检索结果-内蒙古大学图书馆

Multilevel Optimization for Registration of Deformable point Clouds

IEEE TRANSACTIONS ON IMAGE PROCESSING 2020年 29卷 8735-8746页

作者： Chaudhury, Ayan INRIA Grenoble Rhone Alpes F-69364 Lyon France Ecole Normale Super Lyon F-69364 Lyon France

Handling deformation is one of the biggest challenges associated with point cloud registration. When deformation happens due to the motion of an animated object which actively changes its location and general shape, registration of two instances of the same object turns out to be a challenging task. The focus of this work is to address the problem by leveraging the complementary attributes of local and global geometric structures of the point clouds. We define an energy function which consists of local and global terms, as well as a semi-local term to model the intermediate level geometry of the point cloud. The local energy estimates the transformation parameters at the lowest level by assuming a reduced deformation model. The parameters are estimated in a closed form solution, which are then used to assign the initial probability of a stochastic model working at the intermediate level. The global energy term estimates the overall transformation parameters by minimizing a nonlinear least square function via Gauss-Newton optimization framework. The total energy is optimized in a block coordinate descent fashion, updating one term at a time while keeping others constant. Experiments on three publicly available datasets show that the method performs significantly better than several state-of-the-art algorithms in registering pairwise point cloud data.

关键词： Strain Three-dimensional displays Geometry Shape Deformable models Optimization iterative closest point algorithm Deformable registration quaternion gauss-newton nonlinear least squares Gaussian mixture model expectation maximization

来源：评论

学校读者我要写书评

暂无评论

Calibration of robot DH parameters based on structured light camera

Calibration of robot DH parameters based on structured light...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Yuntaek Oh Minwoo Na Jae-Bok Song Department of Mechanical Engineering Korea University Seoul Korea

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

This study presents a new calibration method using a structured-light camera for low-cost recalibration of the Denavit-Hartenberg (DH) parameters in collaborative robots. Although laser trackers provide high accuracy, they are very expensive and the procedure is complex. In contrast, structured-light cameras are inexpensive and easy to use, making them suitable for the calibration of DH parameters in collaborative robots. Experiments were conducted using the structured-light camera from ZIVID and the UR5 model from Universal Robots. The point-to-plane iterative closest point (ICP) technique was used to measure the positions of the robot base and calibration tool, and the DH parameters were adjusted using the Levenberg-Marquardt method's least-squares approach. The results showed that calibration accuracy improved with repetition, and repeated calibrations reduced the position error to an average of 1.85mm and the orientation error to an average of 0.43°. The proposed method can be usefully applied in fields where micro-level precision is not required or where automation of calibration is needed.

关键词： Automation Accuracy iterative closest point algorithm Robot vision systems Collaborative robots Position measurement Cameras Laser modes Calibration iterative methods

来源：评论

学校读者我要写书评

暂无评论

point cloud registration for LiDAR and photogrammetric data: A critical synthesis and performance analysis on classic and deep learning algorithms

引用

ISPRS Open Journal of Photogrammetry and Remote Sensing 2023年 8卷

作者： Xu, Ningli Qin, Rongjun Song, Shuang Geospatial Data Analytics Lab The Ohio State University Columbus United States Department of Civil Environmental and Geodetic Engineering The Ohio State University Columbus United States Department of Electrical and Computer Engineering The Ohio State University Columbus United States Translational Data Analytics Institute The Ohio State University Columbus United States

Three-dimensional (3D) point cloud registration is a fundamental step for many 3D modeling and mapping applications. Existing approaches are highly disparate in the data source, scene complexity, and application, therefore the current practices in various point cloud registration tasks are still ad-hoc processes. Recent advances in computer vision and deep learning have shown promising performance in estimating rigid/similarity transformation between unregistered point clouds of complex objects and scenes. However, their performances are mostly evaluated using a limited number of datasets from a single sensor (e.g. Kinect or RealSense cameras), lacking a comprehensive overview of their applicability in photogrammetric 3D mapping scenarios. In this work, we provide a comprehensive review of the state-of-the-art (SOTA) point cloud registration methods, where we analyze and evaluate these methods using a diverse set of point cloud data from indoor to satellite sources. The quantitative analysis allows for exploring the strengths, applicability, challenges, and future trends of these methods. In contrast to existing analysis works that introduce point cloud registration as a holistic process, our experimental analysis is based on its inherent two-step process to better comprehend these approaches including feature/keypoint-based initial coarse registration and dense fine registration through cloud-to-cloud (C2C) optimization. More than ten methods, including classic hand-crafted, deep-learning-based feature correspondence, and robust C2C methods were tested. We observed that the success rate of most of the algorithms are fewer than 40% over the datasets we tested and there are still are large margin of improvement upon existing algorithms concerning 3D sparse corresopondence search, and the ability to register point clouds with complex geometry and occlusions. With the evaluated statistics on three datasets, we conclude the best-performing methods for each step and prov

