Filters








337 Hits in 5.1 sec

A Point-Based Fully Convolutional Neural Network for Airborne LiDAR Ground Point Filtering in Forested Environments

Shichao Jin, Yanjun Su, Xiaoqian Zhao, Tianyu Hu, Qinghua Guo
2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Index Terms-Digital terrain model (DTM), deep learning, fully convolutional neural network (FCN), ground filtering, light detection and ranging (LiDAR).  ...  In this article, we proposed a point-based fully convolutional neural network (PFCN) which directly consumed points with only geometric information and extracted both point-wise and tile-wise features  ...  In this study, we aim to propose a point-based fully CNN (PFCN) for filtering ground points from ALS data in forested environments.  ... 
doi:10.1109/jstars.2020.3008477 fatcat:jla5hddkm5fdziun3uftzfeabq

Tree Annotations in LiDAR Data Using Point Densities and Convolutional Neural Networks

Ananya Gupta, Jonathan Byrne, David Moloney, Simon Watson, Hujun Yin
2019 IEEE Transactions on Geoscience and Remote Sensing  
The second method uses a voxel-based 3D Convolutional Neural Network on low density LiDAR datasets and is able to identify most large trees accurately but struggles with smaller ones due to the voxelisation  ...  Manual annotation of such data is time consuming, tedious and error prone, and hence in this paper we present three automatic methods for annotating trees in LiDAR data.  ...  [19] used a 1D convolutional neural network (CNN) in conjunction with LiDAR data and spectral information to generate point-wise semantic labels for unordered points and achieved a mean F score of 63.32%  ... 
doi:10.1109/tgrs.2019.2942201 fatcat:sbwb4enm3nf5riin2te2buonlq

EFFICIENT LARGE-SCALE AIRBORNE LIDAR DATA CLASSIFICATION VIA FULLY CONVOLUTIONAL NETWORK

E. Maset, B. Padova, A. Fusiello
2020 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
The image is then segmented by a Fully Convolutional Network (FCN), assigning a label to each pixel and, consequently, to the corresponding point.  ...  Nowadays, we are witnessing an increasing availability of large-scale airborne LiDAR (Light Detection and Ranging) data, that greatly improve our knowledge of urban areas and natural environment.  ...  ACKNOWLDGMENT The authors are grateful to Regione Autonoma Friuli Venezia Giulia (Italy) for allowing the publication of the results obtained on the LiDAR dataset acquired as part of the regional remote  ... 
doi:10.5194/isprs-archives-xliii-b3-2020-527-2020 fatcat:dkqxinyllvhlvcbkzqtr47apqy

High-Resolution Terrain Modeling Using Airborne LiDAR Data with Transfer Learning

Huxiong Li, Weiya Ye, Jun Liu, Weikai Tan, Saied Pirasteh, Sarah Narges Fatholahi, Jonathan Li
2021 Remote Sensing  
This study presents a novel workflow for automated Digital Terrain Model (DTM) extraction from Airborne LiDAR point clouds based on a convolutional neural network (CNN), considering a transfer learning  ...  First, each point is transformed into a featured image based on its elevation differences with neighboring points.  ...  Acknowledgments: This study was carried out as part of the proposed joint research to build a foundation for working together to support Sustainable Development Goal (SDG)-17 and develop possibilities  ... 
doi:10.3390/rs13173448 doaj:7176e51da3a048268ee611faaa39fc01 fatcat:emnewzy62nf6xhompuouvdwhcu

2020 Index IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 13

2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
., +, JSTARS 2020 4133-4148 A Point-Based Fully Convolutional Neural Network for Airborne LiDAR Ground Point Filtering in Forested Environments.  ...  ., +, JSTARS 2020 1639-1648 A Point-Based Fully Convolutional Neural Network for Airborne LiDAR Ground Point Filtering in Forested Environments.  ...  A New Deep-Learning-Based Approach for Earthquake-Triggered Landslide Detection From Single-Temporal RapidEye Satellite Imagery. Yi, Y., +, JSTARS 2020  ... 
doi:10.1109/jstars.2021.3050695 fatcat:ycd5qt66xrgqfewcr6ygsqcl2y

