Filters








997 Hits in 5.5 sec

Indoor Scene Point Cloud Registration Algorithm Based on RGB-D Camera Calibration

2017 Sensors  
In this paper, an automatic point cloud registration algorithm is proposed to efficiently handle the task of 3D indoor scene reconstruction using pan-tilt platforms on a fixed position.  ...  The proposed algorithm aims to align multiple point clouds using extrinsic parameters of the RGB-D camera obtained from every preset pan-tilt control point.  ...  Author Contributions: Chi-Yi Tsai proposed the idea and supervised the research; Chih-Hung Huang designed and implemented the algorithm; Chih-Hung Huang performed the experiments and collected the experimental  ... 
doi:10.3390/s17081874 pmid:28809787 pmcid:PMC5579576 fatcat:o2brkvhlzfenza4svegkcuehxm

Calibrate Multiple Consumer RGB-D Cameras for Low-Cost and Efficient 3D Indoor Mapping

Chi Chen, Bisheng Yang, Shuang Song, Mao Tian, Jianping Li, Wenxia Dai, Lina Fang
2018 Remote Sensing  
Tsai et al. aligned multiple point clouds collected by a structured light RGB-D camera (ASUS Xtion Pro RGB-D camera) mounted on a pan-tilt platform to reconstruct the indoor scenes [29] .  ...  The intrinsic calibration that involves the geometry and depth calibration of single RGB-D cameras are solved by homography-based method and ray correction followed by range biases correction based on  ...  Figure 15 . 15 Point clouds captured by the proposed RGB-D camera array in typical indoor scenes. Figure 15 . 15 Point clouds captured by the proposed RGB-D camera array in typical indoor scenes.  ... 
doi:10.3390/rs10020328 fatcat:ewcwwqzjujbfbchoevcpprhhem

Visual Map Construction Using RGB-D Sensors for Image-Based Localization in Indoor Environments

Guanyuan Feng, Lin Ma, Xuezhi Tan
2017 Journal of Sensors  
Taking advantage of matched visual features and corresponding depth values, a novel local optimization algorithm is proposed to achieve point cloud registration and database camera pose estimation.  ...  The performance of the visual map construction and the image-based localization are evaluated on typical indoor scenes.  ...  The existing algorithms of RGB-D indoor mapping pay more attention to indoor scene recovery, but fewer of the algorithms focus mainly on the optimization of the RGB-D camera poses.  ... 
doi:10.1155/2017/8037607 fatcat:y6twx3uvv5bg3pmlfx77otkryq

A Vertex-to-Edge Weighted Closed-Form Method for Dense RGB-D Indoor SLAM

Shengjun Tang, You Li, Zhilu Yuan, Xiaoming Li, Renzhong Guo, YETING Zhang, Weixi Wang
2019 IEEE Access  
In this paper, we develop a vertex-to-edge weighted closed-form algorithm to reduce camera drift for dense RGB-D indoor simultaneous localization and mapping (SLAM).  ...  RGB-D dense mapping systems are widely used for indoor navigation and augmented reality. However, the drift in egomotion estimation systems accumulates as the systems expand over space and time.  ...  [21] presented an adaptive coarse-to-fine registration method for RGB-D mapping. Each point used for registration was weighted based on the theoretical random error of the depth measurement.  ... 
doi:10.1109/access.2019.2900990 fatcat:nbp6cr6ajrgthplofdkgnzhsvi

Enhanced RGB-D Mapping Method for Detailed 3D Indoor and Outdoor Modeling

Shengjun Tang, Qing Zhu, Wu Chen, Walid Darwish, Bo Wu, Han Hu, Min Chen
2016 Sensors  
The RGB-D sensors capture RGB images along with per-pixel depth images, which enables the estimation of the camera poses and the scene geometry with image-based algorithms such as SLAM or structure-from-motion  ...  In addition to the calibration of internal and external parameters for both, IR camera and RGB camera, the relative pose between RGB camera and IR camera is also calibrated.  ...  Tie points are obtained on the RGB images based on the image matching algorithm in Section 3.3.1.  ... 
doi:10.3390/s16101589 pmid:27690028 pmcid:PMC5087378 fatcat:uxvdljnpcbbg3hvvenjxjdjbre