关键词： Deep learning iterative closest point algorithm point cloud registration Terrestrial laser scanning

来源：评论

学校读者我要写书评

暂无评论

Research on Environmental Perception of Smart Cane Based on Multi-Sensor Fusion

Research on Environmental Perception of Smart Cane Based on ...

引用

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems

作者： Hao Teng Haiyan Shao Bin Chen Bo Chen Xuan Sun Zhen Zhao School of Mechanical Engineering University of Jinan Jinan Shandong China Shandong Youbaote Intelligent Robotics Co Ltd of Jinan Jinan Shandong China Linyi Lingong Intelligent Information Technology Co. Ltd Shandong China

ISBN: (数字)9798331506056

ISBN: (纸本)9798331506063

The article addresses the issues encountered when using a single LiDAR or monocular camera for mapping in the indoor environment perception of smart canes. These issues include incomplete obstacle detection or suboptimal mapping effects and the problem of motion distortion in Lidar point clouds. Firstly, in the LiDAR preprocessing stage, we propose the IPL-ICP(IMU and point to Line iterative closest point) algorithm, which is a fusion of IMU and PL-ICP, to address the Lidar point cloud distortion caused by the rapid movement of the smart cane. This algorithm aims to correct the motion distortion of Lidar point clouds to improve matching accuracy and speed. Secondly, the Gmapping algorithm, which removes Lidar point cloud motion distortion, is employed for the Lidar range-finder, while the ORB-SLAM2 algorithm is utilized for the monocular camera to construct local grid maps. These maps are then mutually fused according to Bayesian estimation rules to build a global grid map. The indoor scene experiments indicate that this method not only obtains more complete and accurate environmental map information, but also achieves an approximately 35.2% improvement in mapping accuracy compared to traditional LiDAR and camera mapping methods. Furthermore, this method exhibits stronger environmental perception capabilities, meeting practical requirements.

关键词： point cloud compression Laser radar Accuracy Simultaneous localization and mapping iterative closest point algorithm Robot vision systems Distortion Cameras Intelligent systems Robots

来源：评论

学校读者我要写书评

暂无评论

GMMCalib: Extrinsic Calibration of LiDAR Sensors using GMM-based Joint Registration

GMMCalib: Extrinsic Calibration of LiDAR Sensors using GMM-b...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Ilir Tahiraj Felix Fent Philipp Hafemann Egon Ye Markus Lienkamp TUM School of Engineering and Design Chair of Automotive Technology Technical University of Munich TUM School of Computation Information and Technology Professorship of Cyber Physical Systems Technical University of Munich

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

State-of-the-art LiDAR calibration frameworks mainly use non-probabilistic registration methods such as iterative closest point (ICP) and its variants. These methods suffer from biased results due to their pair-wise registration procedure as well as their sensitivity to initialization and parameterization. This often leads to misalignments in the calibration process. Probabilistic registration methods compensate for these drawbacks by specifically modeling the probabilistic nature of the observations. This paper presents GMMCalib, an automatic target-based extrinsic calibration approach for multi-LiDAR systems. Using an implementation of a Gaussian Mixture Model (GMM)-based registration method that allows joint registration of multiple point clouds, this data-driven approach is compared to ICP algorithms. We perform simulation experiments using the digital twin of the EDGAR research vehicle and validate the results in a real-world environment. We also address the local minima problem of local registration methods for extrinsic sensor calibration and use a distance-based metric to evaluate the calibration results. Our results show that an increase in robustness against sensor miscalibrations can be achieved by using GMM-based registration algorithms. The code is open source and available on GitHub 3 .

