively solve the above-mentioned problems. Next, we will combine multiple embodiments to explain in detail how to implement the railway scene point cloud segmentation method based on mutual attention;

[0086] Figure 1 A method flow chart of a railway scene point cloud segmentation method and system based on mutual attention is shown, including:

[0087] S1: Use LiDAR to collect point cloud data of different railway track scenes;

[0088] Furthermore, the point cloud data of different railway track scenes are collected, including:

[0089] Use lidar to collect data for different orbital scenarios;

[0090] Perform format conversion, filtering and data annotation processing on the collected point cloud data;

[0091] The point cloud data after data annotation is used as the training and testing data set for the point cloud segmentation network.

[0092] S2: Build a railway scene point cloud segmentation network model based on mutual attention and point cloud serialization, and perform point cloud feature extraction;

[0093] Furthermore, the railway scene point cloud segmentation network model includes a point cloud preprocessing module, a point cloud feature extraction module and a point cloud feature reconstruction module.

[0094] Furthermore, the point cloud preprocessing module includes,

[0095] Voxelize the input point cloud to reduce the number of points and select an appropriate voxel size;

[0096] The voxelized point cloud is serialized to maintain the spatial proximity of the point cloud voxels.

[0097] Specifically, point cloud feature extraction includes:

[0098] The initial point cloud is used as the input of the point cloud network. The size of the input point cloud data is about 24000×4. After voxelization and serialization, a single actual input point cloud pc∈R8192×4 is finally obtained.

[0099] Use the bidirectional recursive attention module and the sparse spatial feature extraction module to extract features from a single actual input point cloud;

[0100] The extracted point cloud features are input into the multi-view feature fusion module, and feature fusion is performed. After downsampling, the layer-by-layer feature point cloud is obtained, as follows:

[0101] pc1∈R4096×32

[0102] pc2∈R2048×64

[0103] pc3∈R1024×128

[0104] pc4∈R512×256

[0105] pc5∈R256×256

[0106] Through residual connection, different feature point clouds are upsampled and feature adjusted respectively to obtain pc′ 1，2，3，4，5 ∈R8192×32;

[0107] The output point cloud feature pc is obtained through the fully connected layer out ∈R8192×4.

[0108] S3: Using the collected point cloud data as input, the railway scene point cloud segmentation network model is trained to obtain the trained model weights;

[0109] Furthermore, the point cloud feature extraction module includes a bidirectional recursive attention module, a sparse spatial feature extraction module, and a multi-view feature fusion module;

[0110] Specifically, the global feature extraction of the bidirectional recursive attention module includes:

[0111] Take serialized point cloud data as input;

[0112] Use bidirectional gated recurrent units to process serialized point cloud data and capture spatial sequence dependencies in the sequence;

[0113] Apply the multi-head cross attention mechanism to capture the features of different subspaces by processing multiple attention heads in parallel, thus improving the feature expression ability and the attention focus of the model;

[0114] After multi-head cross attention, normalization is performed, and the nonlinear processing capability of the network is increased through a multi-layer perceptron (MLP) to extract more complex features.

[0115] The multi-head cross attention, normalization and multi-layer perceptron operations are performed again to further enhance the expressiveness of the features;

[0116] Add the features after multiple processing and combine the information of each feature stream to make the final output of the model more comprehensive;

[0117] After the addition operation, a multi-head cross attention, normalization and multi-layer perceptron operation are performed to ensure the comprehensiveness and accuracy of the features;

[0118] Finally, the output features are obtained after being processed by the bidirectional recursive attention module.

[0119] Specifically, the multi-feature fusion process of the multi-view feature fusion module includes:

[0120] Receiving output features from the bidirectional recursive attention module and the sparse spatial feature extraction module;

[0121] A multi-head cross-attention mechanism is applied to the two input features respectively. Multiple attention heads are processed in parallel to capture the features of different subspaces and realize the interaction and fusion between features.

[0122] Normalize the features processed by multi-head cross attention, and then use a multi-layer perceptron to increase the nonlinear processing capability of the network and extract more complex features;

[0123] The normalized and multi-layer perceptron processed features are sent to another multi-layer perceptron for further processing, and then added to the original features to combine the information of each feature stream;

[0124] The features are passed to the next module or layer through residual connections to ensure the preservation and transmission of information flow and avoid the gradient disappearance problem;

[0125] After the above processing, the final result is obtained by integrating the output features of the bidirectional recursive attention module and the sparse spatial feature extraction module, which provides input for subsequent network layers.

