Local Geometric Features Research Articles

Coarse-to-fine segmentation of individual street trees from side-view point clouds

Segmenting individual street trees from a street side-view point cloud is the first and key step of obtaining a street tree inventory. Using the classification-segmentation framework for individual tree segmentation makes tree detection simple and accurate, but segmenting overlapping trees is still challenging. To more accurately segment overlapping trees, a coarse-to-fine method for segmenting individual street trees from a side-view point cloud is proposed in this paper. Following the classification-segmentation framework, the tree points are first detected from the side-view street point cloud by a pointwise classifier fused from 13 local geometric features and then trained using random forest (RF). Second, the tree proposals are obtained by density-based spatial clustering of applications with noise (DBSCAN) clustering and detection error filtering. Third, the overlapping tree proposals are recognized by trunk identification, and the single tree proposals are directly output as individual trees. Fourth, the overlapping trees are roughly divided into individual tree proposals through vertical planes. Finally, individual trees with optimized contours are obtained by iteratively using DBSCAN clustering and k-nearest neighbor (k-NN) classification. The side-view point cloud of a 290 m-long urban street containing 77 street trees is captured by a hand-held mobile ZEB Horizon laser scanner. The tree detection attained an F1 score of 0.9916 with a precision of 0.9989 and a recall of 0.9864. For individual tree segmentation, the F1 score was 0.9745 with a precision of 0.9672 and a recall of 0.9819. Compared to two current classification-segmentation methods, the overlapping tree segmentation F1 scores were increased by 0.0914 and 0.0617, respectively. The proposed method can be applied to tree parameter extraction, which is an important urban forest inventory task and is crucial for urban forest management. In our experiment, the root mean squared error (RMSE) of the trunk diameter at breast height (DBH) estimation was 0.8485 cm.

An iteration-based interactive attention network for 3D point cloud registration

Several learning-based methods dedicated to 3D point cloud registration have been developed recently. However, the performance of such methods is limited due to a lack of effective feature interaction mechanisms. To overcome this problem, an iteration-based interactive attention network is proposed here for 3D point cloud registration that can effectively learn the overlapping features of point cloud pairs and improve the registration accuracy. Concretely, we first designed a condensed global information extractor to achieve aggregated global features. Meanwhile, to reduce the amount of calculation required for subsequent modules while maintaining high-level characteristic information, the number of point cloud features is reduced. Furthermore, an overlapping feature iterative attention module and a discriminant feature iterative expansion module are designed. The main function of both modules is to implement feature interaction in the form of cross-attention and self-attention as well as to deepen interactions iteratively. The former captures overlapping information by iteratively interacting with the features of the condensed global features of one point cloud and the local geometric features of another point cloud. The latter can expand the number of features back to the initial number of point clouds through the interaction of overlapping features and local geometric features. Finally, matching features with high discriminative ability are obtained and used to formulate a soft correspondence matrix. Furthermore, weighted singular-value decomposition is adopted to obtain the rigid transformation matrix. Extensive experiments demonstrate that the proposed method achieves state-of-the-art performance.

Monitoring method for detecting and localizing overheat, smoke and fire faults in wind turbine nacelle

This study presents a monitoring method that utilizes 3D object classification to accurately detect mechanical and electrical components of a wind turbine by combining a geometric and statistic feature extractor (GSFE) with a multiview approach. The proposed monitoring method also detect outlier after executing object detection to localize overheat faults in these components with fused Optical or Infrared/LiDAR measurements. The proposed method hasthree key characteristics. First, the proposed outlier detection allocates two extremes of normal and faulty clusters by using 2D object classification/detection model or measuring thestandard deviation of temperature with sensor fusing measurements. Specifically, the outlier detection with sensor fusing measurements extracts the position coordinates andtemperature data to localize overheat faults, effectively detecting an overheat component. Second, the GSFE utilizes a group sampling approach to extract the local geometric feature information from neighboring point clouds, aggregating normal vectors and standard deviation. This method ensures the high accuracy of object classification. Third, a multi-view approach focuses on updating local geometric and statistic features through a graph convolution network, improving the accuracy and robustness of object classification. The proposed outlier detection is verified through overheat/fire field tests. The effectiveness of the proposed 3D object classification method is also validated by using a virtual wind turbine nacelle CAD dataset and a public CAD dataset named ModelNet40. Consequently, the proposed method is practical and effective for monitoring a fire and overheat component because it can accurately detect critical components with only a few virtual datasets because gathering bigdata for training a neural network is extremely difficult.

