Cloth Simulation Research Articles

Inverse Garment and Pattern Modeling with a Differentiable Simulator

AbstractThe capability to generate simulation‐ready garment models from 3D shapes of clothed people will significantly enhance the interpretability of captured geometry of real garments, as well as their faithful reproduction in the digital world. This will have notable impact on fields like shape capture in social VR, and virtual try‐on in the fashion industry. To align with the garment modeling process standardized by the fashion industry and cloth simulation software, it is required to recover 2D patterns, which are then placed around the wearer's body model and seamed prior to the draping simulation. This involves an inverse garment design problem, which is the focus of our work here: Starting with an arbitrary target garment geometry, our system estimates its animatable replica along with its corresponding 2D pattern. Built upon a differentiable cloth simulator, it runs an optimization process that is directed towards minimizing the deviation of the simulated garment shape from the target geometry, while maintaining desirable properties such as left‐to‐right symmetry. Experimental results on various real‐world and synthetic data show that our method outperforms state‐of‐the‐art methods in producing both high‐quality garment models and accurate 2D patterns.

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.

UAV-MSSH: A novel UAV photogrammetry-based framework for mining surface three-dimensional movement basin monitoring

Monitoring the surface three-dimensional movement caused by underground coal mining is a critical and challenging task. Despite many methods have been proposed in previous works, they focus more on the subsidence, with insufficient discussions on the horizontal displacement and the underlying coupled mechanisms between them. To address these issues, we introduce a novel UAV photogrammetry-based framework for mining surface three-dimensional movement basin monitoring, named UAV-MSSH. This framework consists of two branches: vertical subsidence and horizontal displacements. For the subsidence branch, we propose an improved cloth simulation filtering algorithm based on slope zone indexing (CSFS) to model high-precision subsidence basins. In the horizontal displacement branch, we develop a probability integral prediction prior-guided COSI-Corr (PIM-CC) method for displacement detection by bridging the gaps between the horizontal displacement and subsidence. Employing this framework, we monitored the surface three-dimensional movement using the UAV oblique photogrammetry method at a working face in western China. The accuracy evaluation results with net station GNSS data show that the RMSE of the subsidence basin is 161 mm, the relative error is 3.1 %, and the RMSEs of the east–west and north–south components are 99 mm and 85 mm, respectively, which demonstrates the effectiveness and practicality of our proposed UAV-MSSH framework in mining surface monitoring tasks. This study establishes an innovative and proven methodology for UAV monitoring in the mining field, which is valuable for safe production, disaster warning, and ecological restoration.

Indoor scene reconstruction from LiDAR point cloud based on roof extraction

Indoor scene reconstruction from LiDAR point clouds is crucial for indoor navigation, scan-to-BIM, and virtual reality. However, occlusions caused by furniture and clutter make this task challenging. This paper introduces a novel framework for reconstructing 3D models using typically unoccluded ceiling point clouds, because the ceiling is difficult to be obstructed by indoor objects and is relatively well preserved. This framework starts with extracting the roof, roof is extracted by a proposed method based on cloth simulation which can extract various shape of roofs. Then a room instance map of the scene is obtained by input the point cloud density map to Mask R-CNN. By overlapping the roof point cloud and room instance map, the whole roof is segmented into roof points of different rooms. Next, we extracted the contours of every room's roof and a new algorithm was proposed to detect connections between different rooms to restore the topological relationship between rooms, generating the scene's floor plan. Finally, by detecting the contours and connections' height, the floor plan is stretched to detected height to generate a 3D model. To evaluate the proposed method's effectiveness, experiments were conducted on two indoor LiDAR point cloud datasets, GibLayout and ISPRS Benchmark, comprising a total of 13 scenes. The results were compared with representative methods, including Floor-sp and Heat for floor plan extraction, and Polyfit and KSR for 3D model reconstruction. The experimental results show that the new method outperform existing approaches, enabling the reconstruction of highly overlapping 3D models of real scenes.

