DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Multi-Scale Local Context Embedding for LiDAR Point Cloud Classification

Huang, Rong and Hong, Danfeng and Xu, yusheng and Yao, wei and Stilla, U. (2020) Multi-Scale Local Context Embedding for LiDAR Point Cloud Classification. IEEE Geoscience and Remote Sensing Letters. IEEE - Institute of Electrical and Electronics Engineers. DOI: 10.1109/LGRS.2019.2927779 ISSN 1545-598X (In Press)

[img] PDF - Registered users only until July 2020 - Postprint version (accepted manuscript)

Official URL: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8777118


The semantic interpretation using point clouds, especially regarding light detection and ranging (LiDAR) point cloud classification, has attracted a growing interest in the fields of photogrammetry, remote sensing, and computer vision. In this letter, we aim at tackling a general and typical feature learning problem in 3-D point cloud classification—how to represent geometric features by structurally considering a point and its surroundings in a more effective and discriminative fashion? Recently, enormous efforts have been made to design the geometric features, yet it is less investigated to fully explore the potentials of the features. For that, there have been many filter-based studies proposed by selecting a subset of the whole feature space for better representing the local geometry structure. However, such a hard-threshold selection strategy inevitably suffers from information loss. In addition, the construction of the geometric features is relatively sensitive to the size of the neighborhood. To this end, we propose to extract multi-scaled feature representations and locally embed them into a low-dimensional and robust subspace where a more compact representation with the intrinsic structure preservation of the data is expected to be obtained, thereby further yielding a better classification performance. In our case, we apply a popular manifold learning approach, that is, locality-preserving projections, for the task of learning low-dimensional embedding. Experimental results conducted on one LiDAR point cloud data set provided by the 2018 IEEE Data Fusion Contest demonstrate the effectiveness of the proposed method in comparison with several commonly used state-of-the-art baselines.

Item URL in elib:https://elib.dlr.de/132299/
Document Type:Article
Title:Multi-Scale Local Context Embedding for LiDAR Point Cloud Classification
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Huang, Rongrong.huang (at) tum.deUNSPECIFIED
Hong, DanfengDanfeng.Hong (at) dlr.deUNSPECIFIED
Yao, weiwei.hn.yao (at) polyu.edu.hkUNSPECIFIED
Stilla, U.TU MuenchenUNSPECIFIED
Journal or Publication Title:IEEE Geoscience and Remote Sensing Letters
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In ISI Web of Science:Yes
DOI :10.1109/LGRS.2019.2927779
Publisher:IEEE - Institute of Electrical and Electronics Engineers
Status:In Press
Keywords:Geometric features, light detection and ranging (LiDAR) point cloud classification, local manifold learning (LML), multi-scale
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben hochauflösende Fernerkundungsverfahren
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Hong, Danfeng
Deposited On:05 Dec 2019 16:11
Last Modified:05 Dec 2019 16:11

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.