Boundary representation compatible feature recognition for manufacturing CAD models

This paper presents a Boundary Representation (BREP) compatible data representation for Graph Neural Network (GNN) based feature identification. This data representation follows BREP and STEP AP 203 standards and can transfer holistic manufacturing CAD information to the deep neural network, which assists to identify small local geometrical features and highly complex interactive geometric features. Inversely, this data representation can be easily converted back to a conventional CAD model due to its direct encoding approach. With this data representation, the GNN can reach 99.57% accuracy on 36 classes FeatureNet + dataset and realize 99.12% accuracy on Machining Process Identification (MPI) dataset with highly interactive features. This method can largely benefit Computer Assisted Process Planning and pave the way for future industrial automation.

Predicting localised corrosion and mechanical performance of a PEO surface modified rare earth magnesium alloy for implant use through in-silico modelling

In this study, the influence of a plasma electrolytic oxidation (PEO) surface treatment on a medical-grade WE43-based magnesium alloy is examined through an experimental and computational framework that considers the effects of localised corrosion features and mechanical properties throughout the corrosion process. First, a comprehensive in-vitro immersion study was performed on WE43-based tensile specimens with and without PEO surface modification, which included fully automated spatial reconstruction of the phenomenological features of corrosion through micro-CT scanning, followed by uniaxial tensile testing. Then the experimental data of both unmodified and PEO-modified groups were used to calibrate parameters of a finite element-based surface corrosion model. In-vitro, it was found that the WE43-PEO modified group had a significantly lower corrosion rate and maintained significantly higher mechanical properties than the unmodified. While corrosion rates were ∼50% lower in the WE43-PEO modified specimens, the local geometric features of corroding surfaces remained similar to the unmodified WE43 group, however evolving after almost the double amount of time. We were also able to quantitatively demonstrate that the PEO surface treatment on magnesium continued to protect samples from corrosion throughout the entire period tested, and not just in the early stages of corrosion. Using the results from the testing framework, the model parameters of the surface-based corrosion model were identified for both groups. This enabled, for the first time, in-silico prediction of the physical features of corrosion and the mechanical performance of both unmodified and PEO modified magnesium specimens. This simulation framework can enable future in-silico design and optimisation of bioabsorbable magnesium devices for load-bearing medical applications.

Modular Soft Robotic Actuators from Flexible Perforated Sheets

Soft robotic actuators can be designed to achieve complex and tailored motions while simultaneously leveraging their compliance to interact with complex and often delicate environments. Mechanical metamaterials reveal a route to customizable deformations, force exertion, and mechanical energy efficiency attainable by careful arrangement of local geometric features. Herein, modular soft robotic actuators are developed from soft elastomers and flexible thermoplastic sheets of various unit cell designs. The efforts are focused on center‐symmetric perforated sheets, which are formed into flexible cylindrical skins that surround the soft inflatable actuators. The results demonstrate the influence of perforation geometry on the spatial stiffness of the reinforcement structure and the proposed actuators’ response through several investigations. It is demonstrated that the free‐boundary displacement, maximal force exertion, and mechanical energy efficiency of extensile actuators are dependent on a change of deformation mode in the mesostructure. The spatial stiffness concept is extended to develop soft robotic actuators that can bend, twist, and perform hybrid motions, such as simultaneous bending and twisting. Multisegment soft robotic arms are also developed from the aforementioned actuators. Investigations in this study provide a step toward the development of highly customizable and programmable soft robotic actuators for various applications.