关键词： point cloud compression Laser radar Sensitivity iterative closest point algorithm Robot sensing systems Probabilistic logic Robustness Calibration iterative methods Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

MULLS: Versatile LiDAR SLAM via Multi-metric Linear Least Square

MULLS: Versatile LiDAR SLAM via Multi-metric Linear Least Sq...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Pan, Yue Xiao, Pengchuan He, Yujie Shao, Zhenlei Li, Zesong Swiss Fed Inst Technol Dept Civil Environm & Geomat Engn Zurich Switzerland Hesai Technol Co Ltd Shanghai Peoples R China Ecole Polytech Fed Lausanne Sch Engn Lausanne Switzerland

ISBN: (纸本)9781728190778

The rapid development of autonomous driving and mobile mapping calls for off-the-shelf LiDAR SLAM solutions that are adaptive to LiDARs of different specifications on various complex scenarios. To this end, we propose MULLS, an efficient, low-drift, and versatile 3D LiDAR SLAM system. For the front-end, roughly classified feature points (ground, facade, pillar, beam, etc.) are extracted from each frame using dual-threshold ground filtering and principal components analysis. Then the registration between the current frame and the local submap is accomplished efficiently by the proposed multi-metric linear least square iterative closest point algorithm. point-to-point (plane, line) error metrics within each point class are jointly optimized with a linear approximation to estimate the ego-motion. Static feature points of the registered frame are appended into the local map to keep it updated. For the back-end, hierarchical pose graph optimization is conducted among regularly stored history submaps to reduce the drift resulting from dead reckoning. Extensive experiments are carried out on three datasets with more than 100,000 frames collected by seven types of LiDAR on various outdoor and indoor scenarios. On the KITTI benchmark, MULLS ranks among the top LiDAR-only SLAM systems with real-time performance.

关键词： Measurement Laser radar Simultaneous localization and mapping Three-dimensional displays iterative closest point algorithm Linear approximation Feature extraction

来源：评论

学校读者我要写书评

暂无评论

The Fusion-ICP Data Registration algorithm Using Ortogonal Transformations for 3D Reconstructing of an Archaeological Sites' Models

The Fusion-ICP Data Registration Algorithm Using Ortogonal T...

引用

International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)

作者： A. Vokhmintcev A. Mityanina M. Romanov Institute of Information Technology Chelyabinsk State University Chelyabinsk Russia Institute of Digital Economy Ugra State University Khanty-Mansiysk Russia South Ural State University Chelyabinsk Russia

ISBN: (数字)9798350395013

ISBN: (纸本)9798350395020

In this paper a system for the detection and research of archaeological sites using on machine learning methods, mapping methods and geophysics methods is presented. The development of an information system for remote archaeological research allows, on the one hand, to solve the most important problem of archaeological science, related to the preservation of cultural heritage, and on the other hand, to reduce the duration of the archaeological examination procedure conducted before the industrial development of the territory. In this paper the method for registering 3D data based on ICP (iterative closest points) based on fusion of visual and semantic characteristics of an archaeological site for a class of orthogonal transformations was proposed. Computer modeling of the proposed 3d registration method was carried out using a collection of data from archaeological sites of the Bronze Age of the Southern Trans-Urals. When performing computer modeling, methods for solving the variational ICP problem were considered, using various options for minimizing the functional: the point-to-point metric with and without extrapolation, using the point-to-plane metric. A comparative analysis with various options for minimizing the functional was carried out, the results of computer simulation were presented and discussed.

关键词： Measurement point cloud compression Solid modeling Three-dimensional displays iterative closest point algorithm Computational modeling Data models

来源：评论

学校读者我要写书评

暂无评论

A Fast Synthetic-Frame Method for MIMO Radar Global Imaging

A Fast Synthetic-Frame Method for MIMO Radar Global Imaging

引用

Cross Strait Quad-Regional Radio Science and Wireless Technology Conference (CSRWTC)

作者： Xiaocha Liu Kai Tan Xiaoyi Wang Guo-Min Yang Lirong Zheng Key Laboratory of Information Science of Electromagnetic Waves Fudan University China College of Electronic and Information Engineering Tongji University China