[0126] Furthermore, the training of the railway scene point cloud segmentation network model includes:

[0127] Using bidirectional gated recurrent units to enhance the model’s understanding of sparse variations in point clouds;

[0128] Improve feature expression capabilities and capture subspace features through multi-head cross-attention mechanism;

[0129] Application layer normalization stabilizes training and accelerates convergence;

[0130] Use multi-layer perceptron to increase the nonlinear processing capability of the network;

[0131] Perform multi-layer perceptron and feature addition operations to ensure comprehensive representation of features.

[0132] S4: Apply the trained model weights and test the point cloud data of the railway scene to generate the segmentation results of the railway scene point cloud.

[0133] Furthermore, the segmentation results of the railway scene point cloud are generated, including:

[0134] Use the trained model weights to perform point cloud data segmentation tests on railway scenes;

[0135] Output and verify the accuracy of segmentation results and model performance;

[0136] The residual connection is combined to ensure the integrity of the information flow and the stability of the segmentation results.

[0137] Furthermore, the accuracy of the segmentation results and the model performance were verified, including:

[0138] The point cloud containing multi-scale segmentation features output by the railway scene point cloud segmentation network model is input into a fully connected layer, and finally the probability value of each point in the railway scene point cloud for each classification is obtained;

[0139] If the classification corresponding to the highest probability of a point is consistent with its actual classification, the prediction is considered correct;

[0140] The segmentation accuracy of the entire point cloud is calculated, that is, the ratio of correctly predicted points to the total number of points. At the same time, the segmentation intersection-union ratio is calculated, which is determined by comparing the ratio of the correctly predicted points to the actual number of points in the point cloud and the union of the prediction results.

[0141] Furthermore, the present embodiment also provides a railway scene point cloud segmentation system based on mutual attention, comprising: a data acquisition module, a model construction module, a model training module and a model verification module;

[0142] The data acquisition module is used to collect point cloud data of different railway track scenes using laser radar;

[0143] The model building module is used to build a railway scene point cloud segmentation network model based on mutual attention and point cloud serialization, and perform point cloud feature extraction;

[0144] The model training module is used to perform model training on the railway scene point cloud segmentation network model according to the point cloud data to obtain the trained model weight;

[0145] The model verification module is used to apply the trained model weights and perform model testing based on the point cloud data to generate a segmentation result of the railway scene point cloud.

[0146] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 2As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a comprehensive evaluation method suitable for orderly access of large-scale distributed power sources is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0147] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented: using a laser radar to collect point cloud data of different railway track scenes;

[0148] Build a railway scene point cloud segmentation network model based on mutual attention and point cloud serialization, and perform point cloud feature extraction;

[0149] Performing model training on the railway scene point cloud segmentation network model according to the point cloud data to obtain a trained model weight;

[0150] The trained model weights are applied, and a model test is performed based on the point cloud data to generate a segmentation result of the railway scene point cloud.

[0151] Example 2

[0152] Reference Figure 1 , which is the second embodiment of the present invention, and this embodiment provides a railway scene point cloud segmentation method based on mutual attention. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0153] This example aims to verify the effectiveness of the railway scene point cloud segmentation method based on mutual attention and point cloud serialization. The experiment selected three typical track scenes (such as single track, double track and elevated track) of a certain railway section for data collection to ensure the richness of data under different environments and conditions. The data was collected using a laser radar device, and each scene was measured continuously for three days. The scanning frequency of the laser radar was set to 10Hz, and the amount of point cloud data collected was approximately 24,000 points per scan. The collected point cloud data was then format converted, filtered and annotated to ensure data quality and accuracy.

[0154] The processed point cloud data are used as training sets and test sets respectively. The constructed railway scene point cloud segmentation network model includes a point cloud preprocessing module, a feature extraction module and a feature reconstruction module. The point cloud preprocessing module uses voxelization to reduce the data volume to 40% of the original data to ensure the efficiency of the network input; the voxel size is selected as 0.1m to balance accuracy and computational efficiency. The feature extraction module uses a bidirectional recursive attention mechanism to extract features, capture the spatial relationship between point clouds, and finally generate a vector representation with a feature dimension of 128. Then, through the multi-view feature fusion module, feature information from different angles is combined to achieve a more comprehensive feature representation.