A Convolutional Neural Network Classifier Identifies Tree Species in Mixed-Conifer Forest from Hyperspectral Imagery

Geoffrey A. Fricker, Jonathan D. Ventura, Jeffrey A. Wolf, Malcolm P. North, Frank W. Davis, Janet Franklin
2019 Remote Sensing  
In this study, we automate tree species classification and mapping using field-based training data, high spatial resolution airborne hyperspectral imagery, and a convolutional neural network classifier  ...  Our classifier is pixel-based rather than object based, although we use three-dimensional structural information from airborne Light Detection and Ranging (LiDAR) to identify trees (points > 5 m above  ...  The opinions expressed in this article are the author's own and do not reflect the view of Amazon Corporation.  ... 
doi:10.3390/rs11192326 fatcat:el6nbum7pfephbmkvjz4dyjuzu

Roof Shape Classification from LiDAR and Satellite Image Data Fusion Using Supervised Learning

Jeremy Castagno, Ella Atkins
2018 Sensors  
Multiple convolutional neural network (CNN) architectures are trained and tested, with the best performing networks providing a condensed feature set for support vector machine and decision tree classifiers  ...  Satellite imagery and airborne LiDAR data are processed and manually labeled to create a diverse annotated roof image dataset for small to large urban cities.  ...  The Convolutional Neural Network (CNN) An artificial neural network is composed of a series of functional layers connected in a weighted graph structure.  ... 
doi:10.3390/s18113960 fatcat:lnvccglopfgfbakdg4vv45pkya

Change Detection of Selective Logging in the Brazilian Amazon Using X-Band SAR Data and Pre-Trained Convolutional Neural Networks

Tahisa Neitzel Kuck, Paulo Fernando Ferreira Silva Filho, Edson Eyji Sano, Polyanna da Conceição Bispo, Elcio Hideiti Shiguemori, Ricardo Dalagnol
2021 Remote Sensing  
The aim of this study was to test different pre-trained models of Convolutional Neural Networks (CNNs) for change detection associated with forest degradation in bitemporal products obtained from a pair  ...  It is estimated that, in the Brazilian Amazon, forest degradation contributes three times more than deforestation for the loss of gross above-ground biomass.  ...  Acknowledgments: The authors would like to thank José Humberto Chaves, from the Brazilian Forest Service, for the data cession. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs13234944 fatcat:w7ewsdbm3fgxddpe2xkfmtxlbm

Forest Tree Detection and Segmentation using High Resolution Airborne LiDAR [article]

Lloyd Windrim, Mitch Bryson
2018 arXiv   pre-print
This paper presents an autonomous approach to tree detection and segmentation in high resolution airborne LiDAR that utilises state-of-the-art region-based CNN and 3D-CNN deep learning algorithms.  ...  If the number of training examples for a site is low, it is shown to be beneficial to transfer a segmentation network learnt from a different site with more training data and fine-tune it.  ...  ACKNOWLEDGMENT This work was supported in part by Forest and Wood Products Australia research grant PNC377-1516.  ... 
arXiv:1810.12536v1 fatcat:6r6nlfmgvvcrpazw7guft63ksy

Multi-Level Interpolation-Based Filter for Airborne LiDAR Point Clouds in Forested Areas

Chuanfa Chen, Mengying Wang, Bingtao Chang, Yanyan Li
2020 IEEE Access  
Therefore, the proposed method can be considered as an effective ground filtering algorithm for airborne LiDAR point clouds in forested areas.  ...  Over the past decades, plenty of filtering algorithms have been presented to distinguish ground and non-ground points from airborne LiDAR point clouds.  ...  Hu and Yuan [33] developed a filtering method based on deep learning using deep convolutional neural networks. Rizaldy et al. [34] used fully convolutional networks to classify point clouds.  ... 
doi:10.1109/access.2020.2976848 fatcat:gtpaggp65vfqvjh35r6thv34hi

