5,163 Hits in 1e+01 sec

Automatic labelling of urban point clouds using data fusion [article]

Daan Bloembergen, Chris Eijgenstein
2021 arXiv   pre-print
We use data fusion techniques using public data sources such as elevation data and large-scale topographical maps to automatically label parts of the point cloud, after which only limited human effort  ...  In this paper we describe an approach to semi-automatically create a labelled dataset for semantic segmentation of urban street-level point clouds.  ...  To the best of our knowledge, we present the first fully modular and open source point cloud processing pipeline 1 that uses smart data fusion with different data sources to automatically label large parts  ... 
arXiv:2108.13757v2 fatcat:chalovumgzf5bc2xn6wtw7dtsu

Editorial for Special Issue: "Remote Sensing based Building Extraction"

Mohammad Awrangjeb, Xiangyun Hu, Bisheng Yang, Jiaojiao Tian
2020 Remote Sensing  
Building extraction from remote sensing data plays an important role in urban planning, disaster management, navigation, updating geographic databases, and several other geospatial applications [...]  ...  Conflicts of Interest: The authors declare no conflict of interest. Remote Sens. 2020, 12, 549  ...  Methods based on single source data can use point cloud data [9] , aerial imagery [4] and digital surface models (DSM) [8] .  ... 
doi:10.3390/rs12030549 fatcat:r2sqr6gem5bntci6kksgvk77mi


B. Hujebri, M. Ebrahimikia, H. Enayati
2019 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
In this paper, a method based on the fusion of LiDAR point cloud and aerial image data sources has been proposed.  ...  The first step of the proposed method is to separate ground and non-ground (that contain 3d objects like buildings, trees, ...) points using cloth simulation filtering and then normalize the non-ground  ...  Automatic extraction of building roofs using LIDAR data and multispectral imagery.  ... 
doi:10.5194/isprs-archives-xlii-4-w18-541-2019 fatcat:vzldkfu2vrcqdlokgsqmok4sf4

A Point-Wise LiDAR and Image Multimodal Fusion Network (PMNet) for Aerial Point Cloud 3D Semantic Segmentation

Vinayaraj Poliyapram, Weimin Wang, Ryosuke Nakamura
2019 Remote Sensing  
3D semantic segmentation of point cloud aims at assigning semantic labels to each point by utilizing and respecting the 3D representation of the data.  ...  Notably, multi-view 3D scanned data can also be trained using PMNet since it considers aerial point cloud as a fully 3D representation.  ...  The data originally provided for urban area 2D segmentation using multimodal fusion techniques, however, this research used this dataset for the 3D point cloud segmentation task.  ... 
doi:10.3390/rs11242961 fatcat:2h2slmdyo5gkpn4ay6gahrvd5a


W. Yao, P. Polewski, P. Krzystek
2017 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
In this paper, a labelling method for the semantic analysis of ultra-high point density MLS data (up to 4000 points/m<sup>2</sup>) in urban road corridors is developed based on combining a conditional  ...  The MLS data used for this study were acquired by vehicle-borne Z+F phase-based laser scanner measurement, which permits the generation of a point cloud with an ultra-high sampling rate and accuracy.  ...  Gunnar Graefe from 3D Mapping Solutions GmbH for their productive contributions and providing us the MLS data.  ... 
doi:10.5194/isprs-archives-xlii-2-w7-971-2017 fatcat:6zw2fnhepzhr5kfny5lmfbmeeq


D. Tosic, S. Tuttas, L. Hoegner, U. Stilla
2019 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Both, point cloud data, as well as the data from a multi-camera system are used for gaining spatial information in an urban scene.  ...  The automatic point labeling is achieved by utilizing the combination of a feature-based approach for semantic classification of point clouds and a deep learning approach for semantic segmentation of images  ...  At the end, fusion of the point clouds from the same urban scene, classified with these two methods is presented as experiment result and the performance of our method evaluated on a manually labeled dataset  ... 
doi:10.5194/isprs-archives-xlii-2-w16-235-2019 fatcat:jl3mtjmgbzbtxcinzwcbygetku

Efficient Urban-scale Point Clouds Segmentation with BEV Projection [article]

Zhenhong Zou, Yizhe Li
2021 arXiv   pre-print
Most deep point clouds models directly conduct learning on 3D point clouds, which will suffer from the severe sparsity and extreme data processing load in urban-scale data.  ...  We hope our work can inspire further exploration in point cloud analysis.  ...  INTRODUCTION 3D semantic segmentation is the critical technology of point cloud learning with the purpose of assigning a semantic label to each individual point data, which has been extensively applied  ... 
arXiv:2109.09074v1 fatcat:kh5vhlqqs5dajhssugkj5gpm44

3D Urban buildings extraction based on airborne LiDAR and photogrammetric point cloud fusion according to U-Net deep learning model segmentation

Pengcheng Zhang, Huagui He, Yun Wang, Yang Liu, Hong Lin, Liang Guo, Weijun Yang
2022 IEEE Access  
The LiDAR and photogrammetric point clouds fusion procedure for building extraction according to U-Net deep learning model segmentation is provided and tested.  ...  Firstly, an initial geolocalization process is performed for photogrammetric point clouds generated using structure-from-motion and dense-matching methods.  ...  Then, an urban building map from U-Net segmentation was utilized for point cloud segmentation. The two types of point cloud data and polygons all use the same coordinate system.  ... 
doi:10.1109/access.2022.3152744 fatcat:p7ha7yhhi5f4toelqdynylamd4

