scholarly journals 3D Reconstruction using Kinect Sensor and Parallel Processing on 3D Graphics Processing Unit

2013 ◽  
Vol 3 (1-2) ◽  
Author(s):  
Thuong Le-Tien ◽  
Marie Luong ◽  
Thai Phu Ho ◽  
Viet Dai Tran
Keyword(s):  
Graphics Processing Unit ◽  
Point Clouds ◽  
Microsoft Kinect ◽  
Alignment Algorithm ◽  
Processing Unit ◽  
Initial Alignment ◽  
Depth Cameras ◽  
3D Point Clouds ◽  
Alpha Shapes ◽  
Reconstruction Methods

One of depth cameras such as the Microsoft Kinect is much cheaper than conventional 3D scanning devices, thus it can be acquired for everyday users easily. However, the depth data captured by Kinect over a certain distance is of low quality. In this work, we implement a set of algorithms allowing users to capture 3D surfaces by using the handheld Kinect. As a classic alignment algorithm such as the Iterative Closest Point (ICP) does not show efficacy in aligning point clouds that have limited overlapped regions, another coarse alignment using the Sample Consensus Initial Alignment (SAC-IA) is incorporated in to the registration process in order to ameliorate 3D point clouds’ fitness. Two robust reconstruction methods namely the Alpha Shapes and the Grid Projection are also implemented to reconstruct 3D surface from registered point clouds. The experimental results have shown the efficiency and applicability of of our blueprint. The constructed system obtains acceptable results in a few minutes with a low price device, thus it may practically be an useful approach for avatar generations or online shoppings.

scholarly journals Real-Time Terrain Storage Generation from Multiple Sensors towards Mobile Robot Operation Interface

2014 ◽  
Vol 2014 ◽  
pp. 1-12
Author(s):  
Wei Song ◽  
Seoungjae Cho ◽  
Yulong Xi ◽  
Kyungeun Cho ◽  
Kyhyun Um
Keyword(s):  
Mobile Robot ◽  
Real Time ◽  
Large Scale ◽  
Graphics Processing Unit ◽  
Point Clouds ◽  
Outdoor Environment ◽  
Processing Unit ◽  
Multiple Sensors ◽  
3D Point Clouds ◽  
Video Images

A mobile robot mounted with multiple sensors is used to rapidly collect 3D point clouds and video images so as to allow accurate terrain modeling. In this study, we develop a real-time terrain storage generation and representation system including a nonground point database (PDB), ground mesh database (MDB), and texture database (TDB). A voxel-based flag map is proposed for incrementally registering large-scale point clouds in a terrain model in real time. We quantize the 3D point clouds into 3D grids of the flag map as a comparative table in order to remove the redundant points. We integrate the large-scale 3D point clouds into a nonground PDB and a node-based terrain mesh using the CPU. Subsequently, we program a graphics processing unit (GPU) to generate the TDB by mapping the triangles in the terrain mesh onto the captured video images. Finally, we produce a nonground voxel map and a ground textured mesh as a terrain reconstruction result. Our proposed methods were tested in an outdoor environment. Our results show that the proposed system was able to rapidly generate terrain storage and provide high resolution terrain representation for mobile mapping services and a graphical user interface between remote operators and mobile robots.

scholarly journals Strong-Weak Feature Alignment for 3D Object Detection

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1205
Author(s):  
Zhiyu Wang ◽  
Li Wang ◽  
Bin Dai
Keyword(s):  
Object Detection ◽  
Point Clouds ◽  
Autonomous Driving ◽  
Feature Representation ◽  
Alignment Algorithm ◽  
3D Object ◽  
3D Point Clouds ◽  
Object Feature ◽  
3D Object Detection ◽  
Feature Alignment

Object detection in 3D point clouds is still a challenging task in autonomous driving. Due to the inherent occlusion and density changes of the point cloud, the data distribution of the same object will change dramatically. Especially, the incomplete data with sparsity or occlusion can not represent the complete characteristics of the object. In this paper, we proposed a novel strong–weak feature alignment algorithm between complete and incomplete objects for 3D object detection, which explores the correlations within the data. It is an end-to-end adaptive network that does not require additional data and can be easily applied to other object detection networks. Through a complete object feature extractor, we achieve a robust feature representation of the object. It serves as a guarding feature to help the incomplete object feature generator to generate effective features. The strong–weak feature alignment algorithm reduces the gap between different states of the same object and enhances the ability to represent the incomplete object. The proposed adaptation framework is validated on the KITTI object benchmark and gets about 6% improvement in detection average precision on 3D moderate difficulty compared to the basic model. The results show that our adaptation method improves the detection performance of incomplete 3D objects.

scholarly journals Fast Planar Detection System Using a GPU-Based 3D Hough Transform for LiDAR Point Clouds

