Monocular 3D object detection with Pseudo-LiDAR confidence sampling and hierarchical geometric feature extraction in 6G network

The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms.Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost,lowpower solution compared to LiDAR solutions in the field of autonomous driving.However,this technique has some problems,i.e.,(1)the poor quality of generated Pseudo-LiDAR point clouds resulting from the nonlinear error distribution of monocular depth estimation and(2)the weak representation capability of point cloud features due to the neglected global geometric structure features of point clouds existing in LiDAR-based 3D detection networks.Therefore,we proposed a Pseudo-LiDAR confidence sampling strategy and a hierarchical geometric feature extraction module for monocular 3D object detection.We first designed a point cloud confidence sampling strategy based on a 3D Gaussian distribution to assign small confidence to the points with great error in depth estimation and filter them out according to the confidence.Then,we present a hierarchical geometric feature extraction module by aggregating the local neighborhood features and a dual transformer to capture the global geometric features in the point cloud.Finally,our detection framework is based on Point-Voxel-RCNN(PV-RCNN)with high-quality Pseudo-LiDAR and enriched geometric features as input.From the experimental results,our method achieves satisfactory results in monocular 3D object detection.

High-precision automatic measurement of two-dimensional geometric features based on machine vision

To realize high-precision automatic measurement of two-dimensional geometric features on parts, a cooperative measurement system based on machine vision is constructed. Its hardware structure, functional composition and working principle are introduced. The mapping relationship between the feature image coordinates and the measuring space coordinates is established. The method of measuring path planning of small field of view （FOV） images is proposed. With the cooperation of the panoramic image of the object to be measured, the small FOV images with high object plane resolution are acquired automatically. Then, the auxiliary measuring characteristics are constructed and the parameters of the features to be measured are automatically extracted. Experimental results show that the absolute value of relative error is less than 0. 03% when applying the cooperative measurement system to gauge the hole distance of 100 mm nominal size. When the object plane resolving power of the small FOV images is 16 times that of the large FOV image, the measurement accuracy of small FOV images is improved by 14 times compared with the large FOV image. It is suitable for high-precision automatic measurement of two-dimensional complex geometric features distributed on large scale parts.

Japanese Sign Language Recognition by Combining Joint Skeleton-Based Handcrafted and Pixel-Based Deep Learning Features with Machine Learning Classification

Sign language recognition is vital for enhancing communication accessibility among the Deaf and hard-of-hearing communities.In Japan,approximately 360,000 individualswith hearing and speech disabilities rely on Japanese Sign Language(JSL)for communication.However,existing JSL recognition systems have faced significant performance limitations due to inherent complexities.In response to these challenges,we present a novel JSL recognition system that employs a strategic fusion approach,combining joint skeleton-based handcrafted features and pixel-based deep learning features.Our system incorporates two distinct streams:the first stream extracts crucial handcrafted features,emphasizing the capture of hand and body movements within JSL gestures.Simultaneously,a deep learning-based transfer learning stream captures hierarchical representations of JSL gestures in the second stream.Then,we concatenated the critical information of the first stream and the hierarchy of the second stream features to produce the multiple levels of the fusion features,aiming to create a comprehensive representation of the JSL gestures.After reducing the dimensionality of the feature,a feature selection approach and a kernel-based support vector machine(SVM)were used for the classification.To assess the effectiveness of our approach,we conducted extensive experiments on our Lab JSL dataset and a publicly available Arabic sign language(ArSL)dataset.Our results unequivocally demonstrate that our fusion approach significantly enhances JSL recognition accuracy and robustness compared to individual feature sets or traditional recognition methods.

METHOD FOR ADAPTIVE MESH GENERATION BASED ON GEOMETRICAL FEATURES OF 3D SOLID

In order to provide a guidance to specify the element size dynamically during adaptive finite element mesh generation, adaptive criteria are firstly defined according to the relationships between the geometrical features and the elements of 3D solid. Various modes based on different datum geometrical elements, such as vertex, curve, surface, and so on, are then designed for generating local refined mesh. With the guidance of the defmed criteria, different modes are automatically selected to apply on the appropriate datum objects to program the element size in the local special areas. As a result, the control information of element size is successfully programmed covering the entire domain based on the geometrical features of 3D solid. A new algorithm based on Delatmay triangulation is then developed for generating 3D adaptive finite element mesh, in which the element size is dynamically specified to catch the geometrical features and suitable tetrahedron facets are selected to locate interior nodes continuously. As a result, adaptive mesh with good-quality elements is generated. Examples show that the proposed method can be successfully applied to adaptive finite element mesh automatic generation based on the geometrical features of 3D solid.

