Point Cloud Segmentation Research Articles

Filtering-Assisted Airborne Point Cloud Semantic Segmentation for Transmission Lines

Point cloud semantic segmentation is crucial for identifying and analyzing transmission lines. Due to the number of point clouds being huge, complex scenes, and unbalanced sample proportion, the mainstream machine learning methods of point cloud segmentation cannot provide high efficiency and accuracy when extending to transmission line scenes. This paper proposes a filter-assisted airborne point cloud semantic segmentation for transmission lines. First, a large number of ground point clouds is identified by introducing the well-developed cloth simulation filter to alleviate the impact of the imbalance of the target object proportion on the classifier’s performance. The multi-dimensional features are then defined, and the classification model is trained to achieve the multi-element semantic segmentation of the transmission line scene. The experimental results and analysis indicate that the proposed filter-assisted algorithm can significantly improve the semantic segmentation performance of the transmission line point cloud, enhancing both the point cloud segmentation efficiency and accuracy by more than 25.46% and 3.15%, respectively. The filter-assisted point cloud semantic segmentation method reduces the volume of sample data, the number of sample classes, and the sample imbalance index in power line scenarios to a certain extent, thereby improving the classification accuracy of classifiers and reducing time consumption. This research holds significant theoretical reference value and engineering application potential for scene reconstruction and intelligent understanding of airborne laser point cloud transmission lines.

Multi-Modal LiDAR Point Cloud Semantic Segmentation with Salience Refinement and Boundary Perception

Point cloud segmentation is essential for scene understanding, which provides advanced information for many applications, such as autonomous driving, robots, and virtual reality. To improve the accuracy and robustness of point cloud segmentation, many researchers have attempted to fuze camera images to complement the color and texture information. The common fusion strategy is the combination of convolutional operations with concatenation, element-wise addition or element-wise multiplication. However, conventional convolutional operators tend to confine the fusion of modal features within their receptive fields, which can be incomplete and limited. In addition, the inability of encoder–decoder segmentation networks to explicitly perceive segmentation boundary information results in semantic ambiguity and classification errors at object edges. These errors are further amplified in point cloud segmentation tasks, significantly affecting the accuracy of point cloud segmentation. To address the above issues, we propose a novel self-attention multi-modal fusion semantic segmentation network for point cloud semantic segmentation. Firstly, to effectively fuze different modal features, we propose a self-cross fusion module (SCF), which models long-range modality dependencies and transfers complementary image information to the point cloud to fully leverage the modality-specific advantages. Secondly, we design the salience refinement module (SR), which calculates the importance of channels in the feature maps and global descriptors to enhance the representation capability of salient modal features. Finally, we propose the local-aware anisotropy loss measure the element-level importance in the data and explicitly provide boundary information for the model, which alleviates the inherent semantic ambiguity problem in segmentation networks. Extensive experiments on two benchmark datasets demonstrate that our proposed method surpasses current state-of-the-art methods.

Arch dam point cloud segmentation based on deep feature learning and normal vector data optimization

Separating the dam body, spillway, and other structures from the point cloud in the dam area is an important step in dam deformation monitoring. Manual segmentation is time consuming and inaccurate. This study proposes a point cloud segmentation neural network model based on normal vector optimization suitable for dam environment: (1) This model utilizes the voxel uniform sampling method of equal length cubes to solve the problem of uneven point cloud density caused by wide range and long-distance measurement during point cloud measurement in dam areas. (2) Designed block input and combined output modules in the model, achieving efficient input of large volume point cloud and eliminating the impact of interpolation points offset during seq2seq model decoding process. (3) In response to the diverse characteristics of point cloud normal vectors presented by vegetation, rock mass, and complex dam structures in the dam area, this paper proposes an adaptive radius plane fitting vector estimation method based on eigenvalue method to improve the accuracy of segmentation. The experiment on the prototype arch dam shows that the proposed normal estimation method improves the classification accuracy of PointNet + + from 96.26 to 98.27%. Compared with the other three normal estimation methods (2-jets, Hough CNN, iterative PCA), the overall accuracy is improved by 0.82%, 1.22%, and 0.22%, and the joint average intersection is improved by 0.0293, 0.0325, and 0.0104. The prototype arch dam experiment shows that our proposed method has a segmentation accuracy of 98.27%. Compared with 2-jets, Hough CNN, and iterative PCA, the overall accuracy has been improved by 0.82%, 1.22%, and 0.22%. This study provides a high-precision segmentation scheme for applications such as deformation detection of dam components based on point clouds.