ISBN: (数字)9798331507794

ISBN: (纸本)9798331507800

This paper introduces a novel method for synthesizing high-resolution MIMO radar images on a frame-by-frame basis, specifically designed for scanning environments from moving platforms. Leveraging higher solution millimeter-wave radar, the approach employs Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to cluster point clouds into distinct objects for each image frame. Subsequently, image frames are aligned using the iterative closest point (ICP) algorithm to compute the relative motion between them. These frames are then combined to reconstruct a comprehensive image of the entire scanned environment. Notably, this method achieves high-resolution imaging without the need for supplementary hardware such as cameras, GPS, or IMU systems, thereby significantly reducing costs. The effectiveness and efficiency of this approach make it particularly valuable for environmental sensing and map construction in robotics and autonomous driving applications.

关键词： iterative closest point algorithm MIMO radar Noise Radar imaging Millimeter wave radar Hardware Topology Sensors iterative methods Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Simulation of Data Fusion Model of Power Grid Geographic Information System Based on Image Processing algorithm

Simulation of Data Fusion Model of Power Grid Geographic Inf...

引用

Software Engineering, Social Network Analysis and Intelligent Computing (SSAIC), Asia-Pacific Conference on

作者： Shiping Yang Heng Liu Li Wang Dongjunming Yang Zhen Li Guizhou Power Grid Company Limited Guiyang Guizhou China

ISBN: (数字)9798350393682

ISBN: (纸本)9798350393699

Because the influence of GIS (Geographic Information System) is mostly from satellite images, and the images collected by satellite sensor system are restricted and influenced by the platform, the position and angle of the sun and other conditions, it will show some phenomena such as fuzziness, distortion, distortion and speckle noise, which will reduce the image quality to a certain extent, so the application of image processing technology is essential. Based on this, this paper designs a GIS data fusion model of power grid based on image processing algorithm according to the differences of digital images, spaces and general attribute structures. Using binary segmentation method can complete image segmentation in power grid GIS platform. ICP (iterative closest point) algorithm is used to match DEM (Digital Elevation Model) with 3D GIS. Through repeated iteration, the transformation matrix gradually approaches the real value, thus realizing registration. The research results show that the results can be obtained directly by using DEM and GIS data, and there is no frequent and time-consuming conversion, so the data fusion method can be used to realize the overall integration of GIS and DEM. When DEM data is registered with 3D GIS, the rotation matrix and translation vector obtained from registration can be used to realize the updating of 3D GIS by DEM, which proves the feasibility of this method.

关键词： Image segmentation Three-dimensional displays Image recognition iterative closest point algorithm Digital images Data integration Power grids

来源：评论

学校读者我要写书评

暂无评论

3D point Cloud Coarse Registration algorithm Based on Center of Gravity and Centroid Transformation

3D Point Cloud Coarse Registration Algorithm Based on Center...

引用

Frontiers of Computer Science and Information Technology (FCSIT), Euro-Asia Conference on

作者： Shuifa Sun Kun Xia Ning Wei Yongheng Tang Yaobin Zou Yirong Wu China Three Gorges University Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering Yichang Key Laboratory of Intelligent Medicine China Three Gorges University College of Computer and Information Technology China Three Gorges University College of Computer and Information Technology China Three Gorges University Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges University College of Computer and Information Technology China Three Gorges University Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges University Colleg e of Economics and Management

It is easy to fall into a local optimum for registration algorithms, such as iterative closest point (ICP) algorithm in 3-D point cloud registration. In this study, a coarse registration algorithm based on the transformation of the geometric center of gravity and the centroid is proposed. Firstly, the noise and outliers are removed by using the filters for the point clouds. Then, a preliminary model of rotational transformation of point the clouds is established through the analysis of the relation of the gravity center and centroid of two point clouds. Moreover, according to the relation between rotation angle and registration error, an iterative rotation model is established to obtain the optimal rotation angle. Finally, ICP algorithm is applied to further improve registration performance. The experimental results show that the proposed coarse registration algorithm demonstrates superior performance, compared with the registration methods relying on the overlapped center of gravity.

关键词： point cloud compression Three-dimensional displays iterative closest point algorithm Toy manufacturing industry Filtering algorithms Information filters Data models

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：