Intelligent Identification and Verification of Flutter Derivatives and Critical Velocity of Closed-Box Girders Using Gradient Boosting Decision Tree

Flutter derivatives (FDs) of the bridge deck are basic aerodynamic parameters by which flutter analysis determines critical flutter velocity (CFV), and they are traditionally identified by sectional model wind tunnel tests or computational fluid dynamics (CFD) numerical simulation. Based on some wind tunnel testing results and numerical simulation data, the machine learning models for identifying FDs of closed-box girders are trained and developed via a gradient boosting decision tree in this study. The models can explore the underlying input–output transfer relationship of datasets and realize rapid intelligent identification of FDs without wind tunnel tests or numerical simulation. This method also provides a convenient and feasible option for expanding datasets of FDs, and the distribution of FDs can be analyzed through the post-interpretation of trained models. Combined with FD sensitivity analysis, the models can be verified by the calculation error of CFV. In addition, the proposed method can help determine the appropriate shape of the box girder cross-section in the preliminary design stage of long-span bridges and provide the necessary reference for aerodynamic shape optimization by modifying the local geometric features of the cross-section.

Automatic identification of rock discontinuity and stability analysis of tunnel rock blocks using terrestrial laser scanning

Local geometric information and discontinuity features are key aspects of the analysis of the evolution and failure mechanisms of unstable rock blocks in rock tunnels. This study demonstrates the integration of terrestrial laser scanning (TLS) with distinct element method for rock mass characterization and stability analysis in tunnels. TLS records detailed geometric information of the surrounding rock mass by scanning and collecting the positions of millions of rock surface points without contact. By conducting a fuzzy K-means method, a discontinuity automatic identification algorithm was developed, and a method for obtaining the geometric parameters of discontinuities was proposed. This method permits the user to visually identify each discontinuity and acquire its spatial distribution features (e.g. occurrences, spacings, trace lengths) in great detail. Compared with hand mapping in conventional geotechnical surveys, the geometric information of discontinuities obtained by this approach is more accurate and the identification is more efficient. Then, a discrete fracture network with the same statistical characteristics as the actual discontinuities was generated with the distinct element method, and a representative numerical model of the jointed surrounding rock mass was established. By means of numerical simulation, potential unstable rock blocks were assessed, and failure mechanisms were analyzed. This method was applied to detection and assessment of unstable rock blocks in the spillway and sand flushing tunnel of the Hongshiyan hydropower project after a collapse. The results show that the noncontact detection of blocks was more labor-saving with lower safety risks compared with manual surveys, and the stability assessment was more reliable since the numerical model built by this method was more consistent with the distribution characteristics of actual joints. This study can provide a reference for geological survey and unstable rock block hazard mitigation in tunnels subjected to complex geology and active rockfalls.

LWSNet: A Point-Based Segmentation Network for Leaf-Wood Separation of Individual Trees

The accurate leaf-wood separation of individual trees from point clouds is an important yet challenging task. Many existing methods rely on manual features that are time-consuming and labor-intensive to distinguish between leaf and wood points. However, due to the complex interlocking structure of leaves and wood in the canopy, these methods have not yielded satisfactory results. Therefore, this paper proposes an end-to-end LWSNet to separate leaf and wood points within the canopy. First, we consider the linear and scattering distribution characteristics of leaf and wood points and calculate local geometric features with distinguishing properties to enrich the original point cloud information. Then, we fuse the local contextual information for feature enhancement and select more representative features through a rearrangement attention mechanism. Finally, we use a residual connection during the decoding stage to improve the robustness of the model and achieve efficient leaf-wood separation. The proposed LWSNet is tested on eight species of trees with different characteristics and sizes. The average F1 score for leaf-wood separation is as high as 97.29%. The results show that this method outperforms the state-of-the-art leaf-wood separation methods in previous studies, and can accurately and robustly separate leaves and wood in trees of different species, sizes, and structures. This study extends the leaf-wood separation of tree point clouds in an end-to-end manner and demonstrates that the deep-learning segmentation algorithm has a great potential for processing tree and plant point clouds with complex morphological traits.

