An Efficient Reliability-Based Optimization Method Utilizing High-Dimensional Model Representation and Weight-Point Estimation Method

The objective of reliability-based design optimization(RBDO)is to minimize the optimization objective while satisfying the corresponding reliability requirements.However,the nested loop characteristic reduces the efficiency of RBDO algorithm,which hinders their application to high-dimensional engineering problems.To address these issues,this paper proposes an efficient decoupled RBDO method combining high dimensional model representation(HDMR)and the weight-point estimation method(WPEM).First,we decouple the RBDO model using HDMR and WPEM.Second,Lagrange interpolation is used to approximate a univariate function.Finally,based on the results of the first two steps,the original nested loop reliability optimization model is completely transformed into a deterministic design optimization model that can be solved by a series of mature constrained optimization methods without any additional calculations.Two numerical examples of a planar 10-bar structure and an aviation hydraulic piping system with 28 design variables are analyzed to illustrate the performance and practicability of the proposed method.

Non-cooperative Space Target Estimation Algorithm Without Prior Information Dependence Based on Temporal Line of Sight Constraint

Under single-satellite observation,the parameter estimation of the boost phase of high-precision space noncooperative targets requires prior information.To improve the accuracy without prior information,we propose a parameter estimation model of the boost phase based on trajectory plane parametric cutting.The use of the plane passing through the geo-center and the cutting sequence line of sight(LOS)generates the trajectory-cutting plane.With the coefficient of the trajectory cutting plane directly used as the parameter to be estimated,a motion parameter estimation model in space non-cooperative targets is established,and the Gauss-Newton iteration method is used to solve the flight parameters.The experimental results show that the estimation algorithm proposed in this paper weakly relies on prior information and has higher estimation accuracy,providing a practical new idea and method for the parameter estimation of space non-cooperative targets under single-satellite warning.

Multi-Branch High-Dimensional Guided Transformer-Based 3D Human Posture Estimation

The human pose paradigm is estimated using a transformer-based multi-branch multidimensional directed the three-dimensional(3D)method that takes into account self-occlusion,badly posedness,and a lack of depth data in the per-frame 3D posture estimation from two-dimensional(2D)mapping to 3D mapping.Firstly,by examining the relationship between the movements of different bones in the human body,four virtual skeletons are proposed to enhance the cyclic constraints of limb joints.Then,multiple parameters describing the skeleton are fused and projected into a high-dimensional space.Utilizing a multi-branch network,motion features between bones and overall motion features are extracted to mitigate the drift error in the estimation results.Furthermore,the estimated relative depth is projected into 3D space,and the error is calculated against real 3D data,forming a loss function along with the relative depth error.This article adopts the average joint pixel error as the primary performance metric.Compared to the benchmark approach,the estimation findings indicate an increase in average precision of 1.8 mm within the Human3.6M sample.

Application of adaptive Kalman filter in rocket impact point estimation

In order to measure the parameters of flight rocket by using radar,rocket impact point was estimated accurately for rocket trajectory correction.The Kalman filter with adaptive filter gain matrix was adopted.According to the particle trajectory model,the adaptive Kalman filter trajectory model was constructed for removing and filtering the outliers of the parameters during a section of flight detected by three-dimensional data radar and the rocket impact point was extrapolated.The results of numerical simulation show that the outliers and noise in trajectory measurement signal can be removed effectively by using the adaptive Kalman filter and the filter variance can converge in a short period of time.Based on the relation of filtering time and impact point estimation error,choosing the filtering time of 8-10 scan get the minimum estimation error of impact point.

Estimation of annual variation of water vapor in the Arctic Ocean between 80°–87°N using shipborne GPS data based on kinematic precise point positioning

The measurement of atmospheric water vapor （WV） content and variability is important for meteorological and climatological research. A technique for the remote sensing of atmospheric WV content using ground-based Global Positioning System （GPS） has become available, which can routinely achieve accuracies for integrated WV content of 1-2 kg/m2. Some experimental work has shown that the accuracy of WV measurements from a moving platform is comparable to that of （static） land-based receivers. Extending this technique into the marine environment on a moving platform would be greatly beneficial for many aspects of meteorological research, such as the calibration of satellite data, investigation of the air-sea interface, as well as forecasting and climatological studies. In this study, kinematic precise point positioning has been developed to investigate WV in the Arctic Ocean （80°-87°N） and annual variations are obtained for 2008 and 2012 that are identical to those related to the enhanced greenhouse effect.