[0155] In order to evaluate the performance of the model, segmentation accuracy and intersection-over-union ratio were selected as evaluation indicators. In the model training phase, the Adam optimizer was used, the learning rate was set to 0.001, and the number of training iterations was 50. In the testing phase, the trained model was used to segment the newly collected point cloud data and compared with the actual annotation results to ensure the objectivity and accuracy of the verification.

[0156] Table 1: Railway scene point cloud data collection and processing

[0157]

[0158] Table 2: Performance comparison of railway scene point cloud segmentation models

[0159]

[0160] As can be seen from Table 1, for three different railway scenes, after the point cloud data collection and processing of the LiDAR, the final segmentation accuracy is above 90%, among which the accuracy of the elevated track scene reaches 93.1%. These data show that the method of the present invention improves the data quality and the learning effect of the model by adopting advanced voxelization and serialization processing during data processing and feature extraction, thereby improving the accuracy of segmentation.

[0161] In the comparison in Table 2, there is a significant performance difference between the basic model and the model of the present invention. The segmentation accuracy of the basic model is only 85.0%, and the intersection-over-union ratio is 75.0%. The segmentation accuracy of the model of the present invention is increased to 92.5%, and the intersection-over-union ratio is increased to 80.5%. The training time is slightly increased but the test time is significantly shortened, indicating that the efficiency and performance of the model of the present invention have reached an optimized balance in the training stage. This improvement not only reflects the enhancement of the model's feature extraction capabilities, but more importantly, through the bidirectional recursive attention mechanism and multi-view feature fusion, it ensures the effective interaction and integration between features in different subspaces, thereby enhancing the generalization ability of the model.

[0162] The present invention proposes a new point cloud segmentation neural network, which uses a long-distance sparse point cloud that is more suitable for railway scenes as input to extract features from the input point cloud, and obtains the feature dependency relationship between the long-distance sparse point clouds; and performs a multi-view feature fusion based on multi-head cross-attention, and performs attention-weighted complementary enhancement to achieve effective integration of local features and global features; while improving the overall feature extraction capability of the network model, it introduces the special structural information of the railway scene as fully as possible, thereby improving the feature extraction capability and segmentation efficiency of the model.

[0163] In summary, the data and analysis results in this embodiment fully verify the effectiveness and innovation of the railway scene point cloud segmentation method based on mutual attention and point cloud serialization. Compared with the existing technology, it has higher segmentation accuracy and better processing performance, demonstrating the significant advantages of the present invention in practical applications.

[0164] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0165] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0166] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0167] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0168] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0169] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0170] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A railway scene point cloud segmentation method based on mutual attention, characterized by: include, Use LiDAR to collect point cloud data of different railway track scenes; Build a railway scene point cloud segmentation network model based on mutual attention and point cloud serialization, and perform point cloud feature extraction; Performing model training on the railway scene point cloud segmentation network model according to the point cloud data to obtain a trained model weight; The trained model weights are applied, and a model test is performed based on the point cloud data to generate a segmentation result of the railway scene point cloud.

2. The railway scene point cloud segmentation method based on mutual attention according to claim 1, characterized in that: The point cloud data collected for different railway track scenes includes: Use lidar to collect data for different orbital scenarios; Perform format conversion, filtering and data annotation processing on the collected point cloud data; The point cloud data after data annotation is used as the training and testing data set for the point cloud segmentation network.