Real-Time Semantic Segmentation of 3D LiDAR Point Clouds for Aircraft Engine Detection in Autonomous Jetbridge Operations

This paper presents a study on aircraft engine identification using real-time 3D LiDAR point cloud segmentation technology, a key element for the development of automated docking systems in airport boarding facilities, known as jetbridges. To achieve this, 3D LiDAR sensors utilizing a spinning method were employed to gather surrounding environmental 3D point cloud data. The raw 3D environmental data were then filtered using the 3D RANSAC technique, excluding ground data and irrelevant apron areas. Segmentation was subsequently conducted based on the filtered data, focusing on aircraft sections. For the segmented aircraft engine parts, the centroid of the grouped data was computed to determine the 3D position of the aircraft engine. Additionally, PointNet was applied to identify aircraft engines from the segmented data. Dynamic tests were conducted in various weather and environmental conditions, evaluating the detection performance across different jetbridge movement speeds and object-to-object distances. The study achieved a mean intersection over union (mIoU) of 81.25% in detecting aircraft engines, despite experiencing challenging conditions such as low-frequency vibrations and changes in the field of view during jetbridge maneuvers. This research provides a strong foundation for enhancing the robustness of jetbridge autonomous docking systems by reducing the sensor noise and distortion in real-time applications. Our future research will focus on optimizing sensor configurations, especially in environments where sea fog, snow, and rain are frequent, by combining RGB image data with 3D LiDAR information. The ultimate goal is to further improve the system’s reliability and efficiency, not only in jetbridge operations but also in broader autonomous vehicle and robotics applications, where precision and reliability are critical. The methodologies and findings of this study hold the potential to significantly advance the development of autonomous technologies across various industrial sectors.

Point cloud segmentation method based on an image mask and its application verification

Abstract Accurately perceiving three-dimensional (3D) environments or objects is crucial for the advancement of artificial intelligence (AI) interaction technologies. Currently, various types of sensors are employed to obtain point cloud data for 3D object detection or segmentation tasks. While this multi-sensor approach provides more precise 3D data than monocular or stereo cameras, it is also more expensive. The advent of RGB-D cameras, which provide both RGB images and depth information, addresses this issue.
In this study, we propose a point cloud segmentation method based on image masks. By using an RGB-D camera to capture color and depth images, we generate image masks through object recognition and segmentation. Given the mapping relationship between RGB image pixels and point clouds, these image masks can be further used to extract the point cloud data of the target objects. The experimental results revealed that the average accuracy of target segmentation was 84.78%, which was close to that of PointNet++. Compared with three traditional segmentation algorithms, the accuracy was improved by nearly 23.97%. The running time of our algorithm is reduced by 95.76% compared to the PointNet++ algorithm, which has the longest running time; and by 15.65% compared to the LCCP algorithm, which has the shortest running time among traditional methods. Compared with PointNet++, the segmentation accuracy was improved. This method addressed the issues of low robustness and excessive reliance on manual feature extraction in traditional point cloud segmentation methods, providing valuable support and reference for the accurate segmentation of 3D point clouds.

Maize Phenotypic Parameters Based on the Constrained Region Point Cloud Phenotyping Algorithm as a Developed Method

As one of the world’s most crucial food crops, maize plays a pivotal role in ensuring food security and driving economic growth. The diversification of maize variety breeding is significantly enhancing the cumulative benefits in these areas. Precise measurement of phenotypic data is pivotal for the selection and breeding of maize varieties in cultivation and production. However, in outdoor environments, conventional phenotyping methods, including point cloud processing techniques based on region growing algorithms and clustering segmentation, encounter significant challenges due to the low density and frequent loss of point cloud data. These issues substantially compromise measurement accuracy and computational efficiency. Consequently, this paper introduces a Constrained Region Point Cloud Phenotyping (CRPCP) algorithm that proficiently detects the phenotypic traits of multiple maize plants in sparse outdoor point cloud data. The CRPCP algorithm consists primarily of three core components: (1) a constrained region growth algorithm for effective segmentation of maize stem point clouds in complex backgrounds; (2) a radial basis interpolation technique to bridge gaps in point cloud data caused by environmental factors; and (3) a multi-level parallel decomposition strategy leveraging scene blocking and plant instances to enable high-throughput real-time computation. The results demonstrate that the CRPCP algorithm achieves a segmentation accuracy of 96.2%. When assessing maize plant height, the algorithm demonstrated a strong correlation with manual measurements, evidenced by a coefficient of determination R2 of 0.9534, a root mean square error (RMSE) of 0.4835 cm, and a mean absolute error (MAE) of 0.383 cm. In evaluating the diameter at breast height (DBH) of the plants, the algorithm yielded an R2 of 0.9407, an RMSE of 0.0368 cm, and an MAE of 0.031 cm. Compared to the PointNet point cloud segmentation method, the CRPCP algorithm reduced segmentation time by more than 44.7%. The CRPCP algorithm proposed in this paper enables efficient segmentation and precise phenotypic measurement of low-density maize multi-plant point cloud data in outdoor environments. This algorithm offers an automated, high-precision, and highly efficient solution for large-scale field phenotypic analysis, with broad applicability in precision breeding, agronomic management, and yield prediction.