IDENTIFICATION OF RELEVANT POINT CLOUD GEOMETRIC FEATURES FOR THE DETECTION OF PAVEMENT CRACKS USING MLS DATA

Abstract. The maintenance of road infrastructures is one of the main challenges that transportation authorities must face to guarantee the safe mobility of people and goods. Novel remote monitoring technologies offer advanced solutions for this issue, allowing the inspection of large sections of the network in a time-effective way. In this paper, we introduce a methodology for the detection of cracks on road pavements using point clouds acquired with a mobile laser scanner. First, the points of the cloud are labelled as pavement or cracks based on field annotations, and local geometric features of the points are calculated using principal component analysis. Two different machine learning classifiers, Support Vector Machine (SVM) and Random Forest, are then trained to identify crack points using the point feature data. The crack points predicted by the classifiers are clustered as individual instances and compared to the corresponding ones from a test dataset. Although pointwise performance of the method is modest, it can correctly identify and measure areas of the pavement affected by cracking.

A Speedy Point Cloud Registration Method Based on Region Feature Extraction in Intelligent Driving Scene.

The challenges of point cloud registration in intelligent vehicle driving lie in the large scale, complex distribution, high noise, and strong sparsity of lidar point cloud data. This paper proposes an efficient registration algorithm for large-scale outdoor road scenes by selecting the continuous distribution of key area laser point clouds as the registration point cloud. The algorithm extracts feature descriptions of the key point cloud and introduces local geometric features of the point cloud to complete rough and fine registration under constraints of key point clouds and point cloud features. The algorithm is verified through extensive experiments under multiple scenarios, with an average registration time of 0.5831 s and an average accuracy of 0.06996 m, showing significant improvement compared to other algorithms. The algorithm is also validated through real-vehicle experiments, demonstrating strong versatility, reliability, and efficiency. This research has the potential to improve environment perception capabilities of autonomous vehicles by solving the point cloud registration problem in large outdoor scenes.

Automatic Numeral Recognition System Using Local Statistical and Geometrical Features

Optical Character Recognition (OCR) research includes computer vision, artificial intelligence, and pattern recognition. Character recognition has garnered a lot of attention in the last decade due to its broad variety of uses and applications, including multiple-choice test data, business documents (e.g., ID cards, bank notes, passports, etc.), and automatic number plate recognition. This paper introduces an automatic recognition system for printed numerals. The automatic reading system is based on extracting local statistical and geometrical features from the text image. Those features are represented by eight vectors extracted from each digit. Two of these features are local statistical (A, A th), and six are local geometrical (P1, P2, P3, P4, P5, and P6). Thus, the database created consists of 1120 statistical and geometrical features. For the purpose of recognition, the features of the test image are compared with the features of all the images saved in the database depending on the value of the Minimum Distance (MD). All digits (0–9) were identified with 100% accuracy. The average computational time required to recognize a numeral at any font size is 0.06879 seconds.

Zero watermarking scheme for 3D triangle mesh model based on global and local geometric features

Zero watermarking scheme for 3D triangle mesh model based on global and local geometric features

Adaptive Regularized Warped Gradient Descent Enhances Model Generalization and Meta-learning for Few-shot Learning