Non-cooperative target pose estimation based on improved iterative closest point algorithm

For localisation of unknown non-cooperative targets in space,the existence of interference points causes inaccuracy of pose estimation while utilizing point cloud registration.To address this issue,this paper proposes a new iterative closest point(ICP)algorithm combined with distributed weights to intensify the dependability and robustness of the non-cooperative target localisation.As interference points in space have not yet been extensively studied,we classify them into two broad categories,far interference points and near interference points.For the former,the statistical outlier elimination algorithm is employed.For the latter,the Gaussian distributed weights,simultaneously valuing with the variation of the Euclidean distance from each point to the centroid,are commingled to the traditional ICP algorithm.In each iteration,the weight matrix W in connection with the overall localisation is obtained,and the singular value decomposition is adopted to accomplish high-precision estimation of the target pose.Finally,the experiments are implemented by shooting the satellite model and setting the position of interference points.The outcomes suggest that the proposed algorithm can effectively suppress interference points and enhance the accuracy of non-cooperative target pose estimation.When the interference point number reaches about 700,the average error of angle is superior to 0.88°.

Comparison of two Bayesian-point-estimation methods in multiple-source localization

Environmental uncertainty represents the limiting factor in matched-field localization. Within a Bayesian framework, both the environmental parameters, and the source parameters are considered to be unknown variables. However, including environmental parameters in multiple-source localization greatly increases the complexity and computational demands of the inverse problem. In the paper, the closed-form maximumlikelihood expressions for source strengths and noise variance at each frequency allow these parameters to be sampled implicitly, substantially reducing the dimensionality and difficulty of the inversion. This paper compares two Bayesian-point-estimation methods： the maximum a posteriori（MAP） approach and the marginal posterior probability density（PPD） approach to source localization. The MAP approach determines the sources locations by maximizing the PPD over all source and environmental parameters. The marginal PPD approach integrates the PPD over the unknowns to obtain a sequence of marginal probability distribution over source range or depth.Monte Carlo analysis of the two approaches for a test case involving both geoacoustic and water-column uncertainties indicates that：（1） For sensitive parameters such as source range, water depth and water sound speed, the MAP solution is better than the marginal PPD solution.（2） For the less sensitive parameters, such as,bottom sound speed, bottom density, bottom attenuation and water sound speed, when the SNR is low, the marginal PPD solution can better smooth the noise, which leads to better performance than the MAP solution.Since the source range and depth are sensitive parameters, the research shows that the MAP approach provides a slightly more reliable method to locate multiple sources in an unknown environment.

Optimal Deep Convolutional Neural Network with Pose Estimation for Human Activity Recognition

Human Action Recognition(HAR)and pose estimation from videos have gained significant attention among research communities due to its applica-tion in several areas namely intelligent surveillance,human robot interaction,robot vision,etc.Though considerable improvements have been made in recent days,design of an effective and accurate action recognition model is yet a difficult process owing to the existence of different obstacles such as variations in camera angle,occlusion,background,movement speed,and so on.From the literature,it is observed that hard to deal with the temporal dimension in the action recognition process.Convolutional neural network(CNN)models could be used widely to solve this.With this motivation,this study designs a novel key point extraction with deep convolutional neural networks based pose estimation(KPE-DCNN)model for activity recognition.The KPE-DCNN technique initially converts the input video into a sequence of frames followed by a three stage process namely key point extraction,hyperparameter tuning,and pose estimation.In the keypoint extraction process an OpenPose model is designed to compute the accurate key-points in the human pose.Then,an optimal DCNN model is developed to classify the human activities label based on the extracted key points.For improving the training process of the DCNN technique,RMSProp optimizer is used to optimally adjust the hyperparameters such as learning rate,batch size,and epoch count.The experimental results tested using benchmark dataset like UCF sports dataset showed that KPE-DCNN technique is able to achieve good results compared with benchmark algorithms like CNN,DBN,SVM,STAL,T-CNN and so on.

