scholarly journals Virtual Namesake Point Multi-Source Point Cloud Data Fusion Based on FPFH Feature Difference

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5441
Author(s):  
Li Zheng ◽  
Zhukun Li
Keyword(s):  
Data Fusion ◽  
Point Cloud ◽  
Bundle Adjustment ◽  
Target Point ◽  
Point Cloud Data ◽  
Icp Algorithm ◽  
Cloud Data ◽  
Advantages And Disadvantages ◽  
Source Point ◽  
Feature Difference

There are many sources of point cloud data, such as the point cloud model obtained after a bundle adjustment of aerial images, the point cloud acquired by scanning a vehicle-borne light detection and ranging (LiDAR), the point cloud acquired by terrestrial laser scanning, etc. Different sensors use different processing methods. They have their own advantages and disadvantages in terms of accuracy, range and point cloud magnitude. Point cloud fusion can combine the advantages of each point cloud to generate a point cloud with higher accuracy. Following the classic Iterative Closest Point (ICP), a virtual namesake point multi-source point cloud data fusion based on Fast Point Feature Histograms (FPFH) feature difference is proposed. For the multi-source point cloud with noise, different sampling resolution and local distortion, it can acquire better registration effect and improve the accuracy of low precision point cloud. To find the corresponding point pairs in the ICP algorithm, we use the FPFH feature difference, which can combine surrounding neighborhood information and have strong robustness to noise, to generate virtual points with the same name to obtain corresponding point pairs for registration. Specifically, through the establishment of voxels, according to the F2 distance of the FPFH of the target point cloud and the source point cloud, the convolutional neural network is used to output a virtual and more realistic and theoretical corresponding point to achieve multi-source Point cloud data registration. Compared with the ICP algorithm for finding corresponding points in existing points, this method is more reasonable and more accurate, and can accurately correct low-precision point cloud in detail. The experimental results show that the accuracy of our method and the best algorithm is equivalent under the clean point cloud and point cloud of different resolutions. In the case of noise and distortion in the point cloud, our method is better than other algorithms. For low-precision point cloud, it can better match the target point cloud in detail, with better stability and robustness.

scholarly journals Multi-sensor point cloud data fusion for precise 3D mapping

2021 ◽  
Author(s):  
Mohamed Abdelazeem ◽  
Ahmed Elamin ◽  
Akram Afifi ◽  
Ahmed El-Rabbany
Keyword(s):  
Data Fusion ◽  
Point Cloud ◽  
3D Mapping ◽  
Point Cloud Data ◽  
Cloud Data

scholarly journals A GROSS ERROR ELIMINATION METHOD FOR POINT CLOUD DATA BASED ON KD-TREE

2018 ◽  
Vol XLII-3 ◽  
pp. 719-722 ◽  
Author(s):  
Q. Kang ◽  
G. Huang ◽  
S. Yang
Keyword(s):  
Point Cloud ◽  
Nearest Neighbor ◽  
Target Point ◽  
Point Cloud Data ◽  
K Nearest Neighbor ◽  
Cloud Data ◽  
Gross Error ◽  
Error Elimination ◽  
K Nearest Neighbor Algorithm ◽  
Key Steps

Point cloud data has been one type of widely used data sources in the field of remote sensing. Key steps of point cloud data’s pro-processing focus on gross error elimination and quality control. Owing to the volume feature of point could data, existed gross error elimination methods need spend massive memory both in space and time. This paper employed a new method which based on Kd-tree algorithm to construct, k-nearest neighbor algorithm to search, settled appropriate threshold to determine with result turns out a judgement that whether target point is or not an outlier. Experimental results show that, our proposed algorithm will help to delete gross error in point cloud data and facilitate to decrease memory consumption, improve efficiency.

scholarly journals The Segmentation Method of Target Point Cloud for Polarization-Modulated 3D Imaging

Sensors ◽  
2019 ◽  
Vol 20 (1) ◽  
pp. 179 ◽  
Author(s):  
Shengjie Wang ◽  
Bo Liu ◽  
Zhen Chen ◽  
Heping Li ◽  
Shuo Jiang
Keyword(s):  
Time Resolution ◽  
Point Cloud ◽  
3D Imaging ◽  
Test Method ◽  
Target Point ◽  
Point Cloud Data ◽  
Segmentation Method ◽  
Electron Multiplier ◽  
Cloud Data ◽  
Gray Image

To implement target point cloud segmentation for a polarization-modulated 3D imaging system in practical projects, an efficient segmentation concept of multi-dimensional information fusion is designed. As the electron multiplier charge coupled device (EMCCD) camera can only acquire the gray image, but has no ability for time resolution owing to the time integration mechanism, large diameter electro-optic modulators (EOM) are used to provide time resolution for the EMCCD cameras to obtain the polarization-modulated images, from which a 3D image can also be simultaneously reconstructed. According to the characteristics of the EMCCD camera’s plane array imaging, the point-to-point mapping relationship between the gray image pixels and point cloud data coordinates is established. The target’s pixel coordinate position obtained by image segmentation is mapped to 3D point cloud data to get the segmented target point cloud data. On the basis of the specific environment characteristics of the experiment, the maximum entropy test method is applied to the target segmentation of the gray image, and the image morphological erosion algorithm is used to improve the segmentation accuracy. This method solves the problem that conventional point clouds’ segmentation methods cannot effectively segment irregular objects or closely bound objects. Meanwhile, it has strong robustness and stability in the presence of noise, and reduces the computational complexity and data volume. The experimental results show that this method is better for the segmentation of the target in the actual environment, and can avoid the over-segmentation and under-segmentation to some extent. This paper illustrates the potential and feasibility of the segmentation method based on this system in real-time data processing.

