中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 植物研究所
  3. 中国科学院植物研究所
  4. 植被与环境变化国家重点实验室
A Point-Based Fully Convolutional Neural Network for Airborne LiDAR Ground Point Filtering in Forested Environments

文献类型：期刊论文

作者Jin, Shichao2,3; Sun, Yanjun2; Zhao, Xiaoqian2; Hu, Tianyu2; Guo, Qinghua2
刊名IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
出版日期2020
卷号13页码:3958-3974
关键词Digital terrain model (DTM) deep learning fully convolutional neural network (FCN) ground filtering light detection and ranging (LiDAR)
ISSN号1939-1404
DOI10.1109/JSTARS.2020.3008477
文献子类Article
英文摘要Airborne laser scanning (ALS) data is one of the most commonly used data for terrain products generation. Filtering ground points is a prerequisite step for ALS data processing. Traditional filtering methods mainly use handcrafted features or predefined classification rules with preprocessing/post-processing operations to filter ground points iteratively, which is empirical and cumbersome. Deep learning provides a new approach to solve classification and segmentation problems because of its ability to self-learn features, which has been favored in many fields, particularly remote sensing. 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 to classify each point. The network was trained with 37449157 points from 14 sites and evaluated on 6 sites in various forested environments. Additionally, the method was compared with five widely used filtering methods and one of the best point-based deep learning methods (PointNet++). Results showed that the PFCN achieved the best results in terms of mean omission error (T1 = 1.10%), total error (Te = 1.73%), and Kappa coefficient (93.88%), but ranked second for the root mean square error of the digital Terrain model caused by the worst commission error. Additionally, our method was on par with or even better than PointNet++ in accuracy. Moreover, the method consumes one-third of the computational resource and one-seventh of the training time. We believe that PFCN is a simple and flexible method that can be widely applied for ground point filtering.
学科主题Engineering, Electrical & Electronic ; Geography, Physical ; Remote Sensing ; Imaging Science & Photographic Technology
出版地PISCATAWAY
电子版国际标准刊号2151-1535
WOS关键词LASER-SCANNING DATA ; MORPHOLOGICAL FILTER ; ALGORITHM ; CLASSIFICATION ; DENSIFICATION ; SEGMENTATION ; ELEVATION ; HEIGHT ; MODELS ; CLOUDS
WOS研究方向Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:000552182800002
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key R&D Program of China [2016YFC0500202, 2017YFC0503905] ; National Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [31971575, 41871332, 41901358]
源URL[http://ir.ibcas.ac.cn/handle/2S10CLM1/21661]  
专题植被与环境变化国家重点实验室
作者单位1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
2.Nanjing Agr Univ, Plant Phen Res Ctr, Nanjing 210095, Peoples R China
3.Chinese Acad Sci, Inst Bot, State Key Lab Vegetat & Environm Change, Beijing 100093, Peoples R China
推荐引用方式
GB/T 7714		 Jin, Shichao,Sun, Yanjun,Zhao, Xiaoqian,et al. A Point-Based Fully Convolutional Neural Network for Airborne LiDAR Ground Point Filtering in Forested Environments[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2020,13:3958-3974.
APA Jin, Shichao,Sun, Yanjun,Zhao, Xiaoqian,Hu, Tianyu,&Guo, Qinghua.(2020).A Point-Based Fully Convolutional Neural Network for Airborne LiDAR Ground Point Filtering in Forested Environments.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,13,3958-3974.
MLA Jin, Shichao,et al."A Point-Based Fully Convolutional Neural Network for Airborne LiDAR Ground Point Filtering in Forested Environments".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 13(2020):3958-3974.

入库方式： OAI收割

来源：植物研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。