Automatic multi-storey building partitioning from point cloud via bidirectional cloth simulation

With the advancements in scanning technology, the rapid acquisition of point cloud spanning multiple storeys of buildings has become feasible. Accurately dividing the building into individual storeys deepens the understanding of the building environment, accelerates the processing of the vast point cloud, and is crucial for numerous fields such as model reconstruction, indoor navigation, and building management. However, it remains a challenge to handle the building with rooms across multiple storeys. This study presents a novel method to partition complex multi-storey building from cluttered point cloud. First, the non-vertical structural elements are detected by taking the difference of height and normal vector as growth conditions. Next, we iteratively employ bidirectional cloth with height variation constraints to simulate the floor and ceiling trend surface. In this step, candidate ceiling patches are obtained through the optimization of a cost function. Finally, the irregular boundary between adjacent storeys that used for partitioning the point cloud is rasterized in terms of the ceilings at lower storey and the floors at upper storey. Each point is orderly classified into the correspond storey with reference to the elevation of the estimated boundary. Through comprehensive evaluation and analysis, our method has demonstrated its effectiveness and adaptability across various datasets. Our method yields superior results compared to the advanced methods, achieving an approximate value of 99 % on the weighted recall, weighted precision and weighted F1-score. Besides, the proposed method is not limited to Manhattan world buildings and requires only the spatial coordinate of points.

Seeking Efficiency for the Accurate Draping of Digital Garments in Production.

Digital garments are set to revolutionize the apparel industry in the way we design, produce, market, sell and try-on real garments. But for digital garments to play a central role, from designer to consumer, they must be a faithful digital replica of their real counterpart: a digital twin. Yet, most industry-grade tools used in the apparel industry do not focus on accuracy, but rather on producing fast and plausible drapes for interactive editing and quick feedback, thus limiting the value and the potential of digital garments. The key to accuracy lies in using the proper underlying simulation technology, well documented in the academic literature but historically sidelined in the apparel industry in favor of simulation speed. In this paper, we describe our industry-grade cloth simulation engine, built with a strong focus on accuracy rather than sheer speed. Using a global integration scheme and adopting state of the art simulation practices from the Computer Graphics field, we evaluate a wide range of algorithms to improve its convergence and overall performance. We provide qualitative and quantitative insights on the cost and capabilities of each of these features, with the aim of giving valuable feedback and useful guidelines to practitioners seeking to implement an accurate and robust draping simulator.

3D 의류 시뮬레이션 Z-weave 프로그램을 이용한 실물 소재 비교와 지속 가능한 패션 산업에서의 실현성

This study aims not only to address environmental issues caused by indiscriminate fashion consumption, specifically in the context of Fast Fashion but also to find an alternative and a sustainable solution that is ‘Upcycling’ using the 3D clothing simulation program Z-weave. Upcycling products have limitations in that it is difficult to produce samples since finished products must be produced directly with limited materials and resources like waste clothes. To overcome these limitations, a 3D clothing simulation program is introduced to effectively utilize the limited resources of waste clothing. The purpose of this study is to confirm the similarity between a virtual fabric created through Z-weave and a real fabric, through this, to evaluate the possibility of application in the actual fashion industry. As a research method, surveys and interviews were conducted with related majors on virtual clothing created as similar as possible to actual clothing by adjusting the physical properties within the Z-weave program. This study attempted to describe the impact of digital technology on the fashion industry and how 3D clothing simulation programs can be used in sustainable fashion production.

Shell stand: Stable thin shell models for 3D fabrication

A thin shell model refers to a surface or structure, where the object’s thickness is considered negligible. In the context of 3D printing, thin shell models are characterized by having lightweight, hollow structures, and reduced material usage. Their versatility and visual appeal make them popular in various fields, such as cloth simulation, character skinning, and for thin-walled structures like leaves, paper, or metal sheets. Nevertheless, optimization of thin shell models without external support remains a challenge due to their minimal interior operational space. For the same reasons, hollowing methods are also unsuitable for this task. In fact, thin shell modulation methods are required to preserve the visual appearance of a two-sided surface which further constrain the problem space. In this paper, we introduce a new visual disparity metric tailored for shell models, integrating local details and global shape attributes in terms of visual perception. Our method modulates thin shell models using global deformations and local thickening while accounting for visual saliency, stability, and structural integrity. Thereby, thin shell models such as bas-reliefs, hollow shapes, and cloth can be stabilized to stand in arbitrary orientations, making them ideal for 3D printing.

