Multispectral LiDAR Point Cloud Segmentation for Land Cover Leveraging Semantic Fusion in Deep Learning Network

被引:7
|
作者
Xiao, Kai [1 ]
Qian, Jia [2 ]
Li, Teng [3 ,4 ]
Peng, Yuanxi [1 ]
机构
[1] Natl Univ Def Technol, Coll Comp Sci & Technol, State Key Lab High Performance Comp, Changsha 410073, Peoples R China
[2] Tongji Univ, Coll Surveying & Geoinformat, Shanghai 200082, Peoples R China
[3] Natl Univ Def Technol, Beijing Inst Adv Study, Beijing 100020, Peoples R China
[4] Natl Univ Def Technol, Coll Adv Interdisciplinary Studies, Changsha 410073, Peoples R China
基金
中国国家自然科学基金;
关键词
multispectral LiDAR point cloud; deep learning network; semantic segmentation; FACE REPRESENTATION; 2-DIMENSIONAL PCA; CLASSIFICATION;
D O I
10.3390/rs15010243
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Multispectral LiDAR technology can simultaneously acquire spatial geometric data and multispectral wavelength intensity information, which can provide richer attribute features for semantic segmentation of point cloud scenes. However, due to the disordered distribution and huge number of point clouds, it is still a challenging task to accomplish fine-grained semantic segmentation of point clouds from large-scale multispectral LiDAR data. To deal with this situation, we propose a deep learning network that can leverage contextual semantic information to complete the semantic segmentation of large-scale point clouds. In our network, we work on fusing local geometry and feature content based on 3D spatial geometric associativity and embed it into a backbone network. In addition, to cope with the problem of redundant point cloud feature distribution found in the experiment, we designed a data preprocessing with principal component extraction to improve the processing capability of the proposed network on the applied multispectral LiDAR data. Finally, we conduct a series of comparative experiments using multispectral LiDAR point clouds of real land cover in order to objectively evaluate the performance of the proposed method compared with other advanced methods. With the obtained results, we confirm that the proposed method achieves satisfactory results in real point cloud semantic segmentation. Moreover, the quantitative evaluation metrics show that it reaches state-of-the-art.
引用
收藏
页数:19
相关论文
共 50 条
  • [31] Point attention network for point cloud semantic segmentation
    Dayong Ren
    Zhengyi Wu
    Jiawei Li
    Piaopiao Yu
    Jie Guo
    Mingqiang Wei
    Yanwen Guo
    Science China Information Sciences, 2022, 65
  • [32] 3D Edge Convolution in Deep Neural Network Implementation for Land Cover Semantic Segmentation of Airborne LiDAR Data
    Hamid, Nur
    Wibisono, Ari
    Ma'sum, M. Anwar
    Gamal, Ahmad
    Ardhianto, Roni
    Arymurthy, Aniati Murni
    Jatmiko, Wisnu
    2019 4TH ASIA-PACIFIC CONFERENCE ON INTELLIGENT ROBOT SYSTEMS (ACIRS 2019), 2019, : 216 - 220
  • [33] Hyperspectral Point Cloud Projection for the Semantic Segmentation of Multimodal Hyperspectral and Lidar Data with Point Convolution-Based Deep Fusion Neural Networks
    Decker, Kevin T.
    Borghetti, Brett J.
    APPLIED SCIENCES-BASEL, 2023, 13 (14):
  • [34] pCTFusion: Point Convolution-Transformer Fusion with Semantic Aware Loss for Outdoor LiDAR Point Cloud Segmentation
    Kuriyal A.
    Kumar V.
    Lohani B.
    SN Computer Science, 5 (3)
  • [35] Semantic Point Cloud Segmentation Using Fast Deep Neural Network and DCRF
    Rao, Yunbo
    Zhang, Menghan
    Cheng, Zhanglin
    Xue, Junmin
    Pu, Jiansu
    Wang, Zairong
    SENSORS, 2021, 21 (08)
  • [36] Point cloud semantic segmentation of complex railway environments using deep learning
    Grandio J.
    Riveiro B.
    Soilán M.
    Arias P.
    Automation in Construction, 2022, 141
  • [37] Building point cloud reconstruction in TomoSAR based on deep learning semantic segmentation
    Shi, Minan
    Chen, Longyong
    Zhang, Fubo
    Li, Wenjie
    Cui, Chenghao
    Liu, Yuling
    ELECTRONICS LETTERS, 2024, 60 (12)
  • [38] A voxel-based deep learning approach for Point Cloud Semantic Segmentation
    Diaz-Medina, Miguel
    Fuertes-Garcia, Jose-Manuel
    Ogayar-Anguita, Carlos-Javier
    Lucena, Manuel
    XXIX SPANISH COMPUTER GRAPHICS CONFERENCE (CEIG19), 2019, : 73 - 76
  • [39] Point Cloud Semantic Segmentation Using a Deep Learning Framework for Cultural Heritage
    Pierdicca, Roberto
    Paolanti, Marina
    Matrone, Francesca
    Martini, Massimo
    Morbidoni, Christian
    Malinverni, Eva Savina
    Frontoni, Emanuele
    Lingua, Andrea Maria
    REMOTE SENSING, 2020, 12 (06)
  • [40] Fusion of Multispectral LiDAR, Hyperspectral, and RGB Data for Urban Land Cover Classification
    Haensch, Ronny
    Hellwich, Olaf
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2021, 18 (02) : 366 - 370