A GEOMETRIC FEATURE FOR FINITE ELEMENT SCHEMES

In this note we characterize the geometric facture of a (μ, r, k) - FES. Namely, for a C~μ triangular in- terpolation schcme with C^r vertex data, any angle of the macrotriangle must be divided into at least (μ + 1)/ (r + 1 - μ) parts.

A Multisource Contour Matching Method Considering the Similarity of Geometric Features

The existing multi-source contour matching studies have focused on the matching methods with consideration of topological relations and similarity measurement based on spatial Euclidean distance,while it is lack of taking the contour geometric features into account,which may lead to mismatching in map boundaries and areas with intensive contours or extreme terrain changes.In light of this,it is put forward that a matching strategy from coarse to precious based on the contour geometric features.The proposed matching strategy can be described as follows.Firstly,the point sequence is converted to feature sequence according to a feature descriptive function based on curvature and angle of normal vector.Then the level of similarity among multi-source contours is calculated by using the longest common subsequence solution.Accordingly,the identical contours could be matched based on the above calculated results.In the experiment for the proposed method,the reliability and efficiency of the matching method are verified using simulative datasets and real datasets respectively.It has been proved that the proposed contour matching strategy has a high matching precision and good applicability.

GENERATION AND APPLICATION OF VARIATIONAL GEOMETRIC CONSTRAINTS NETWORK BASED ON ISO'S FEATURE

The concept of variantional geometric constraints network is presented. Basedon ISO's feature, three kinds of variational geometric constraints are defined. The concepts ofmate tree (MT) and loop circuit (LC) are presented. The generation method of well-constrainedvariational geometric constraints network (VGCN) is studied. The network can be applied ingeneration of well-constrained tolerance types and tolerance chains. A simple example is analyzed toshow the scheme to be effective.

Dependence of Conductance of Corrugated Graphene Quantum Dot on Geometrical Features

Dependence of conductance of corrugated graphene quantum dot(CGQD)on geometrical features includinglength,width,connection and edge is investigated by the first principles calculations.The results demonstrate that theconductance of CGQD with different geometrical features is different from each other.The positions and amplitudesof discrete levels in densities of states and transmission coefficients are sensitive to geometrical features.The I-Vcharacteristics of graphene are modified by size and edge,it is surprise the current does not change monotonously butoscillatory with length.And they are slight change for different connections.

Robust Image Watermarking Using Local Invariant Features and Independent Component Analysis

This paper proposes a novel robust image watermarking scheme for digital images using local invariant features and Independent Component Analysis （ICA）. Most present watermarking algorithms are unable to resist geometric distortions that desynchronize the location. The method we propose here is robust to geometric attacks. In order to resist geometric distortions, we use a local invariant feature of the image called the scale invariant feature transform, which is invariant to translation and scaling distortions. The watermark is inserted into the circular patches generated by scale-invariant key point extractor. Rotation invariance is achieved using the translation property of the polar-mapped circular patches. Our method belongs to the blind watermark category, because we use Independent Component Analysis for detection that does not need the original image during detection. Experimental results show that our method is robust against geometric distortion attacks as well as signal-processing attacks.

Two-Edge-Corner Image Features for Registration of Geospatial Images with Large View Variations

This paper presents a robust image feature that can be used to automatically establish match correspondences between aerial images of suburban areas with large view variations. Unlike most commonly used invariant image features, this feature is view variant. The geometrical structure of the feature allows predicting its visual appearance according to the observer’s view. This feature is named 2EC (2 Edges and a Corner) as it utilizes two line segments or edges and their intersection or corner. These lines are constrained to correspond to the boundaries of rooftops. The description of each feature includes the two edges’ length, their intersection, orientation, and the image patch surrounded by a parallelogram that is constructed with the two edges. Potential match candidates are obtained by comparing features, while accounting for the geometrical changes that are expected due to large view variation. Once the putative matches are obtained, the outliers are filtered out using a projective matrix optimization method. Based on the results of the optimization process, a second round of matching is conducted within a more confined search space that leads to a more accurate match establishment. We demonstrate how establishing match correspondences using these features lead to computing more accurate camera parameters and fundamental matrix and therefore more accurate image registration and 3D reconstruction.