Filtering airborne LiDAR data based on multi-view window and multi-resolution hierarchical cloth simulation

ABSTRACT Ground filtering is a fundamental step in airborne LiDAR data processing toward a variety of applications. However, existing algorithms remain tremendously challenging in complex environments, e.g. steep hillsides, ridges, valleys, discontinuities, and numerous objects. We presented a new ground filtering algorithm that can handle various landscapes. First, the multi-view window is developed to increase the number of ground seeds on the various terrains. Second, multi-resolution hierarchical cloth simulation is used to rapidly construct the high-resolution reference terrain, and bidirectional internal force operation is proposed to improve the accuracy of reference terrain by smoothing the spikes in cloth. Finally, ground and non-ground points are classified based on the height differences between points and the reference terrain. The proposed algorithm was validated not only in the International Society for Photogrammetry and Remote Sensing (ISPRS) but also karst datasets, where particularly complex environments is contained. Results showed that the proposed algorithm outperformed the existing algorithms, with the lowest average total error of 3.85% and the highest average kappa coefficient of 87.75%. Moreover, the proposed algorithm can completely preserve complex terrain, e.g. extremely steep hillsides, and sharp ridges. This study had great potential to provide a useful tool for LiDAR data processing.

Virtual try-on using Open-CV

Abstract: Virtual Try-On (VTO) technology has drawn a lot of interest recently as a potentially effective way to improve online shopping experiences, eliminate the need for in-person trials, and raise consumer happiness. This report provides a comprehensive analysis of the state-of-the-art methods, challenges, and possible future opportunities in the virtual try-on industry. In the future, consider integrating augmented reality (AR) for real-time virtual fitting in physical environments, deep learning to improve the accuracy of cloth simulation, and effortlessly creating an effective and user-friendly VTO system for users to boost customer satisfaction. With aim to create a reliable e-commerce platform that will enable customers to try on clothing wherever they are, whenever they like, with the necessary privacy and security. The report concludes by emphasizing the transformative potential of VTO in transcending temporal and spatial constraints, presenting a vision where customers can try on clothing at their convenience. This vision aligns with the overarching goal of creating a reliable e-commerce platform that not only meets but exceeds customer expectations, thus setting a new standard in the online shopping landscape. The findings and recommendations herein provide a roadmap for industry stakeholders to navigate the challenges, seize opportunities, and collectively usher in a new era of online retail.

A fast railway track surface extraction method based on bidirectional cloth simulated point clouds

Point cloud-based railway track surface extraction is a crucial technology for railway inspection. It is still challenging to extract railway track surfaces from point cloud data due to the variable quantities, densities, and diverse scenarios, which limit the applicability and versatility of existing methods. To address these limitations, we propose a bidirectional cloth simulation approach that utilizes the geometric structural characteristics of the track surface for rapid extraction. This method applies simulated cloth in both bottom-up and top-down directions to the roadbed. Our method can process hundreds of thousands of point clouds per second and is adaptable to various point cloud types (TLS and MLS), roadbed types (ballasted and ballast-less), rail types (single, double and turnouts). It achieves a completeness of over 97 % in the automatic extraction of both ballasted single and ballast-less double tracks and a correctness of over 89 % in the extraction of complex turnouts.

A Building Point Cloud Extraction Algorithm in Complex Scenes

Buildings are significant components of digital cities, and their precise extraction is essential for the three-dimensional modeling of cities. However, it is difficult to accurately extract building features effectively in complex scenes, especially where trees and buildings are tightly adhered. This paper proposes a highly accurate building point cloud extraction method based solely on the geometric information of points in two stages. The coarsely extracted building point cloud in the first stage is iteratively refined with the help of mask polygons and the region growing algorithm in the second stage. To enhance accuracy, this paper combines the Alpha Shape algorithm with the neighborhood expansion method to generate mask polygons, which help fill in missing boundary points caused by the region growing algorithm. In addition, this paper performs mask extraction on the original points rather than non-ground points to solve the problem of incorrect identification of facade points near the ground using the cloth simulation filtering algorithm. The proposed method has shown excellent extraction accuracy on the Urban-LiDAR and Vaihingen datasets. Specifically, the proposed method outperforms the PointNet network by 20.73% in precision for roof extraction of the Vaihingen dataset and achieves comparable performance with the state-of-the-art HDL-JME-GGO network. Additionally, the proposed method demonstrated high accuracy in extracting building points, even in scenes where buildings were closely adjacent to trees.