Real-Time RGB-D Simultaneous Localization and Mapping Guided by Terrestrial LiDAR Point Cloud for Indoor 3-D Reconstruction and Camera Pose Estimation

Xujie Kang, Jing Li, Xiangtao Fan, Wenhui Wan
2019 Applied Sciences  
Next, we used terrestrial LiDAR point cloud to obtain prior data of the landscape, and then we applied the point-to-surface inductively coupled plasma (ICP) iterative algorithm to realize accurate camera  ...  The RGB-D SLAM constructs 3D environmental models of natural landscapes while simultaneously estimating camera poses.  ...  Figure 9 . 9 RGB-D point cloud generated by keyframes and LiDAR point cloud data ICP (point to plane) registration.  ... 
doi:10.3390/app9163264 fatcat:4jmpc5yuyzfdpoohjrgsn2ibwq

Effective Indoor Localization and 3D Point Registration Based on Plane Matching Initialization

Dongchen ZHU, Ziran XING, Jiamao LI, Yuzhang GU, Xiaolin ZHANG
2017 IEICE transactions on information and systems  
With the recovered colorful point cloud, the traditional ICP (Iterative Closest Point) algorithm can be used to estimate the camera poses and reconstruct the scene.  ...  Tracking the RGB-D camera becomes more popular since it can capture the relatively accurate color and depth information at the same time.  ...  In this work, we present a new method to track camera pose in the indoor scene and reconstruct the scene by using Kinect 2.0 as RGB-D camera.  ... 
doi:10.1587/transinf.2016edp7379 fatcat:gppjjw7nvfh3lbstzc4qjuefta

Registration of RGB and Thermal Point Clouds Generated by Structure From Motion

Trong Phuc Truong, Masahiro Yamaguchi, Shohei Mori, Vincent Nozick, Hideo Saito
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
The registration process includes a normalization of the point cloud scale, a global registration based on calibration data and the output of the structure from motion, and a fine registration employing  ...  The RGB and thermal point clouds are generated independently by structure from motion.  ...  The proposed system to align the RGB and IRT point clouds is based on the constant relative position and orientation between the two cameras.  ... 
doi:10.1109/iccvw.2017.57 dblp:conf/iccvw/TruongYMNS17 fatcat:nlfrz6eqq5gqhlvpw6hvelosue

Point cloud registration for agriculture and forestry crops based on calibration balls using Kinect V2

Sanzhang Zhou, 1. School of Technology, Beijing Forestry University, Beijing 100083, China, Feng Kang, Wenbin Li, Jiangming Kan, Yongjun Zheng, 2. Key Lab of State Forestry and Grassland Administration on Forestry Equipment and Automation, School of Technology, Beijing Forestry University, Beijing 100083, China, 3. College of Engineering, China Agricultural University, Beijing 100083, China
2020 International Journal of Agricultural and Biological Engineering  
Point cloud registration for agriculture and forestry crops based on calibration balls using Kinect V2. Int J Agric & Biol Eng, 2020; 13(1): 198-205.  ...  Using the Kinect V2 depth camera to collect the point cloud of the experimental scene from four different viewpoints, the PassThrough filter algorithm was used for point cloud filtering in each view of  ...  Point cloud registration and point cloud smoothing Coarse and fine registrations were two parts of the point cloud registration method based on calibration balls.  ... 
doi:10.25165/j.ijabe.20201301.5077 fatcat:o4rzjztiijhntlcmzxye4op3vq

MOBILE LASER SCANNING SYSTEMS FOR GPS/GNSS-DENIED ENVIRONMENT MAPPING

C. Wen, Y. Xia, Y. Lian, Y. Dai, J. Tan, C. Wang, J. Li
2018 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
The proposed approach uses the SLAM-based algorithm to achieve a large calibration scene using mobile platforms, registers an acquired multi-beam LIDAR point cloud to the terrestrial LIDAR point cloud  ...  The systems provide both 3D laser scanning point cloud and camera images.  ...  The 3D indoor map was built based on the SLAM algorithm. With the proposed calibration approach, the LiDAR point clouds and images were well fused ( Figure 5 ).  ... 
doi:10.5194/isprs-archives-xlii-1-457-2018 fatcat:4wulng6m45cffdytqh2fglbyfi