An approximate point-based alternative for the estimation of variance under big BAF sampling

Background:A new variance estimator is derived and tested for big BAF(Basal Area Factor)sampling which is a forest inventory system that utilizes Bitterlich sampling(point sampling)with two BAF sizes,a small BAF for tree counts and a larger BAF on which tree measurements are made usually including DBHs and heights needed for volume estimation.Methods:The new estimator is derived using the Delta method from an existing formulation of the big BAF estimator as consisting of three sample means.The new formula is compared to existing big BAF estimators including a popular estimator based on Bruce’s formula.Results:Several computer simulation studies were conducted comparing the new variance estimator to all known variance estimators for big BAF currently in the forest inventory literature.In simulations the new estimator performed well and comparably to existing variance formulas.Conclusions:A possible advantage of the new estimator is that it does not require the assumption of negligible correlation between basal area counts on the small BAF factor and volume-basal area ratios based on the large BAF factor selection trees,an assumption required by all previous big BAF variance estimation formulas.Although this correlation was negligible on the simulation stands used in this study,it is conceivable that the correlation could be significant in some forest types,such as those in which the DBH-height relationship can be affected substantially by density perhaps through competition.We derived a formula that can be used to estimate the covariance between estimates of mean basal area and the ratio of estimates of mean volume and mean basal area.We also mathematically derived expressions for bias in the big BAF estimator that can be used to show the bias approaches zero in large samples on the order of 1n where n is the number of sample points.

基于PointNet++的机器人抓取姿态估计

为解决在无约束、部分遮挡的场景下对部分遮挡的物体生成可靠抓取姿态的问题,基于PointNet++网络改进了一种抓取姿态估计算法,该算法可直接从目标点云中生成二指夹具的抓取姿态。由于该算法降低了抓取姿态的维度,将抓取的7自由度问题转变成4自由度问题处理,从而简化学习的过程加快了学习速度。实验结果表明:该算法在无约束、部分遮挡的场景中,能够生成有效的抓取姿态,且较Contact-GraspNet算法成功抓取率提升了约12%,能够应用于家用机器人的抓取任务。

Fast Estimation of Loader’s Shovel Load Volume by 3D Reconstruction of Material Piles

Fast and accurate measurement of the volume of earthmoving materials is of great signifcance for the real-time evaluation of loader operation efciency and the realization of autonomous operation. Existing methods for volume measurement, such as total station-based methods, cannot measure the volume in real time, while the bucket-based method also has the disadvantage of poor universality. In this study, a fast estimation method for a loader’s shovel load volume by 3D reconstruction of material piles is proposed. First, a dense stereo matching method (QORB–MAPM) was proposed by integrating the improved quadtree ORB algorithm (QORB) and the maximum a posteriori probability model (MAPM), which achieves fast matching of feature points and dense 3D reconstruction of material piles. Second, the 3D point cloud model of the material piles before and after shoveling was registered and segmented to obtain the 3D point cloud model of the shoveling area, and the Alpha-shape algorithm of Delaunay triangulation was used to estimate the volume of the 3D point cloud model. Finally, a shovel loading volume measurement experiment was conducted under loose-soil working conditions. The results show that the shovel loading volume estimation method (QORB–MAPM VE) proposed in this study has higher estimation accuracy and less calculation time in volume estimation and bucket fll factor estimation, and it has signifcant theoretical research and engineering application value.

Enhanced 3D Point Cloud Reconstruction for Light Field Microscopy Using U-Net-Based Convolutional Neural Networks

This article describes a novel approach for enhancing the three-dimensional(3D)point cloud reconstruction for light field microscopy(LFM)using U-net architecture-based fully convolutional neural network(CNN).Since the directional view of the LFM is limited,noise and artifacts make it difficult to reconstruct the exact shape of 3D point clouds.The existing methods suffer from these problems due to the self-occlusion of the model.This manuscript proposes a deep fusion learning(DL)method that combines a 3D CNN with a U-Net-based model as a feature extractor.The sub-aperture images obtained from the light field microscopy are aligned to form a light field data cube for preprocessing.A multi-stream 3D CNNs and U-net architecture are applied to obtain the depth feature fromthe directional sub-aperture LF data cube.For the enhancement of the depthmap,dual iteration-based weighted median filtering(WMF)is used to reduce surface noise and enhance the accuracy of the reconstruction.Generating a 3D point cloud involves combining two key elements:the enhanced depth map and the central view of the light field image.The proposed method is validated using synthesized Heidelberg Collaboratory for Image Processing(HCI)and real-world LFM datasets.The results are compared with different state-of-the-art methods.The structural similarity index(SSIM)gain for boxes,cotton,pillow,and pens are 0.9760,0.9806,0.9940,and 0.9907,respectively.Moreover,the discrete entropy(DE)value for LFM depth maps exhibited better performance than other existing methods.