Accurate Segmentation Method for Roadside Lampposts Based on Vehicle-Mounted Lidar Point Clouds

Abstract. The extraction of roadside lampposts constitutes a significant research focus within the domain of vehicular LiDAR point cloud object retrieval. Addressing the complexities inherent in discerning lampposts amidst convoluted vegetation in diverse roadway settings, this study introduces an innovative, progressive technique for the individualized extraction of lampposts utilizing vehicular LiDAR point clouds. The proposed method initiates with a bifurcation of the primary point cloud into terrestrial and aerial subsets via the Cloth Simulation Filter (CSF) algorithm. Subsequent processes involve the extraction of distinct lamppost structures from aerial point clouds through a methodology integrating elevation-normalized spatial partitioning and directional coverage analysis, thereby facilitating precise lamppost localization. The culmination of this process involves the refinement of lamppost point clouds through supervoxel clustering complemented by a non-discretization filter grounded in Principal Component Analysis (PCA). The efficacy of this novel approach is substantiated through empirical studies employing a LiDAR dataset encompassing extensive adhesive scenarios, whereupon comparative analysis with extant methodologies reveals its enhanced proficiency in isolating individual lampposts in complex environments.

Fast constrained optimization for cloth simulation parameters from static drapes

AbstractWe present a cloth simulation parameter estimation method that integrates the flexibility of global optimization with the speed of neural networks. While global optimization allows for varied designs in objective functions and specifying the range of optimization variables, it requires thousands of objective function evaluations. Each evaluation, which involves a cloth simulation, is computationally demanding and impractical time‐wise. On the other hand, neural network learning methods offer quick estimation results but face challenges such as the need for data collection, re‐training when input data formats change, and difficulties in setting constraints on variable ranges. Our proposed method addresses these issues by replacing the simulation process, typically necessary for objective function evaluations in global optimization, with a neural network for inference. We demonstrate that, once an estimation model is trained, optimization for various objective functions becomes straightforward. Moreover, we illustrate that it is possible to achieve optimization results that reflect the intentions of expert users through visualization of a wide optimization space and the use of range constraints.

A clothing pattern generating framework based on scanned human body model

PurposeAccurate and automatic clothing pattern making is very important in personalized clothing customization and virtual fitting room applications. Clothing pattern generating as well as virtual clothing simulation is an attractive research issue both in clothing industry and computer graphics.Design/methodology/approachPhysics-based method is an effective way to model dynamic process and generate realistic clothing animation. Due to conceptual simplicity and computational speed, mass-spring model is frequently used to simulate deformable and soft objects follow the natural physical rules. We present a physics-based clothing pattern generating framework by using scanned human body model. After giving a scanned human body model, first, we extract feature points, planes and curves on the 3D model by geometric analysis, and then, we construct a remeshed surface which has been formatted to connected quad meshes. Second, for each clothing piece in 3D, we construct a mass-spring model with same topological structures, and conduct a typical time integration algorithm to the mass-spring model. Finally, we get the convergent clothing pieces in 2D of all clothing parts, and we reconnected parts which are adjacent on 3D model to generate the basic clothing pattern.FindingsThe results show that the presented method is a feasible way for clothing pattern generating by use of scanned human body model.Originality/valueThe main contribution of this work is twofold: one is the geometric algorithm to scanned human body model, which is specially conducted for clothing pattern design to extract feature points, planes and curves. This is the crucial base for suit clothing pattern generating. Another is the physics-based pattern generating algorithm which flattens the 3D shape to 2D shape of cloth pattern pieces.