3. The railway scene point cloud segmentation method based on mutual attention according to claim 1, characterized in that: The railway scene point cloud segmentation network model includes a point cloud preprocessing module, a point cloud feature extraction module and a point cloud feature reconstruction module; The point cloud preprocessing module includes: Voxelize the input point cloud to reduce the number of points and select an appropriate voxel size; Serialize the voxelized point cloud to maintain the spatial proximity of the point cloud voxels; The point cloud feature extraction module includes a bidirectional recursive attention module, a sparse spatial feature extraction module and a multi-view feature fusion module; The point cloud feature extraction module includes: Use the bidirectional recursive attention module and the sparse spatial feature extraction module to extract features from a single actual input point cloud; The extracted point cloud features are input into the multi-view feature fusion module, and feature fusion is performed. After downsampling, the layer-by-layer feature point cloud is obtained, as follows: pc1∈R4096×32 pc2∈R2048×64 pc3∈R1024×128 pc4∈R512×256 pc5∈R256×256 Through residual connection, different feature point clouds are upsampled and feature adjusted respectively to obtain pc′ 1，2，3，4，5 ∈R8192×32; The output point cloud feature pc is obtained through the fully connected layer out ∈R8192×4.

4. The railway scene point cloud segmentation method based on mutual attention as claimed in claim 3, characterized in that: The global feature extraction of the bidirectional recursive attention module includes, Take serialized point cloud data as input; Use bidirectional gated recurrent units to process serialized point cloud data and capture spatial sequence dependencies in the sequence; Apply a multi-head cross-attention mechanism to capture the features of different subspaces by processing multiple attention heads in parallel; After multi-head cross attention, normalization is performed and features are extracted through a multi-layer perceptron; Perform multi-head cross attention, normalization and multi-layer perceptron operations again; Add the features after multiple processing; After the addition operation, multi-head cross attention, normalization and multi-layer perceptron operations are performed again to obtain the processed output features.

5. The railway scene point cloud segmentation method based on mutual attention as claimed in claim 3, characterized in that: The multi-feature fusion process of the multi-view feature fusion module includes: Receiving output features from the bidirectional recursive attention module and the sparse spatial feature extraction module; A multi-head cross-attention mechanism is applied to the two input features respectively, capturing features of different subspaces by processing multiple attention heads in parallel; Normalize the features processed by multi-head cross attention, and then extract features again through multi-layer perceptron; The normalized and multi-layer perceptron processed features are sent to another multi-layer perceptron for further processing and then added to the original features; Pass the features to the next module or layer through residual connections; After the above processing, the final result is obtained, which combines the output features of the bidirectional recursive attention module and the sparse spatial feature extraction module.

6. The railway scene point cloud segmentation method based on mutual attention according to claim 1, characterized in that: The training of the railway scene point cloud segmentation network model includes: Using bidirectional gated recurrent units to enhance the model’s understanding of sparse variations in point clouds; Improve feature expression capabilities and capture subspace features through multi-head cross-attention mechanism; Apply layer normalization operations for training and accelerating convergence; Use a multi-layer perceptron to perform addition operations on features.

7. The railway scene point cloud segmentation method based on mutual attention as claimed in claim 1, characterized in that: The segmentation result of generating the railway scene point cloud includes: Use the trained model weights to perform point cloud data segmentation tests on railway scenes; Output and verify the accuracy of segmentation results and model performance; The accuracy of the segmentation results and the model performance are verified as follows: The point cloud containing multi-scale segmentation features output by the railway scene point cloud segmentation network model is input into a fully connected layer to obtain the probability value of each point in the railway scene point cloud for each classification; If the classification corresponding to the highest probability of a point is consistent with the actual classification, the prediction is considered correct; The segmentation accuracy of the entire point cloud is calculated by the ratio of the number of correctly predicted points to the total number of points, and the segmentation intersection-union ratio is calculated by comparing the ratio of the number of correctly predicted points to the actual number of points in the point cloud and the union of the prediction results.

8. A railway scene point cloud segmentation system based on mutual attention, based on the railway scene point cloud segmentation method based on mutual attention according to any one of claims 1 to 7, characterized in that: It includes data collection module, model building module, model training module and model verification module; The data acquisition module is used to collect point cloud data of different railway track scenes using laser radar; The model building module is used to build a railway scene point cloud segmentation network model based on mutual attention and point cloud serialization, and perform point cloud feature extraction; The model training module is used to perform model training on the railway scene point cloud segmentation network model according to the point cloud data to obtain the trained model weight; The model verification module is used to apply the trained model weights and perform model testing based on the point cloud data to generate a segmentation result of the railway scene point cloud.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the railway scene point cloud segmentation method based on mutual attention are implemented in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the railway scene point cloud segmentation method based on mutual attention according to any one of claims 1 to 7 are implemented.

Images