2020 ◽  
Vol 10 (5) ◽  
pp. 1744 ◽  
Author(s):  
Yifei Tian ◽  
Wei Song ◽  
Long Chen ◽  
Yunsick Sung ◽  
Jeonghoon Kwak ◽  
...  
Keyword(s):  
Hough Transform ◽  
Detection System ◽  
Point Clouds ◽  
Detection Algorithm ◽  
Polar Coordinates ◽  
Processing Unit ◽  
3D Point Clouds ◽  
Hough Space ◽  
Plane Extraction ◽  
3D Hough Transform

Plane extraction is regarded as a necessary function that supports judgment basis in many applications, including semantic digital map reconstruction and path planning for unmanned ground vehicles. Owing to the heterogeneous density and unstructured spatial distribution of three-dimensional (3D) point clouds collected by light detection and ranging (LiDAR), plane extraction from it is recently a significant challenge. This paper proposed a parallel 3D Hough transform algorithm to realize rapid and precise plane detection from 3D LiDAR point clouds. After transforming all the 3D points from a Cartesian coordinate system to a pre-defined 3D Hough space, the generated Hough space is rasterised into a series of arranged cells to store the resided point counts into individual cells. A 3D connected component labeling algorithm is developed to cluster the cells with high values in Hough space into several clusters. The peaks from these clusters are extracted so that the targeting planar surfaces are obtained in polar coordinates. Because the laser beams emitted by LiDAR sensor holds several fixed angles, the collected 3D point clouds distribute as several horizontal and parallel circles in plane surfaces. This kind of horizontal and parallel circles mislead plane detecting results from horizontal wall surfaces to parallel planes. For detecting accurate plane parameters, this paper adopts a fraction-to-fraction method to gradually transform raw point clouds into a series of sub Hough space buffers. In our proposed planar detection algorithm, a graphic processing unit (GPU) programming technology is applied to speed up the calculation of 3D Hough space updating and peaks searching.

Registration of 3D Point Clouds for Ship Block Measurement

2015 ◽  
Author(s):  
Sunghan Kim ◽  
Mingyu Kim ◽  
Jeongtae Lee ◽  
Jinhwi Pyo ◽  
Heeyoung Heo ◽  
...  
Keyword(s):  
Point Cloud ◽  
Measurement Data ◽  
User Interaction ◽  
Point Clouds ◽  
Processing Unit ◽  
Feature Points ◽  
Automatic Registration ◽  
Actual Measurement ◽  
Large Size ◽  
3D Point Clouds

In this paper, a software system for registration of point clouds is developed. The system consists of two modules for registration and user interaction. The registration module contains functions for manual and automatic registration. The manual method allows a user to select feature points or planes from the point clouds manually. The selected planes or features are then processed to establish the correspondence between the point clouds, and registration is performed to obtain one large point cloud. The automatic registration uses sphere targets. Sphere targets are attached to an object of interest. A scanner measures the object as well as the targets to produce point clouds, from which the targets are extracted using shape intrinsic properties. Then correspondence between the point clouds is obtained using the targets, and the registration is performed. The user interaction module provides a GUI environment which allows a user to navigate point clouds, to compute various features, to visualize point clouds and to select/unselect points interactively and the point-processing unit containing functions for filtering, estimation of geometric features, and various data structures for managing point clouds of large size. The developed system is tested with actual measurement data of various blocks in a shipyard.

scholarly journals 3D SCANNING OF LIVE PIGS SYSTEM AND ITS APPLICATION IN BODY MEASUREMENTS

2017 ◽  
Vol XLII-2/W7 ◽  
pp. 211-217 ◽  
Author(s):  
H. Guo ◽  
K. Wang ◽  
W. Su ◽  
D. H. Zhu ◽  
W. L. Liu ◽  
...  
Keyword(s):  
Detection Method ◽  
Point Clouds ◽  
3D Scanning ◽  
Scanning System ◽  
Prototype System ◽  
Body Measurements ◽  
Important Indicator ◽  
Depth Cameras ◽  
3D Point Clouds ◽  
Common Coordinate System

The shape of a live pig is an important indicator of its health and value, whether for breeding or for carcass quality. This paper implements a prototype system for live single pig body surface 3d scanning based on two consumer depth cameras, utilizing the 3d point clouds data. These cameras are calibrated in advance to have a common coordinate system. The live 3D point clouds stream of moving single pig is obtained by two Xtion Pro Live sensors from different viewpoints simultaneously. A novel detection method is proposed and applied to automatically detect the frames containing pigs with the correct posture from the point clouds stream, according to the geometric characteristics of pig’s shape. The proposed method is incorporated in a hybrid scheme, that serves as the preprocessing step in a body measurements framework for pigs. Experimental results show the portability of our scanning system and effectiveness of our detection method. Furthermore, an updated this point cloud preprocessing software for livestock body measurements can be downloaded freely from <a href="https://github.com/LiveStockShapeAnalysis"target="_blank">https://github.com/LiveStockShapeAnalysis</a> to livestock industry, research community and can be used for monitoring livestock growth status.