EIDU-Net: edge-preserved inception DenseGCN U-Net for LiDAR point cloud segmentation

With the development of laser scanners and machine learning, point cloud semantic segmentation plays a significant role in autonomous driving, scene reconstruction, human-computer interaction, and other fields. In recent years, point cloud semantic segmentation based on deep learning has become one of the key research directions in point cloud processing. Due to the limited ability to exploit geometric details and contextual information in point clouds, most methods that adopt encoder-decoder architecture lose local structural information easily, especially detailed features, and extract features insufficiently. To address this issue, the edge-preserving inception DenseGCN U-Net (entitled as EIDU-Net) is proposed. EIDU-Net makes full use of the complementation between geometric details in the original point cloud and high-level features. The edge-preserved graph pooling (EGP) layer, the key module of the EIDU-Net, is designed to retain additional edge feature information from the original point cloud during pooling operations. Accordingly, the edge-preserved graph unpooling (EGU) layer can restore the feature graph more efficiently based on the additionally retained edge features. Extensive experiments demonstrate that our proposed EIDU-Net has remarkable improvements on semantic segmentation tasks under whatever S3DIS or Terracotta Warrior fragments. Our code is publicly available at https://github.com/caoxin918/EIDU-Net.

A point cloud segmentation algorithm based on multi-feature training and weighted random forest

Abstract Point cloud segmentation is the process of dividing point cloud data into a series of coherent subsets according to its attributes. It has been widely used in target recognition, digital protection of cultural relics, medical research and other fields. To improve the classification accuracy of point cloud and achieve accurate segmentation of objects or scenes, a point cloud segmentation algorithm based on multi–features training and weighted random forest (RF) is proposed. Firstly, the feature vector composed of 3D coordinate value, RGB value, echo intensity, point cloud density, normal direction and average curvature is used to train the SVM classifier, and the ‘one–to–one’ strategy is adopted to achieve the initial multivariate rough segmentation of point cloud. Then, the maximum information coefficient and sample correlation coefficient (SCC) are used to evaluate the correlation of the decision tree, and the decision tree is weighted accordingly to build a weak correlation weighted RF, so as to achieve further accurate segmentation of the point cloud. The experiment verifies the effectiveness of the proposed algorithm by segmenting the outdoor scene point cloud data model. The results show that the segmentation algorithm based on multi–features training and weighted RF can achieve accurate point cloud segmentation, and is an effective point cloud segmentation method.

Stone instance segmentation of rubble masonry based on laser scanning point clouds

Laser scanning allows for objective area-based analysis of water dam structures to enable targeted interventions in case of displacements, requiring comparison of the same areas over different epochs. This comparison improves if identical areas, e.g. stones, from multiple epochs can be automatically derived in advance. We present an instance segmentation algorithm based on a 3D point cloud with reflected intensity information to identify individual stones in rubble masonry dams that can be used within deformation monitoring. The algorithm uses initial k-means classification followed by image-based processing steps, resulting in a segmented 3D point cloud with individual stones. It is evaluated against a manually labeled reference and analyzed on terrestrial laser scanning (TLS) and UAV-based data sets. Correctly identified stones are 89.92% for TLS and 90.82% for UAV data. Additionally, stone centroids and shapes were evaluated without significant deviation. A first outlook on deformation analysis was provided using ICP matching of stones from two simulated epochs.