Inspiration from hyperbolic paraboloid folding for clothing design

PurposeThis study aims to increase the novelty of clothing design and fabric texture. The element library that can be used for design is systematically summarized. The element database can also be continuously filled according to the existing logic to realize the diversity of design. Improve the theory of fashion design, expand the designer's design ideas and improve design efficiency. Clear design steps and logic can help students and machines learn the design process and promote the development of intelligent design. And verify the feasibility of the simulation software to assist pleated clothing design.Design/methodology/approachFirstly, according to the logical framework of origami theory, different innovative designs and combined designs are made for the basic units of hyperbolic paraboloid, and the element library that can be used for design is systematically summarized. This database can also be continuously filled according to the existing logic to realize the diversity of design. Secondly, it summarizes three methods of pleated element filling clothing – uniform filling method, the irregular filling method and geometric addition method – that improve the theory of fashion design, expand the designer's design ideas and improve design efficiency. Clear design steps and logic can help students and machines learn the design process and promote the development of intelligent design. Finally, the virtual software is used to simulate the effect of pleated clothing, and the three-dimensional simulation software 3dclo is used to make an empirical study on the application of hyperbolic paraboloid origami in clothing pleated design to verify the feasibility of the simulation software to assist pleated clothing design.FindingsThe theoretical results of hyperbolic paraboloid origami are collected and arranged to establish the element library of hyperbolic paraboloid origami. The results expand the designer's design ideas and auxiliary design technology and improve the design efficiency using a sample of hyperbolic paraboloid fabric to verify its practicability and three-dimensional clothing simulation software for exploring the design. The design rules of hyperbolic paraboloid clothing and the realization method of fabric are summarized, including the expansion and combing of elements, the application of size and shape and the method of combination.Research limitations/implicationsOwing to the hyperbolic paraboloid origami’s length shrinkage, the loose computation of clothing requires targeted computation. This paper solely applies a paper model for estimating the shrinkage, and then we tend to subsequently explore the way to precisely compute the porosity, to determine the existing differences in the two-dimensional shrinkage of hyperbolic paraboloid creases of varying materials and to know if the clothing after large-scale production is capable of reaching the anticipated value.Practical implicationsThe exploration of this experiment brings a new 3D experiment process to the design process.Social implicationsThis experiment brings new possibilities for the development of virtual fitting and virtual display in the industry.Originality/valueThis study combines hyperbolic paraboloid origami and clothing and combs and expands the unit with logical thinking to expand the designer's design ideas.

Physics Based Animation Using Computer Graphics

Physics-based animation is a multidisciplinary area that uses ideas from physics, computer science, and mathematics to create realistic and dynamic movements in virtual settings. The basic ideas and methods of physics-based animation are introduced in this research paper, with an emphasis on how mathematical models and physical laws are used to produce realistic motion in computer-generated images. To construct realistic virtual environments, key disciplines covered include fluid simulation, fabric simulation, rigid body dynamics, and soft body dynamics. The report highlights recent developments in real-time physics simulations and addresses other topics such as processing economy, accuracy, and scalability. Applications for physics-based animation can be found in many different fields, such as virtual reality, simulation training, movies, and video games. The pursuit of more precise and effective physics-based animation is essential as technology develops to produce captivating and realistic virtual worlds. Keywords— Physics-based animation(PBA), virtual environment, Physics simulation, Dynamics, Animation software, Real-time physics, Collision detection, Fluid dynamics, Particle systems, Cloth simulation, Smooth particle hydrodynamics, finite element method, Navier-Stokes, Rigid body dynamics, Soft body dynamics, Deformation, Motion capture, Character animation, Kinematics, Rendering, Game development, Virtual reality, Augmented reality, Computer graphics, Simulation accuracy

Tree Diameter at Breast Height Extraction Based on Mobile Laser Scanning Point Cloud

The traditional measurement method (e.g., field survey) of tree diameter circumference often has high labor costs and is time-consuming. Mobile laser scanning (MLS) is a powerful tool for measuring forest diameter at breast height (DBH). However, the accuracy of point cloud registration seriously affects the results of DBH measurements. To address this issue, this paper proposes a new method for extracting tree DBH parameters; it achieves the purpose of efficient and accurate extraction of tree DBH by point cloud filtering, single-tree instance segmentation, and least squares circle fitting. Firstly, the point cloud data of the plantation forest samples were obtained by a self-constructed unmanned vehicle-mounted mobile laser scanning system, and the ground point cloud was removed using cloth simulation filtering (CSF). Secondly, fast Euclidean clustering (FEC) was employed to segment the single-tree instances, and the point cloud slices at breast height were extracted based on the point sets of single-tree instances, which were then fitted in two dimensions using the horizontally projected point cloud slices. Finally, a circle fitting algorithm based on intensity weighted least squares (IWLS) was proposed to solve the optimal circle model based on 2D point cloud slices, to minimize the impact of misaligned point clouds on DBH measures. The results showed that the mean absolute error (MAE) of the IWLS method was 2.41 cm, the root mean square error (RMSE) was 2.81 cm, and the relative accuracy was 89.77%. Compared with the random sample consensus (RANSAC) algorithm and ordinary least squares (OLS), the MAE was reduced by 36.45% and 9.14%, the RMSE was reduced by 40.90% and 12.26%, and the relative accuracy was improved by 8.99% and 1.63%, respectively. The R2 value of the fitted curve of the IWLS method was the closest to 1, with the highest goodness of fit and a significant linear correlation with the true value. The proposed intensity weighted least squares circle-fitting DBH extraction method can effectively improve the DBH extraction accuracy of mobile laser scanning point cloud data and reduce the influence of poorly aligned point clouds on DBH fitting.