ENHANCED RGB-D MAPPING METHOD FOR DETAILED 3D MODELING OF LARGE INDOOR ENVIRONMENTS

Shengjun Tang, Qing Zhu, Wu Chen, Walid Darwish, Bo Wu, Han Hu, Min Chen
2016 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
In this paper, we propose an enhanced RGB-D mapping method for detailed 3D modeling of large indoor environments by combining RGB image-based modeling and depth-based modeling.  ...  Although they are widely used in various applications, RGB-D sensors have significant drawbacks with respect to 3D dense mapping of indoor environments.  ...  Camera Calibration The main concept of camera calibration is based on the pinhole camera model, which illustrates the relationship between the image point and the corresponding ground point as a function  ... 
doi:10.5194/isprs-annals-iii-1-151-2016 fatcat:fdha4eklfzbfxpmzouen2cdjwy

A WEIGHTED CLOSED-FORM SOLUTION FOR RGB-D DATA REGISTRATION

K. M. Vestena, D. R. Dos Santos, E. M. Oilveira Jr., N. L. Pavan, K. Khoshelham
2016 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Existing 3D indoor mapping of RGB-D data are prominently point-based and feature-based methods.  ...  After, a new RGB-D loop-closure solution is implemented based on the volumetric information between pair of point clouds and the dispersion of the random errors.  ...  We also describe a new RGB-D loop-closure approach, based on the uncertainty of the sensor and also on the volumetric information between overlap areas of the pair of point clouds.  ... 
doi:10.5194/isprsarchives-xli-b3-403-2016 fatcat:gdnk4z5s4rggziomp5w6vkymba

A WEIGHTED CLOSED-FORM SOLUTION FOR RGB-D DATA REGISTRATION

K. M. Vestena, D. R. Dos Santos, E. M. Oilveira Jr., N. L. Pavan, K. Khoshelham
2016 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Existing 3D indoor mapping of RGB-D data are prominently point-based and feature-based methods.  ...  After, a new RGB-D loop-closure solution is implemented based on the volumetric information between pair of point clouds and the dispersion of the random errors.  ...  We also describe a new RGB-D loop-closure approach, based on the uncertainty of the sensor and also on the volumetric information between overlap areas of the pair of point clouds.  ... 
doi:10.5194/isprs-archives-xli-b3-403-2016 fatcat:ry65alqblbfbna52lkymym4v5i

Research on Fast Target Positioning Method of Self-Calibration Manipulator

Xuhui Ye, Yuxuan Tang, Xinyu Hu, Daode Zhang, Qi Chen
2021 Symmetry  
The RGB-D camera mounted at the end of the manipulator is used to obtain multiple groups of RGB and depth images of the calibration plate.  ...  Then, based on KD tree algorithm, the holes in the point cloud are extracted to plan the shooting pose of the complementary image, and the target object is photographed from multiple symmetric angles.  ...  Fast Point Cloud Registration The point cloud image obtained by photographing the target in the scene with RGB-D camera usually forms the point cloud hole in the blind area of field of vision as shown  ... 
doi:10.3390/sym13112135 fatcat:bn7idy24dvhltacgyd7wwrxdim

RGB-D Indoor Plane-based 3D-Modeling using Autonomous Robot

N. Mostofi, A. Moussa, M. Elhabiby, N. El-Sheimy
2014 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
In order to have a semantic meaning out of 3D models, the planar patches are segmented from RGB-D point clouds data using region growing technique followed by convex hull method to assign boundaries to  ...  In this research work, we describe a system for visual odometry and 3D modeling using information from RGB-D sensor (Camera).  ...  With the advent of RGB-D cameras, capturing RGB images along with per-pixel depth data provides rich information for 3D mapping. The working principal of RGB-D cameras is based on stereo techniques.  ... 
doi:10.5194/isprsarchives-xl-1-301-2014 fatcat:r55gpqjdv5af3cgeeau5p2lqpu
« Previous Showing results 1 — 15 out of 997 results