基于PointNet改进的无序工件点云配准算法

在无序工件抓取场景中,待抓取的工件处于散乱、堆叠的状态,抓取难度较大,传统配准算法精度不高。针对工件存在堆叠和点云数据含有噪声的场景下,无序工件点云配准的准确性不高的问题,研究提出基于PointNet改进的三维点云配准算法对无序工件进行位姿估计。算法用于模板点云和目标点云的特征提取和匹配,并结合ICP算法求解无序工件的位姿参数,最后通过迭代方式提高点云配准精度。采用结构光相机作为点云数据采集设备,以多种不同形状的工业零件作为配准对象,将采集得到的场景点云数据进行点云配准。实验制作并使用无序工件数据集(WorkpiecesDataSet)训练并测试点云配准网络的性能。实验表明,提出的网络模型(i-SAM)在点云配准任务中具有较小的旋转和平移误差,点云模型数据的误差为(0.783,0.011),场景点云数据的配准误差为(1.269,0.016)。与主流算法相比,对含有噪声和不完整的点云具有较强的鲁棒性。

一种基于蒙特卡洛方法的配电网概率可靠性快速计算方法

配电网的概率可靠性能够弥补传统可靠性指标的期望值仅从均值角度衡量系统可靠性的不足,但随着配电网规模扩大以及数据量的剧增,能够同时兼顾计算准确性与计算速度的概率可靠性计算方法是亟待研究的。为此,提出一种基于蒙特卡洛方法的配电网概率可靠性快速计算方法,利用改进三点估计法以及三阶多项式正态变换,在保留输入变量相关性的同时有效缩减输入样本点规模,并采用级数展开得到概率可靠性。首先采用改进三点估计法,在独立标准正态空间内选取样本点,再通过三阶多项式正态变换将其转换为原始变量空间的样本点;接着采用序贯蒙特卡洛方法,在考虑孤岛划分的情况下对样本点进行可靠性计算;最后通过Edgeworth级数展开,得到可靠性指标的概率分布。对改进的IEEE-RBTS Bus6的F4馈线进行算例分析,结果表明:该文所提方法与传统蒙特卡洛方法的配电网系统可靠性计算结果之间仅存在2.195%的最大偏差,而该文所提方法计算时间仅为传统蒙特卡洛方法的1.05%,证明该文所提方法在保证较高精度的同时可以显著提升计算速度。

设有叠合柱的局部错层RC框架结构地震易损性分析

为研究某一设有叠合柱的局部错层钢筋混凝土(reinforced concrete,RC)框架结构在近断层和远场地震作用下的破坏概率,自定义钢管混凝土叠合柱塑性铰参数,并与试验对比验证塑性铰参数的有效性。采用SAP2000建立非线性分析模型,选取近断层和远场地震波共22条,分别以地震峰值加速度(peak ground acceleration,PGA)和最大层间位移角作为地震动强度指标和结构性能指标,基于增量动力分析(incremental dynamic analysis,IDA)结果和点估计函数对错层框架结构进行易损性分析。结果表明:对于远场地震动,结构满足“三水准”抗震设防要求,在罕遇地震下超越防止倒塌极限状态的概率仅为0.24%;结构在近断层多遇地震下仍能满足“小震不坏”的设计要求,设防地震下结构超越修复后使用极限状态的概率为53.63%,发生中等破坏的概率较大,罕遇地震下结构达到倒塌极限状态的概率为5.37%,较远场地震作用破坏更为严重。研究结果可为错层框架结构的设计和地震风险评估提供参考。

利用点云处理的实时的类别级位姿估计

针对传统的视觉算法无法准确地测量物体3D质心和尺寸、无法检测数据集中未出现过的物体等问题,提出一种基于点云的类别级物体质心与位姿估计算法.首先通过2D分割算法对物体待检测区域进行分割,并通过BlendMask提高实时性;然后将分割区域生成点云,并结合先验形状输入到神经网络中重建物体模型;最后输出一个变形场以及对应矩阵,并通过Umeyama算法对物体进行位姿估计.实验结果表明,所提算法达到了较高的精度;在质心估计方面也优于包络盒中心作为质心的算法;实时速率达到了13帧/s.在GPUNVIDIA2060上进行仿真实验,证明了所提算法计算的质心优于对比算法,以及该算法的准确性及可靠性.