Warped Gradient descent (WarpGrad) is a remarkable meta-learning method for gradient transformation by inserting warp-layers. However, the task-shared initialization provided by WarpGrad is difficult to be adaptive to each task. Moreover, transforming gradients with meta-learned warp-layers ignores the local geometric features or task-specific knowledge, and may lead to a significant risk of overfitting caused by the increase of parameters. In this paper, we propose ARWarpGrad to guarantee better generalization performance with faster convergence speed by modeling both the cross-task and task-specific knowledge. We introduce Initialization Modulation (IM) to meta-learn to initialize the task-learner specifically. Furthermore, the Mixed Gradient Preprocessing (MGP), which includes the Adaptive Learning Rates (ALR) and the Gaussian Momentum Dropout (GMD), is put forward to provide better adaptive optimization direction and length for task adaptation based on the feature of local geometries. In addition, Memory Regularization (MR) is provided to alleviate the overfitting problem effectively with the use of parameter memory. Ultimately, extensive experiments on three settings demonstrate that ARWarpGrad achieves state-of-the-art performance with convergence acceleration and overfitting prevention characteristics.

Robust kernel-based feature representation for 3D point cloud analysis via circular convolutional network

Feature descriptors of point clouds are used in several applications, such as registration and part segmentation of 3D point clouds. Learning representations of local geometric features is unquestionably the most important task for accurate point cloud analyses. However, it is challenging to develop rotation or scale-invariant descriptors. Most previous studies have either ignored rotations or empirically studied optimal scale parameters, which hinders the applicability of the methods for real-world datasets. In this paper, we present a new local feature description method that is robust to rotation and scale variations. Moreover, we improve representations based on a global aggregation method. First, we place kernels aligned around each point in the normal direction. To avoid the sign problem of the normal vector, we use a symmetric kernel point distribution in the tangential plane. From each kernel point, we first project the points from the spatial space to the feature space, which is robust to multiple scales and rotation, based on angles and distances. Subsequently, we perform convolutions by considering local kernel point structures and long-range global context, obtained by a global aggregation method. We experimented with our proposed descriptors on benchmark datasets (i.e., ModelNet40 and ShapeNetPart) to evaluate the performance of registration, classification, and part segmentation on 3D point clouds. Our method showed superior performances when compared to the state-of-the-art methods by reducing 70% of the rotation and translation errors in the registration task. Our method also showed comparable performance in the classification and part-segmentation tasks without any external data augmentation.

Enhanced task parameterized dynamic movement primitives by GMM to solve manipulation tasks

PurposeUnder the development trend of intelligent manufacturing, the unstructured environment requires the robot to have a good generalization performance to adapt to the scene changes. The purpose of this paper aims to present a learning from demonstration (LfD) method (task parameterized [TP]-dynamic movement primitives [DMP]-GMR) that combines DMPs and TP-LfD to improve generalization performance and solve object manipulation tasks.Design/methodology/approachThe dynamic time warping algorithm is applied to processing demonstration data to obtain a more standard learning model in the proposed method. The DMPs are used to model the basic trajectory learning model. The Gaussian mixture model is introduced to learn the force term of DMPs and solve the problem of learning from multiple demonstration trajectories. The robot can learn more local geometric features and generalize the learned model to unknown situations by adding task parameters.FindingsAn evaluation criterion based on curve similarity calculated by the Frechet distance was constructed to evaluate the model’s interpolation and extrapolation performance. The model’s generalization performance was assessed on 2D virtual data sets, and first, the results show that the proposed method has better interpolation and extrapolation performance than other methods.Originality/valueThe proposed model was applied to the axle-hole assembly task on real robots, and the robot’s posture in grasping and placing the axle part was taken as the task parameter of the model. The experiment results show that The proposed model is competitive with other models.