Three-Dimensional Urban Land Cover Classification by Prior-Level Fusion of LiDAR Point Cloud and Optical Imagery

Yanming Chen, Xiaoqiang Liu, Yijia Xiao, Qiqi Zhao, Sida Wan
2021 Remote Sensing  
using light detection and ranging system (LiDAR) point clouds.  ...  However, few studies have focused on the fusion of LiDAR point clouds and optical imagery for three-dimensional land cover classification, especially using a deep learning framework.  ...  Acknowledgments: The Vaihingen data set was accessed on 9 May 2018 from the German Society for Photogrammetry, Remote Sensing and Geoinformation (DGPF) [44] : http://www.ifp.uni-stuttgart. de/dgpf/DKEPAllg.html  ... 
doi:10.3390/rs13234928 fatcat:aiz6kel3jvbdjknj2atz56xjjq

Visibility Estimation in Point Clouds with Variable Density

P. Biasutti, A. Bugeau, J-F. Aujol, M. Brédif
2019 Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications  
Estimating visibility in point clouds has many applications such as visualization, surface reconstruction and scene analysis through fusion of LiDAR point clouds and images.  ...  The method is designed to be fully automatic and it makes no assumption on the point cloud density.  ...  Example of application to data fusion To conclude our experiments, we show the interest of our visibility estimation for the task of data fusion.  ... 
doi:10.5220/0007308600270035 dblp:conf/visapp/BiasuttiBAB19 fatcat:halhye7555dztaazipaezsa5ni

Deep learning for urban remote sensing

Nicolas Audebert, Alexandre Boulch, Hicham Randrianarivo, Bertrand Le Saux, Marin Ferecatu, Sebastien Lefevre, Renaud Marlet
2017 2017 Joint Urban Remote Sensing Event (JURSE)  
For estimation of normals in point clouds, combining Hough transform with convolutional networks also improves the accuracy of previous frameworks by detecting hard configurations like corners.  ...  For classification and semantic mapping of aerial images, we present various deep network architectures and show that context information and dense labeling allow to reach better performances.  ...  The authors would like to thank the Belgian Royal Military Academy for acquiring and providing the Zeebrugge dataset used in this study, and the IEEE GRSS Image Analysis and Data Fusion Technical Committee  ... 
doi:10.1109/jurse.2017.7924536 dblp:conf/jurse/AudebertBRSFLM17 fatcat:4x55h56kifhmpgqoaqnhxckgu4


Z. Nordin, H. Z. M. Shafri, A. F. Abdullah, S. J. Hashim
2019 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
mapping approach offers practicality and significant cost savings for the nation minimizing the need for ground control points on the ground in addition to providing high-resolution, day-and-night, cloud  ...  coverage and weather independent images, which in turn provides faster turnaround times for creation of large area geospatial data.  ...  This primary classification was used on to identify the upper and lower part of each building in an urban scene, needed to model buildings façades; and to extract point cloud of uniform surfaces which  ... 
doi:10.5194/isprs-archives-xlii-4-w16-489-2019 fatcat:xhlrmiru5reo5fbqkhafxucl6a


W. Yuan, X. Yuan, Z. Fan, Z. Guo, X. Shi, J. Gong, R. Shibasaki
2021 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
3D point cloud for accurate building change index generation.  ...  cloud jointly.  ...  Given bi-temporal raw image data, we automatically generate the whole area's dense 3D point clouds and rectify images and detect the changed buildings with semantic change types.  ... 
doi:10.5194/isprs-archives-xliii-b3-2021-377-2021 fatcat:yq76qp6y5ndlrf4c7uc4t6meha

RasterNet: Modeling Free-Flow Speed using LiDAR and Overhead Imagery [article]

Armin Hadzic, Hunter Blanton, Weilian Song, Mei Chen, Scott Workman, Nathan Jacobs
2020 arXiv   pre-print
RasterNet is a neural network that fuses large-scale overhead imagery and aerial LiDAR point clouds using a geospatially consistent raster structure.  ...  To support training and evaluation, we introduce a novel dataset combining free-flow speeds of road segments, overhead imagery, and LiDAR point clouds across the state of Kentucky.  ...  Our approach uses point cloud understanding to process 3D point clouds. Estimating Traffic Speed Several works have proposed automatic methods for estimating the speed of vehicles.  ... 
arXiv:2006.08021v1 fatcat:huob754e45fohoqbko4t2mrpza

3D exploitation of large urban photo archives

Peter Cho, Noah Snavely, Ross Anderson, Ivan Kadar
2010 Signal Processing, Sensor Fusion, and Target Recognition XIX  
Camera ranges to features depend upon image, while urban feature altitudes remain invariant front of the reconstructed Statue point cloud (for which we do not have ladar data).  ...  We focus in particular on automatic feature annotation and image-based querying. Examples of geometry-mediated labeling of buildings and measuring of ranges to target points are presented.  ... 
doi:10.1117/12.849767 fatcat:yqwcuea4evg4zbuvopwi4yxiny
« Previous Showing results 1 — 15 out of 5,163 results