HBIM MODELLING PROCESS FROM 3D POINT CLOUDS BY APPLYING ARTIFICIAL INTELLIGENCE ALGORITHMS IN CULTURAL HERITAGE

In the context of Cultural Heritage (CH), the widespread adoption of 3D point cloud technology, coupled with Artificial Intelligence (AI) algorithms, plays a pivotal role. These technologies facilitate the creation of as-built models by integrating Building Information Modelling (BIM) strategies, enhancing collaboration within the Architecture, Engineering, and Construction (AEC) sector. Leveraging computer vision, robotics, and remote sensing, 3D points clouds provide rich data. However, manual segmentation and classification are labor-intensive and error prone. Consequently, researchers increasingly turn to machine learning (ML) and deep learning (DL) techniques for automating these tasks. The transition from manual reconstruction to automated procedures is crucial. Despite progress, gaps remain, particularly in incorporating 3D point cloud segmentation into Historical Building Information Modelling (HBIM). The lack of conclusive evidence regarding automated derivation of parametric attributes from segmentation outcomes underscores the need for further exploration. Addressing this gap is essential for cultural asset documentation, conservation, and upkeep. By automating the segmentation and classification of 3D point clouds, efficient communication via a shared database becomes feasible. The article aims to review studies on semantically parsing and classifying 3D point clouds using AI algorithms, particularly within complex cultural heritage geometries, shedding light on potential benefits and barriers.

ML Approaches for the Study of Significant Heritage Contexts: An Application on Coastal Landscapes in Sardinia

Remote Sensing (RS) and Geographic Information Science (GIS) techniques are powerful tools for spatial data collection, analysis, management, and digitization within cultural heritage frameworks. Despite their capabilities, challenges remain in automating data semantic classification for conservation purposes. To address this, leveraging airborne Light Detection And Ranging (LiDAR) point clouds, complex spatial analyses, and automated data structuring is crucial for supporting heritage preservation and knowledge processes. In this context, the present contribution investigates the latest Artificial Intelligence (AI) technologies for automating existing LiDAR data structuring, focusing on the case study of Sardinia coastlines. Moreover, the study preliminary addresses automation challenges in the perspective of historical defensive landscapes mapping. Since historical defensive architectures and landscapes are characterized by several challenging complexities—including their association with dark periods in recent history and chronological stratification—their digitization and preservation are highly multidisciplinary issues. This research aims to improve data structuring automation in these large heritage contexts with a multiscale approach by applying Machine Learning (ML) techniques to low-scale 3D Airborne Laser Scanning (ALS) point clouds. The study thus develops a predictive Deep Learning Model (DLM) for the semantic segmentation of sparse point clouds (<10 pts/m2), adaptable to large landscape heritage contexts and heterogeneous data scales. Additionally, a preliminary investigation into object-detection methods has been conducted to map specific fortification artifacts efficiently.

Deep learning network for indoor point cloud semantic segmentation with transferability

Semantic segmentation is crucial for interpreting point cloud data and plays a fundamental role in automating the creation of as-built BIM. Existing neural network models for semantic segmentation often heavily rely on the training dataset, resulting in a significant performance drop when applied to new datasets. This paper presents AttTransNet, a neural network model for automated point cloud semantic segmentation. Its attention-based pooling module improves local feature extraction from point clouds while reducing computational costs. The transfer learning framework enhances segmentation accuracy with minimal training on target datasets. Comparative experiments show that AttTransNet reduces training time by 80 % and improves segmentation accuracy by over 20 % compared with other SOTA methods. Cross-dataset experiments reveal that the transfer learning framework increases accuracy on new datasets by 150 %. By adding semantic information to point clouds, AttTransNet aids BIM modelers with direct reference, encouraging broader application of automated point cloud segmentation in the industry.

RS-SLAM: real time semantic slam with driverless car using LiDAR-camera-IMU sensing

Abstract Accurate and robust Simultaneous Localization and Mapping (SLAM) technology is a critical component of driverless cars, and semantic information plays a vital role in their analysis and understanding of the scene. In the actual scene, the moving object will produce the shadow phenomenon in the mapping process. The positioning accuracy and mapping effect will be affected. Therefore, we propose a semantic SLAM framework combining LiDAR, IMU, and camera, which includes a semantic fusion front-end odometry module and a closed-loop back-end optimization module based on semantic information. An improved image semantic segmentation algorithm based on Deeplabv3+ is designed to enhance the performance of the image semantic segmentation model by replacing the backbone network and introducing an attention mechanism to ensure the accuracy of point cloud segmentation. Dynamic objects are detected and eliminated by calculating the similarity score of semantic labels. A loop closure detection method based on semantic information is proposed to detect key semantic features and use threshold range detection and point cloud re-matching to establish the correct loop closure detection, and finally reduce the global cumulative error and improve the global trajectory accuracy using graph optimization to ultimately obtain the global motion trajectory and realize the construction of 3D semantic maps. We evaluated it on the KITTI dataset and collected a dataset for evaluation by ourselves, which includes four different sequences. The results show that the proposed framework has good positioning accuracy and mapping effect in large-scale urban road environments.