Research on Individual Tree Canopy Segmentation of Camellia oleifera Based on a UAV-LiDAR System

In consideration of the limited accuracy of individual tree canopy segmentation algorithms due to the diverse canopy structure and complex environments in mountainous and hilly areas, this study optimized the segmentation parameters of three algorithms for individual tree canopy segmentation of Camellia oleifera in such environments by analyzing their respective parameters. Utilizing an Unmanned Aerial Vehicle-Light Detecting and Ranging (UAV-LiDAR) system, we obtained Canopy Height Models (CHM) of Camellia oleifera canopies based on Digital Elevation Models (DEM) and Digital Surface Models (DSM). Subsequently, we investigated the effects of CHM segmentation, point cloud clustering segmentation, and layer stacking fitting segmentation on Camellia oleifera canopies across different research areas. Additionally, combining ground survey data from forest lands with visual interpretation of UAV orthophoto images, we evaluated the performance of these three segmentation algorithms in terms of the F-score as an evaluation indicator for individual tree canopy segmentation accuracy. Combined with the Cloth Simulation Filter (CSF) filtering algorithm after removing the ground point cloud, our findings indicate that among different camellia densities and terrain environments, the point cloud clustering segmentation algorithm achieved the highest segmentation accuracy at 93%, followed by CHM segmentation at 88% and the layer stacking fitting segmentation method at 84%. By analyzing the data from UAV-LiDAR technology involving various land and Camellia oleifera planting types, we verified the applicability of these three segmentation algorithms for extracting camellia canopies. In conclusion, this study holds significant importance for accurately delineating camellia canopies within mountainous hilly environments while providing valuable insights for further research in related fields.

Monitoring of Levee Deformation for Urban Flood Risk Management Using Airborne 3D Point Clouds

In the low-lying, river-rich Pearl River Delta in South China, an extensive network of flood defense levees, spanning over 4400 km, plays a crucial role in urban flood management. These levees are designed to withstand floods and storm surges, yet their failure can lead to significant human and economic losses, highlighting the need for robust urban flood defense strategies. This necessitates the development of a sophisticated geographic information system for the levee network and rapid, accurate assessment methods for levee conditions to support water management and flood mitigation efforts. This study focuses on the levees along the Hengmen waterway in the Pearl River Delta, utilizing airborne Light Detection and Ranging (LiDAR) technology to gather 3D spatial data of the levees. Employing the Cloth Simulation Filter (CSF) algorithm, non-ground point cloud data were extracted. The study improved upon the region-growing algorithm, using a seed point set approach for the automatic extraction of levee point cloud data. The accuracy and completeness of levee extraction were evaluated using the quality index. This method achieved effective extraction of four levee types, showing significant improvements over traditional algorithms, with extraction quality ranging from 72% to 83%. Key research outcomes include the development of a novel method for detecting localized levee depressions based on the computation of the variance of angles between normal vectors in single-phase levee point cloud data. An adaptive optimal neighborhood approach was utilized to accurately determine the normal vectors, effectively representing the local morphology of the levee point clouds. Applied in three levee depression detection experiments, this method proved effective, demonstrating the capability of single-phase data in identifying regions of levee depression deformation. This advancement in levee monitoring technology marks a significant step forward in enhancing urban flood defense capabilities in regions such as the cities of the Pearl River Delta in China.