Modeling of Geometric Variations Within Three-Dimensional Tolerance Zones

A tolerance modeling method of geometric variations within three-dimensional(3D) tolerance domain is proposed.According to the classification method of feature variations and classes of invariance or symmetry in the new generation Geometrical Product Specifications(GPS) system,the proposed method is based on the Small Displacement Torsor(SDT) concept,and SDT is used to represent the geometric deviations between the nominal feature and the fitting feature. Furthermore,the variation zones of several kinds complex or irregular geometric features are constructed,and the corresponding tolerance modeling methods are discussed respectively. Finally,an example is presented to verify the efficiency of the presented method for modeling 3D dimensional and geometrical tolerances.The proposed modeling method based on the complete mathematical foundation conforms with the design philosophy and principle of the new generation GPS standards system.

Unsupervised Feature Selection Using Structured Self-Representation

Unsupervised feature selection has become an important and challenging problem faced with vast amounts of unlabeled and high-dimension data in machine learning. We propose a novel unsupervised feature selection method using Structured Self-Representation( SSR) by simultaneously taking into account the selfrepresentation property and local geometrical structure of features. Concretely,according to the inherent selfrepresentation property of features,the most representative features can be selected. Mean while,to obtain more accurate results,we explore local geometrical structure to constrain the representation coefficients to be close to each other if the features are close to each other. Furthermore,an efficient algorithm is presented for optimizing the objective function. Finally,experiments on the synthetic dataset and six benchmark real-world datasets,including biomedical data,letter recognition digit data and face image data,demonstrate the encouraging performance of the proposed algorithm compared with state-of-the-art algorithms.

The Derivation of Skeleton Lines for Terrain Features

The geometric and physical analysis methods are conventional methods for the derivation of skeleton lines in the fields of cartography,digital photogrammetry,and related areas.This paper proposes a stepwise approach that uses the physical analysis method in the first stage and the geometric analysis method in the subsequent stage.The physical analysis method analyses the terrain globally to obtain a rough set of skeleton lines for a terrain surface.The rough skeleton lines help to structure the ordering of feature points by the geometric analysis method.

REVERSE MODELING FOR CONIC BLENDING FEATURE

A novel method to extract conic blending feature in reverse engineering is presented. Different from the methods to recover constant and variable radius blends from unorganized points, it contains not only novel segmentation and feature recognition techniques, but also bias corrected technique to capture more reliable distribution of feature parameters along the spine curve. The segmentation depending on point classification separates the points in the conic blend region from the input point cloud. The available feature parameters of the cross-sectional curves are extracted with the processes of slicing point clouds with planes, conic curve fitting, and parameters estimation and compensation, The extracted parameters and its distribution laws are refined according to statistic theory such as regression analysis and hypothesis test. The proposed method can accurately capture the original design intentions and conveniently guide the reverse modeling process. Application examples are presented to verify the high precision and stability of the proposed method.

GeoGlue: feature matching with self-supervised geometric priors for high-resolution UAV images

We present GeoGlue,a novel method using high-resolution UAV imagery for accurate feature matching,which is normally challenging due to the complicated scenes.Current feature detection methods are performed without guidance of geometric priors(e.g.,geometric lines),lacking enough attention given to salient geometric features which are indispensable for accurate matching due to their stable existence across views.In this work,geometric lines arefirstly detected by a CNN-based geometry detector(GD)which is pre-trained in a self-supervised manner through automatically generated images.Then,geometric lines are naturally vectorized based on GD and thus non-significant features can be disregarded as judged by their disordered geometric morphology.A graph attention network(GAT)is utilized forfinal feature matching,spanning across the image pair with geometric priors informed by GD.Comprehensive experiments show that GeoGlue outperforms other state-of-the-art methods in feature-matching accuracy and performance stability,achieving pose estimation with maximum rotation and translation errors under 1%in challenging scenes from benchmark datasets,Tanks&Temples and ETH3D.This study also proposes thefirst self-supervised deep-learning model for curved line detection,generating geometric priors for matching so that more attention is put on prominent features and improving the visual effect of 3D reconstruction.