基于空间传播的多视图三维重建

针对多视图三维重建任务中点云完整性欠佳的问题,提出一种基于空间传播的多视图深度估计网络(SPMVSNet)。引入空间传播思想用于复杂条件下的稠密点云重建,并分别设计基于空间传播的混合深度假设策略和空间感知优化模块。混合深度假设策略采用由粗糙到精细的深度推理方式,将深度估计视为多标签分类任务,对正则化概率体执行交叉熵损失以约束代价体,从而避免回归方法过拟合和收敛速度过慢的问题。空间感知优化模块从包含高级语义特征表示的特征图中获得引导,在进行置信度检查后采用卷积空间传播网络,通过构建亲和矩阵来细化最终的深度图。同时,为解决大多数方法存在的对不满足多视图一致性的不可靠区域重建质量较低的问题,进一步结合注意力机制设计具有样本自适应能力的动态特征提取网络,用于增强模型的局部感知能力。实验结果表明,在DTU数据集上,SP-MVSNet的重建完整性相比于CVP-MVSNet提升32.8%,整体质量提升11.4%。在Tanks and Temples基准和Blended MVS数据集上,SP-MVSNet的表现也优于大多数已知方法,取得了良好的三维重建效果。

基于深度学习的二维人体姿态估计综述

人体姿态估计是近年来计算机视觉问题中的一个热门话题,它在改善人类生活方面具有巨大的益处和潜在的应用。近年来深度神经网络得到快速发展,相较于传统方法而言,采用深度学习的方法更能提取图像表征信息。综合分析近年来人体姿态估计的进展,根据检测人数分为单人和多人人体姿态估计。针对单人姿态估计,介绍了基于直接预测人体坐标点的坐标回归方法及基于预测人体关键点高斯分布的热图检测方法;针对多人姿态估计,采用解决多人到解决单人过程的自顶向下方法和直接处理多人关键点的自底向上方法。总结了各方法网络结构的特点和优缺点,并阐述当前面临的问题及未来发展趋势。

多尺度特征融合的点云配准算法研究

现有点云配准算法提取的特征不够丰富,导致配准精度很难进一步提升。针对该问题,本文提出一种基于深度学习的多尺度特征融合点云配准算法。首先,利用EdgeConv提取多个不同尺度的特征,该特征能够保持局部几何结构特性;接着,引入非线性极化注意力对其输出特征进行筛选,从而提高特征信息的有效性;然后,将以上多尺度特征进行融合并再次利用EdgeConv提取其特征,从而提高特征的表达能力;在刚体姿态估计阶段,采用线性李代数处理旋转变换以充分挖掘点云中的变换信息;最后,根据配准过程中提取点云特征的变化,动态调整损失函数各组成部分的权重,获得更准确的模型预测结果。在ModelNet40数据集上进行实验,本文算法在训练集和测试集样本种类相同时的旋转误差为1.8267,位移误差为0.0010;在训练集和测试集的样本种类不相同时(泛化实验)的旋转误差为2.9794,位移误差为0.0010。实验结果表明,本文算法的配准精度相比当前主流算法均有提高且泛化性能较好。

地基微波辐射计露点温度廓线估算方案及初步应用

面向业务和台站实际,针对露点温度直接和间接计算经验公式的不确定性,结合地基微波辐射计LV2级数据特征,开展了露点温度估算方案适用性及应用讨论,旨在为预报员提供高时空分辨率的基础物理量露点温度来判识大气饱和程度,服务于强对流天气预报预警分析。研究表明:(1)相对湿度是主导露点温度直接和间接计算公式计算结果差异的敏感因子。地基微波辐射计露点温度估算方案可为相对湿度小于50%时,采用直接计算公式;相对湿度为50%~99%时,采用间接计算公式;相对湿度为100%(饱和)时,温度大于-48.75℃,采用间接计算公式,温度小于-48.75℃,采用直接计算公式。(2)地基微波辐射计估算的露点温度产品精度保持了温度产品的高相关性,较大程度上改善了系统偏差,但离散程度略有扩大。其中,相关系数由0.99变成0.98,降低了0.01;系统性偏差由-3.18℃变成-0.98℃,缩小了2.2℃;均方差由4.92℃变成5.26℃,扩大了0.34℃。(3)相较相对湿度,估算的露点差对高湿区(相对湿度大于70%以上)较为“敏感”,能很好地“勾勒”出云等水凝物内部水汽饱和状态及其特征结构,便于用户判断出饱和区、非饱和区及两者过渡区;与地基微波辐射计直接测量产品联合,可监测强对流天气发生前、中、后水凝物垂直结构特征及其演变,便于天气预报预警,其中预警提前量可达0.5~1.0 h,降水结束预报提前量接近10 min。