LiDAR Data Classification Using Spatial Transformation and CNN | |
He, Xin1; Wang, Aili1; Ghamisi, Pedram2; Li, Guoyu3; Chen, Yushi4 | |
刊名 | IEEE GEOSCIENCE AND REMOTE SENSING LETTERS |
2019 | |
卷号 | 16期号:1页码:125-129 |
关键词 | Convolutional neural networks (CNNs) deep learning feature extraction light detection and ranging (LiDAR) morphological profile (MP) spatial transformation network (STN) |
ISSN号 | 1545-598X |
DOI | 10.1109/LGRS.2018.2868378 |
通讯作者 | Chen, Yushi(chenyushi@hit.edu.cn) |
英文摘要 | Light detection and ranging (LiDAR) is a useful data acquisition technique, which is widely used in a variety of practical applications. The classification of LiDAR-derived rasterized digital surface model (LiDAR-DSM) is a fundamental technique in LiDAR data processing. In recent years, deep learning methods, especially convolutional neural networks (CNNs), have shown their capability in remote sensing areas, including LiDAR data processing. Traditional deep models empirically use a fixed neighborhood system as input to the network. Therefore, the weight and height of the input rectangle may not be optimal. In order to modify such handcrafted setting, a spatial transformation network is used here to identify optimal inputs. The transformed inputs are fed into a well-designed CNN to obtain the final classification results. Furthermore, morphological profiles are combined with spatial transformation CNN to further improve the classification accuracy. The proposed frameworks are tested on two LiDAR-DSMs (i.e., the Recology and Houston data sets). The experimental results show that the proposed models provide competitive results compared to the state-of-the-art methods. Furthermore, the proposed optimal input identification approach can also be found beneficial for other remote sensing applications. |
收录类别 | SCI |
WOS关键词 | DEEP |
WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
WOS类目 | Geochemistry & Geophysics ; Engineering, Electrical & Electronic ; Remote Sensing ; Imaging Science & Photographic Technology |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000455181800026 |
内容类型 | 期刊论文 |
URI标识 | http://www.corc.org.cn/handle/1471x/2558204 |
专题 | 寒区旱区环境与工程研究所 |
通讯作者 | Chen, Yushi |
作者单位 | 1.Harbin Univ Sci & Technol, Higher Educ Key Lab Measure & Control Technol & I, Harbin 150080, Heilongjiang, Peoples R China 2.Helmholtz Zentrum Dresden Rossendorf, Helmholtz Inst Freiberg Resource Technol Explorat, D-09599 Freiberg, Germany 3.Chinese Acad Sci, State Key Lab Frozen Soil Engn, Cold & Arid Reg Environm & Engn Res Inst, Lanzhou 730000, Gansu, Peoples R China 4.Harbin Inst Technol, Sch Elect & Informat Engn, Harbin 150001, Heilongjiang, Peoples R China |
推荐引用方式 GB/T 7714 | He, Xin,Wang, Aili,Ghamisi, Pedram,et al. LiDAR Data Classification Using Spatial Transformation and CNN[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2019,16(1):125-129. |
APA | He, Xin,Wang, Aili,Ghamisi, Pedram,Li, Guoyu,&Chen, Yushi.(2019).LiDAR Data Classification Using Spatial Transformation and CNN.IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,16(1),125-129. |
MLA | He, Xin,et al."LiDAR Data Classification Using Spatial Transformation and CNN".IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 16.1(2019):125-129. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论