Review: Research on product surface quality inspection technology based on 3D point cloud

In recent years, machine vision has played an important role in product surface quality detection. The promotion and use of this technology have largely avoided the subjectivity caused by human detection and improved detection efficiency and accuracy. Different from the image data commonly used in machine vision, point cloud can describe the spatial structure of an object, provide more information than image data, and have the ability to expand the data to build multi-dimensional data models. Due to the strong anti-interference ability of point cloud sensors and the high accuracy of three-dimensional positioning information point cloud, nondestructive testing technology based on point cloud has received more and more attention. This paper summarizes the research progress of product surface quality detection methods based on 3D point cloud in recent years. According to different data processing methods, the detection research is divided into five categories: based on point cloud contour, based on local geometric feature, based on template matching, based on multimodal point cloud, and based on deep learning. The five methods are reviewed and summarized respectively. Finally, the key problems of each detection method and the future trend of product surface quality detection technology based on 3D point cloud are discussed.

Siamese PointNet: 3D Head Pose Estimation with Local Feature Descriptor

Head pose estimation is an important part of the field of face analysis technology. It can be applied to driver attention monitoring, passenger monitoring, effective information screening, etc. However, illumination changes and partial occlusion interfere with the task, and due to the non-stationary characteristic of the head pose change process, normal regression networks are unable to achieve very accurate results on large-scale synthetic training data. To address the above problems, a Siamese network based on 3D point clouds was proposed, which adopts a share weight network with similar pose samples to constrain the regression process of the pose’s angles; meanwhile, a local feature descriptor was introduced to describe the local geometric features of the objects. In order to verify the performance of our method, we conducted experiments on two public datasets: the Biwi Kinect Head Pose dataset and Pandora. The results show that compared with the latest methods, our standard deviation was reduced by 0.4, and the mean error was reduced by 0.1; meanwhile, our network also maintained a good real-time performance.

DFSP: A fast and automatic distance field-based stem-leaf segmentation pipeline for point cloud of maize shoot.

The 3D point cloud data are used to analyze plant morphological structure. Organ segmentation of a single plant can be directly used to determine the accuracy and reliability of organ-level phenotypic estimation in a point-cloud study. However, it is difficult to achieve a high-precision, automatic, and fast plant point cloud segmentation. Besides, a few methods can easily integrate the global structural features and local morphological features of point clouds relatively at a reduced cost. In this paper, a distance field-based segmentation pipeline (DFSP) which could code the global spatial structure and local connection of a plant was developed to realize rapid organ location and segmentation. The terminal point clouds of different plant organs were first extracted via DFSP during the stem-leaf segmentation, followed by the identification of the low-end point cloud of maize stem based on the local geometric features. The regional growth was then combined to obtain a stem point cloud. Finally, the instance segmentation of the leaf point cloud was realized using DFSP. The segmentation method was tested on 420 maize and compared with the manually obtained ground truth. Notably, DFSP had an average processing time of 1.52 s for about 15,000 points of maize plant data. The mean precision, recall, and micro F1 score of the DFSP segmentation algorithm were 0.905, 0.899, and 0.902, respectively. These findings suggest that DFSP can accurately, rapidly, and automatically achieve maize stem-leaf segmentation tasks and could be effective in maize phenotype research. The source code can be found at https://github.com/syau-miao/DFSP.git.

Multiple Attention Mechanism Enhanced YOLOX for Remote Sensing Object Detection.

The object detection technologies of remote sensing are widely used in various fields, such as environmental monitoring, geological disaster investigation, urban planning, and military defense. However, the detection algorithms lack the robustness to detect tiny objects against complex backgrounds. In this paper, we propose a Multiple Attention Mechanism Enhanced YOLOX (MAME-YOLOX) algorithm to address the above problem. Firstly, the CBAM attention mechanism is introduced into the backbone of the YOLOX, so that the detection network can focus on the saliency information. Secondly, to identify the high-level semantic information and enhance the perception of local geometric feature information, the Swin Transformer is integrated into the YOLOX's neck module. Finally, instead of GIOU loss, CIoU loss is adopted to measure the bounding box regression loss, which can prevent the GIoU from degenerating into IoU. The experimental results of three publicly available remote sensing datasets, namely, AIBD, HRRSD, and DIOR, show that the algorithm proposed possesses better performance, both in relation to quantitative and qualitative aspects.