Enhancing BDS-3 PPP-B2b real-time positioning performance by tightly integrating MEMS IMU and LiDAR in GNSS-Degraded environment

Currently, BDS-3 can provide satellite-based real-time precise point positioning (PPP) service via its PPP-B2b signal. However, in a complex Global Navigation Satellite System (GNSS)-degraded environment, the BDS-3 PPP-B2b positioning performance is severely influenced. A tightly coupled PPP/microelectromechanical system inertial measurement unit (MEMS IMU)/Light Detection and Ranging (LiDAR) combination is proposed, in which the original pseudorange and carrier observations, IMU measurements, and LiDAR planar features are fused via an extended Multi-State Constraint Kalman Filter (MSCKF). Moreover, the Galileo satellites are further utilized using the broadcast ephemerides to increase the number of available satellites. And to improve the real-time computing efficiency, a planar feature tracking model based on ground segmentation is adopted. The model consists of point cloud segmentation, planar feature extraction and fusion, and data correlation. To evaluate the effectiveness of the proposed method, the experiment is conducted at both a campus and a park. The result shows that approximately sub-meter-level positioning accuracy can be achieved using tightly coupled BDS-3 PPP-B2b, IMU, and LiDAR, while the positioning errors of BDS-3 PPP-B2b and BDS-3 PPP-B2b/IMU are both larger than 5 m. Furthermore, the MEMS IMU and LiDAR measurements show the capability of bridging the gaps in the GNSS data, which enables continuous and stable positioning. Moreover, compared to the state-of-the-art A-LOAM, LEGO-LOAM, and LIO-SAM frameworks, absolute trajectory errors of less than 1.0 and 2.5 m are achieved in the campus and park, respectively, using the proposed algorithm, with improvements of more than 3.40 and 1.58 times.

Multi-channel depth segmentation network based on 3D graph convolution algorithm and its application in point cloud segmentation

At the current stage, 3D graph convolutional algorithms face the following issues: (1) The problem of determining the neighborhood in graph convolution. (2) The issue of fusing features at different depths in deep graph convolutional algorithms. (3) The challenge of feature fusion and recognition in multi-path deep graph convolutional algorithms. Based on these, the paper "Multi-Path Deep Segmentation Network Based on 3D Graph Convolutional Algorithm and Its Application in Point Cloud Segmentation" is proposed. Inspired by visual computing theory, the neighborhood for 3D graph convolution is determined based on the receptive field theory, and a 3D graph convolutional algorithm based on visual selectivity is proposed; A single-link deep feature extraction algorithm for 3D graph convolution based on visual selectivity is proposed, it achieve the fusion of features at different depths learned by the graph convolutional algorithm by a pyramid learning method; A multi-link feature extraction algorithm for 3D graph convolution based on visual selectivity is proposed, and achieve multi-link feature fusion and segmentation to utilize the RPN calculation method. compared with algorithms such as PointNet, PointNet++, KPConv deform, 3D GCN, and My Algorithm, The segmentation performance and geometric invariance of the proposed algorithm are validated on the ShapeNetPart dataset and the custom Mortise_and_Tenon_DB dataset, and Experiments demonstrate that the proposed algorithm is correct and feasible, offers superior 3D point cloud segmentation performance, and exhibits strong geometric invariance.