The Study of Point Cloud Data Automatic Merging Technology in 3D Measuring

2011 ◽  
Vol 109 ◽  
pp. 621-625
Author(s):  
Fa Su ◽  
Jun Ting Cheng
Keyword(s):  
Reference Point ◽  
Point Cloud ◽  
Reference Points ◽  
3D Point Cloud ◽  
Point Cloud Data ◽  
Icp Algorithm ◽  
Cloud Data ◽  
Merging Process

The measuring of the 3D point cloud data in automatic merging process, it is affixed to the surface of an object to be tested through a reference point on the position, to realize the multi point cloud data automatic seamless splicing.The paper presents the monotone limited algorithm in the acquisition of reference point, this algorithm can effectively and accurately to the reference point for judging and extraction.and puts forward an algorithm which integrates with three reference points orientation principle and ICP algorithm. The algorithm not only realizes the merging, but also raises the efficiency to dozens of times based on raising reorientation precision.

A New Simplification Method within Deviation Parameters and Allowed Angles

2012 ◽  
Vol 566 ◽  
pp. 239-243
Author(s):  
Na Meng ◽  
Xin Li Chen ◽  
Yi Qi Zhou ◽  
Bao Qing Dai
Keyword(s):  
Surface Reconstruction ◽  
Point Cloud ◽  
Practical Method ◽  
Point Cloud Data ◽  
Memory Space ◽  
Cloud Data ◽  
Advantages And Disadvantages ◽  
Research Situation ◽  
Improved Algorithm ◽  
At Home

Research situation at home and abroad is described in detail about simplification methods of point cloud data. After analyzing the advantages and disadvantages of existing algorithms, an improved algorithm, a method combining with deviation parameters and allowed angles to simply mass cloud data, is proposed from several aspects of complexity, required time and memory space. The experiments show that the simplified point cloud have a great relationship with the selected tolerance value. And the point cloud after simplification has advantages of high reservation of curve and surface reconstruction perfectly, which is reserved enough data. The proposed simplification algorithm is an effective and practical method.

Registration Algorithm for Three-Dimensional Point Cloud Data

2015 ◽  
Vol 741 ◽  
pp. 237-240
Author(s):  
Li Lun Huang ◽  
Wen Guo Li ◽  
Qi Le Yang ◽  
Ying Chun Chen
Keyword(s):  
Point Cloud ◽  
Three Dimensional ◽  
Singular Value ◽  
3D Point Cloud ◽  
Point Cloud Data ◽  
Icp Algorithm ◽  
Cloud Data ◽  
Registration Algorithm ◽  
Mathematical Algorithms ◽  
Value Decomposition

The principle of registration of the 3D point cloud data and the current algorithms are compared, and ICP algorithm is chosen since its fast convergence speed, high precision, and simple objective function. On the basis of ICP algorithm, singular value decomposition and four-array method are analysed by programming program, and all the mathematical algorithms is transformed into programming language by Matlab software.

scholarly journals Building 3D Realistic Modeling Based on Air-ground Multi-source Data Fusion

2020 ◽  
Vol 213 ◽  
pp. 03025
Author(s):  
Yan Wang ◽  
Tingting Zhang ◽  
Jingyi Wang
Keyword(s):  
Data Fusion ◽  
Point Cloud ◽  
Laser Scanning ◽  
Spatial Information ◽  
Complex Structure ◽  
Three Dimensional ◽  
Point Cloud Data ◽  
3D Laser Scanning ◽  
Cloud Data ◽  
Source Data

Three-dimensional point cloud data is a new form of three-dimensional collection, which not only contains the geometric topology information of the object, but also has high simplicity and flexibility. In this paper, the air-ground multi-source data fusion technology is used to study the fine reconstruction of the 3D scene: based on the 3D laser scanning laser point cloud, the 3D spatial information of the ground visible objects is obtained, and the orthophoto obtained by the drone aerial photography is assisted, Obtain the three-dimensional space information of the top of the ground feature, and the ground three-dimensional laser scanner can quickly obtain the three-dimensional surface information of the building facade, ground, and trees. Due to the complex structure of the building and the occlusion of spatial objects, sub-station scanning is required when acquiring point cloud data. This article uses the Sino-German Energy Conservation Center Building of Shenyang Jianzhu University as the research area, using drone tilt photography technology and ground lidar technology to integrate. During the experiment, the field industry adopted the UAV image acquisition strategy of “automatic shooting of regular routes, supplemented by manual shooting of areas of interest”; in the field industry, the method of “manual coarse registration and ICP algorithm fine registration” The example results show that the ground 3D laser point cloud air-ground image fusion 3D modeling effect proposed in this paper is better and the quality is greatly improved, which makes up for the ground 3D laser scanning. In point cloud modeling, a large number of holes are insufficient due to occlusion and missing top information.

Sign in / Sign up

Export Citation Format

Share Document