A Highly Parallel Approach to Meshing Scattered Point Data

2009 ◽  
Author(s):  
Hoi Sheung ◽  
Siu-Ping Mok ◽  
Charlie C. L. Wang
Keyword(s):  
Point Cloud ◽  
Graphics Processing Unit ◽  
Approximation Error ◽  
Point Clouds ◽  
Surface Generation ◽  
Graphics Hardware ◽  
Processing Unit ◽  
Mesh Surface ◽  
Normal Vectors ◽  
Point Cloud Simplification

In this paper, we present a parallel mesh surface generation approach for unorganized point clouds that runs on the graphics processing unit (GPU). Our approach integrates point cloud simplification, point cloud optimization, and local triangulation techniques into the same framework. The input point cloud will be processed through three steps of algorithms, which are 1) preprocessing: to generate the neighborhood table of points and estimate the normal vectors, 2) clustering: to group points into optimized clusters that minimize the shape approximation error, and 3) meshing: to connect the seed points in clusters to form the resultant triangular mesh surface. As the number of clusters can be specified by users, the number of vertices on resultant mesh surfaces is controlled. The algorithms exploited here are highly parallelized to take advantage of the single-instruction-multiple-data (SIMD) parallelism that is available on consumer-level graphics hardware with GPU. Moreover, to overcome memory limitation on graphics hardware, the algorithms in all these steps are able to process massive data in streaming mode.

scholarly journals On-the-Fly Camera and Lidar Calibration

2020 ◽  
Vol 12 (7) ◽  
pp. 1137
Author(s):  
Balázs Nagy ◽  
Csaba Benedek
Keyword(s):  
Control Point ◽  
Real Life ◽  
Point Clouds ◽  
Alignment Algorithm ◽  
Extrinsic Calibration ◽  
3D Point Clouds ◽  
Common Coordinate System ◽  
Calibration Problem ◽  
Robust Parameter ◽  
Calibration Approach

Sensor fusion is one of the main challenges in self driving and robotics applications. In this paper we propose an automatic, online and target-less camera-Lidar extrinsic calibration approach. We adopt a structure from motion (SfM) method to generate 3D point clouds from the camera data which can be matched to the Lidar point clouds; thus, we address the extrinsic calibration problem as a registration task in the 3D domain. The core step of the approach is a two-stage transformation estimation: First, we introduce an object level coarse alignment algorithm operating in the Hough space to transform the SfM-based and the Lidar point clouds into a common coordinate system. Thereafter, we apply a control point based nonrigid transformation refinement step to register the point clouds more precisely. Finally, we calculate the correspondences between the 3D Lidar points and the pixels in the 2D camera domain. We evaluated the method in various real-life traffic scenarios in Budapest, Hungary. The results show that our proposed extrinsic calibration approach is able to provide accurate and robust parameter settings on-the-fly.

scholarly journals Comparison of depth cameras for three-dimensional reconstruction in medicine

2019 ◽  
Vol 233 (9) ◽  
pp. 938-947 ◽  
Author(s):  
Chuang-Yuan Chiu ◽  
Michael Thelwell ◽  
Terry Senior ◽  
Simon Choppin ◽  
John Hart ◽  
...  
Keyword(s):  
Three Dimensional ◽  
Time Of Flight ◽  
Point Clouds ◽  
Microsoft Kinect ◽  
Depth Camera ◽  
Three Dimensional Reconstruction ◽  
Kinect V2 ◽  
Depth Cameras ◽  
Human Models ◽  
Dimensional Reconstruction

KinectFusion is a typical three-dimensional reconstruction technique which enables generation of individual three-dimensional human models from consumer depth cameras for understanding body shapes. The aim of this study was to compare three-dimensional reconstruction results obtained using KinectFusion from data collected with two different types of depth camera (time-of-flight and stereoscopic cameras) and compare these results with those of a commercial three-dimensional scanning system to determine which type of depth camera gives improved reconstruction. Torso mannequins and machined aluminium cylinders were used as the test objects for this study. Two depth cameras, Microsoft Kinect V2 and Intel Realsense D435, were selected as the representatives of time-of-flight and stereoscopic cameras, respectively, to capture scan data for the reconstruction of three-dimensional point clouds by KinectFusion techniques. The results showed that both time-of-flight and stereoscopic cameras, using the developed rotating camera rig, provided repeatable body scanning data with minimal operator-induced error. However, the time-of-flight camera generated more accurate three-dimensional point clouds than the stereoscopic sensor. Thus, this suggests that applications requiring the generation of accurate three-dimensional human models by KinectFusion techniques should consider using a time-of-flight camera, such as the Microsoft Kinect V2, as the image capturing sensor.

Sign in / Sign up

Export Citation Format

Share Document