Building Extraction from Airborne Multi-Spectral LiDAR Point Clouds Based on Graph Geometric Moments Convolutional Neural Networks

Dilong Li, Xin Shen, Yongtao Yu, Haiyan Guan, Jonathan Li, Guo Zhang, Deren Li
2020 Remote Sensing  
In addition, a hierarchical architecture equipped with GGM convolution, called GGM convolutional neural networks, is proposed to train and recognize building points.  ...  In this paper, a novel deep-learning-based framework is proposed for building extraction from point cloud data.  ...  In recent years, the success of deep convolutional neural networks (CNNs) for image processing has motivated the data-driven approaches to extract buildings from airborne LiDAR data.  ... 
doi:10.3390/rs12193186 fatcat:vsp3puno5zbotd5yfqfgqhcufa

Performance Comparison of Filtering Algorithms for High-Density Airborne LiDAR Point Clouds over Complex LandScapes

Chuanfa Chen, Jiaojiao Guo, Huiming Wu, Yanyan Li, Bo Shi
2021 Remote Sensing  
Point cloud filtering is a prerequisite for almost all LiDAR-based applications.  ...  However, it is challenging to select a suitable filtering algorithm for handling high-density point clouds over complex landscapes.  ...  Acknowledgments: The authors wish to express their sincere gratitude to the anonymous reviewers for their assistance, comments, and suggestions.  ... 
doi:10.3390/rs13142663 fatcat:s4zv6kggvzcd3em32mnizj56pu

Real-Time Object Detection for LiDAR Based on LS-R-YOLOv4 Neural Network

Yu-Cheng Fan, Chitra Meghala Yelamandala, Ting-Wei Chen, Chun-Ju Huang, Ismail Butun
2021 Journal of Sensors  
And later on, we trained the network with the PASCAL VOC dataset used for object detection by the YOLOv4 neural network. To evaluate, we used the region of interest image as input to YOLOv4.  ...  Firstly, the KITTI dataset provides in-depth data knowledge for the LiDAR segmentation (LS) of objects obtained through LiDAR point clouds.  ...  The authors gratefully acknowledge the Taiwan Semiconductor Research Institute (TSRI), for supplying the technology models used in IC design.  ... 
doi:10.1155/2021/5576262 fatcat:2ltzwrantrey5a67edahqly6nq

Combining LiDAR metrics and Sentinel-2 imagery to estimate basal area and wood volume in complex forest environment via neural networks

Kamel Lahssini, Florian Teste, Karun Dayal, Sylvie Durrieu, Dino Ienco, Jean-Matthieu Monnet
2022 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
To deal with this particular issue in the context of structure and biophysical variables estimation for forest characterization, we propose a new deep learning based fusion strategy to combine together  ...  high density 3D-point clouds acquired by airborne laser scanning (ALS) with high resolution optical imagery freely accessible via the Sentinel-2 mission.  ...  in a complex forest environments.  ... 
doi:10.1109/jstars.2022.3175609 fatcat:svibkir4cnb33n2oxrbj4r4pje

Integrating Normal Vector Features into an Atrous Convolution Residual Network for LiDAR Point Cloud Classification

Chunjiao Zhang, Shenghua Xu, Tao Jiang, Jiping Liu, Zhengjun Liu, An Luo, Yu Ma
2021 Remote Sensing  
To realize the semantic classification of LiDAR point clouds in complex scenarios, this paper proposes the integration of normal vector features into an atrous convolution residual network.  ...  Based on the RandLA-Net network structure, the proposed network integrates the atrous convolution into the residual module to extract global and local features of the point clouds.  ...  A few researchers have proposed an indirect learning point cloud feature extraction scheme based on deep convolutional neural networks.  ... 
doi:10.3390/rs13173427 fatcat:6w6a6l3zlzex3bjyoflqks2njq
« Previous Showing results 1 — 15 out of 337 results