Seabed Segmentation of Airborne Bathymetric Light Detection and Ranging Point Cloud Using Window-based Attention and Orthogonal Regularized PointNet

Seabed Segmentation of Airborne Bathymetric Light Detection and Ranging Point Cloud Using Window-based Attention and Orthogonal Regularized PointNet

Field-grown tomato yield estimation using point cloud segmentation with 3D shaping and RGB pictures from a field robot and digital single lens reflex cameras

The aim of this study was to estimate field-grown tomato yield (weight) and quantity of tomatoes using a self-developed robot and digital single lens reflex (DSLR) camera pictures. The authors suggest a new approach to predicting tomato yield that is based on images taken in the field, 3D scanning, and shape. Field pictures were used for tomato segmentation to determine the ripeness of the crop. A convolution neural network (CNN) model using TensorFlow library was devised for the segmentation of tomato berries along with a small robot, which had a 59.3 % F1 score. To enhance the accurate tomato crop model and to estimate the yield later, point cloud imaging was applied using a Ciclops 3D scanner. The best fitting sphere model was generated using the 3D model. The most optimal model was the 3D model, which gave the best representation and provided the weight of the tomatoes with a relative error of 21.90 % and a standard deviation of 17.9665 %. The results indicate a consistent object-based classification of the tomato crop above the plant/row level with an accuracy of 55.33 %, which is better than in-row sampling (images taken by the robot). By comparing the measured and estimated yield, the average difference for DSLR camera images was more favorable at 3.42 kg.

3D Point Cloud Semantic Segmentation based on Multi-scale Dense Nested Networks

Aiming at the problem that the relationship between geometric features and semantic features is ignored in the point cloud data downsampling process, which leads to inaccurate segmentation of object boundaries and structural details, this paper proposes a 3D point cloud semantic segmentation network based on multi-scale dense nested type. Firstly, a dense nested network architecture is constructed by nesting multiple multi-scale feature fusion modules to fuse multi-scale features of different directions between encoder-decoder paths, so as to effectively propagate local ge-ometric context information and enhance the ability of cross-scale information interaction. Secondly, a local feature aggregation unit is constructed in the multi-scale feature fusion module, which strengthens the structural awareness within the local point set based on graph convolution and attention mechanism, and promotes the complementarity of local geometric features and abstract semantic information. Then, the cross-layer multi-loss supervision module is combined to further optimize the multi-scale feature propagation, which makes the network training more stable and improves the point cloud segmentation accuracy. Finally, this paper verified the proposed network on the S3DIS dataset. The experimental results show that the proposed network has the mean intersection over Union of 71.2% and the overall accuracy of 88.7%, which is 1.2 and 0.7 percentage points higher than RandLA-Net, respectively, which proves that the proposed network can effectively improve the accuracy of 3D point cloud semantic segmentation.

Automated recognition and rebar dimensional assessment of prefabricated bridge components from low-cost 3D laser scanner

Dimension quality inspections for rebar spacing and length of prefabricated bridge components are critical for subsequent efficient assembly on-site. Currently, the traditional manual inspection method is time-consuming, labor-intensive, and error-prone. The existing commercial 3D LiDAR-based methods are difficult in making balances between inspection cost, efficiency, and accuracy. Thus, the automated recognition and segmentation method of 3D point clouds acquired by a self-developed low-cost LiDAR is proposed to evaluate the rebar spacing and length of bridge prefabricated components. Due to the high-cost commercial 3D laser scanner, a spinning 2D LiDAR-based low-cost 3D laser scanner device and geometric calibration model were developed to acquire the 3D spatial point cloud. Then, two-stage automated point cloud segmentation framework is proposed with coarse extraction of the point cloud in the interest region and fine recognition of point cloud using machine learning methods, including plane segmentation and circle fitting employing random sample consensus (RANSAC) algorithm, and rebars segmentation utilizing Gaussian mixture model (GMM) and density-based spatial clustering of applications with noise (DBSCAN) algorithm. The proposed system was evaluated in two prefabricated concrete columns and shows the potential for improving the quality inspection efficiency and accuracy.

An end-to-end radar pulse deinterleaving structure based on point cloud mapping

Radar pulse deinterleaving is a critical technology of electronic reconnaissance equipment. This paper proposes an end-to-end radar pulses deinterleaving structure based on point cloud mapping. The core idea is mapping radar pulse description word (PDW) to a point cloud for mimetic vision, which converts the radar pulse deinterleaving task into a point cloud segmentation task. This structure is characterized by lightweight and strong generalization compared to the image segmentation-based deinterleaving structure. Then this paper proposes a multi-stage graph convolution network (MSGCN) based on graph convolution for point cloud segmentation, which utilises the message passing mechanism of the graph structure to effectively extract, pass and fuse the features of different pulses, thus achieving better segmentation performance. The simulation experimental results show that the proposed method can effectively realize the deinterleaving of densely interleaved and overlapped pulses, and the method has an excellent robustness in pulse missing and spurious pulse interference scenarios.