融合语义信息与物体级几何特征的实时动态激光SLAM算法

针对现有的激光SLAM算法在动态场景下鲁棒性差、定位与建图精度易受动态物体干扰的问题,提出了一种融合语义信息与物体级几何特征的实时动态激光SLAM算法Object-SuMa。首先通过地面滤波、物体分割、方向包围盒解算等过程,生成物体级几何特征并表示为纹理,用于并行计算和修正物体内部错误的语义分割结果;然后在配准过程中分解计算方向包围盒间的IOU,并基于包围盒IOU和语义分割结果引入物体级几何加权和语义加权,减少误匹配和动态点匹配;借助图形渲染管线构建并行计算过程,进行地面点配准和非地面点配准两步优化,降低计算复杂度和耗时;最后在KITTI里程计数据集测试表明,Object-SuMa算法相比SuMa++算法的相对位姿估计精度提升15%,ICP平均耗时下降17%,改善了动态场景下的激光SLAM定位精度和鲁棒性。

基于形体特征层次分析的概念设计原型评价与演化方法

为对概念设计原型进行定量评价,实现具有形位公差需求的机械零件成形时间与制造质量之间的均衡,提出一种基于形体特征层次分析(Shape Feature Hierarchical Analysis,SFHA)的概念设计原型评价与演化方法。针对概念设计形体的孔和轴的形态特性,采用最大内切圆柱和最小外接圆柱构建特征模型,计算由分层策略所导致偏移的实际轴线位置,推算圆柱度误差大小。进行基于形位公差的自适应分层,在保证圆柱度等公差满足设计需求的情况下尽可能减少所需层数。通过改进粒子群算法进行非凸优化求解,遴选出最优的分层序列。计算特征层次化模型向正平面V(XOZ)和侧平面W(YOZ)的平行正投影面积及绝对梯度变化,实现基于SFHA的概念设计原型特征定量化描述与动态演化。以典型支座零件为例进行验证,采用熔融沉积成形设备进行物理试验,基于高精度结构光三维扫描仪获取原型零件的圆柱度误差,相较于均匀分层方法,所提出的SFHA方法制造时间可减少26.97%。

融合颜色与几何信息的点云配准

目前,大部分点云配准算法是基于点云数据的几何特征进行描述.随着能够同时采集对象坐标和颜色的扫描设备出现,为更好利用颜色信息,对彩色点云中的颜色信息描述进行研究,提出一种基于颜色分布的3DLGOP特征描述子,并将其与几何特征描述子FPFH、颜色特征描述子CSHOT融合,设计出FPFH-3DLGOP的混合描述符,采用最近邻比值法得到初始对应关系,采用随机采样一致性去除错误对应关系,对匹配关系使用奇异值分解(SVD)求得三维刚体变换矩阵,进而完成点云配准.实验表明,所提出的特征描述符充分地利用了点云数据的颜色特征与几何特征,不仅可以很好地完成彩色点云的配准,而且还提高了配准的匹配率和精度.

甘肃彩陶的几何风格迁移

甘肃彩陶在中国各类彩陶文化中拥有最为完整的时空序列,然而尚未有专门针对甘肃彩陶的风格迁移研究.为弘扬中华优秀传统文化,构建了甘肃彩陶数据集,提出了一种几何风格迁移方法.该方法生成了一个神经扭曲场,将甘肃彩陶变形为目标对象的几何风格,并保持了彩陶的纹理.网络结构方面加入了位置嵌入和特征增强模块,提高特征编码的质量.损失函数方面引入了形状一致性损失和平滑正则化项,防止彩陶的细节发生突变,提高变形效果.实验结果表明,该模型能够在甘肃彩陶与不同类的对象间进行大规模的几何风格迁移,同时可以保持良好的彩陶细节,产生新的视觉体验.