LiDAR Data Classification Using Morphological Profiles and Convolutional Neural Networks

LiDAR Data Classification Using Morphological Profiles and Convolutional Neural Networks
复制标题

使用形态学轮廓和卷积神经网络进行 LiDAR 数据分类

DOI:
10.1109/lgrs.2018.2810276
复制
发表时间:
2018-03
影响因子:
4.8
通讯作者:
Yushi Chen
Yushi Chen
中科院分区:
工程技术2区
文献类型:
--
作者:
Aili Wang;Xin He;Pedram Ghamisi;Yushi Chen

文献摘要

参考文献

被引文献

相似文献

近年来,基于深度学习的方法,特别是卷积神经网络(CNN),在遥感数据处理中显示出了其能力。光探测和测距(LiDAR)的功效已经在各种研究领域得到了证明。现有的大多数方法都没有从LiDAR衍生的栅格化数字表面模型(LiDAR-DSM)数据中以深入的方式提取信息特征。为了利用深度模型对LiDAR衍生特征进行分类的优势,本文提出了深度CNN来分层提取输入数据的鲁棒性和判别性特征。此外,形态配置文件和多属性配置文件(MAP)进行了研究,以丰富CNN的输入,并进一步提高最终的分类性能。此外,一个新的激活函数,sigmoid-weighted线性单元(SiLUs),被引入。所提出的框架在两个LiDAR-DSM上进行了测试(即,Bayview Park和Houston数据集)。在Bayview Park和Houston数据集上,当每个类的训练样本数量为40时,具有SiLU的MAP-CNN在总体准确性方面分别优于原始CNN 6.62%和6.88%。
In recent years, deep learning-based methods, especially convolutional neural networks (CNNs), have shown their capabilities in remote sensing data processing. The efficacy of light detection and ranging (LiDAR) has been already proven in a wide variety of research areas. Most of the existing methods do not extract the informative features from LiDAR-derived rasterized digital surface models (LiDAR-DSM) data in a deep manner. In order to utilize the advantages of deep models for the classification of LiDAR-derived features, deep CNN is proposed here to hierarchically extract the robust and discriminant features of the input data. Moreover, morphological profiles and multiattribute profiles (MAPs) are investigated to enrich the inputs of the CNN and further to improve the ultimate classification performance. Furthermore, a new activation function, sigmoid-weighted linear units (SiLUs), is introduced. The proposed frameworks are tested on two LiDAR-DSMs (i.e., Bayview Park and Houston data sets). The MAP-CNNs with SiLU outperform original CNNs by 6.62% and 6.88% in terms of overall accuracy on Bayview Park and Houston data sets, respectively, when the number of training samples of each class is 40.
DOI: 10.1109/tgrs.2017.2769120
发表时间: 2018-04
影响因子: 8.2
作者:
Liqiang Zhang;Liang Zhang
通讯作者: Liang Zhang
DOI: 10.1080/01431161.2010.512425
发表时间: 2010-01-01
影响因子: 3.4
作者:
Dalla Mura, Mauro;Benediktsson, Jon Atli;Bruzzone, Lorenzo
通讯作者: Bruzzone, Lorenzo
DOI: 10.1109/whispers.2011.6080867
发表时间: 2011-06
期刊: 2011 3rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)
影响因子: --
作者:
G. Licciardi;P. Marpu;J. Benediktsson;J. Chanussot
通讯作者: G. Licciardi;P. Marpu;J. Benediktsson;J. Chanussot
DOI: 10.1109/tgrs.2002.804618
发表时间: 2002-09-01
影响因子: 8.2
作者:
Soille, P;Pesaresi, M
通讯作者: Pesaresi, M
DOI: 10.1109/i2mtc.2013.6555443
发表时间: 2013-05
期刊: 2013 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
影响因子: --
作者:
Deming Kong;Lijun Xu;Xiaolu Li;Shuyang Li
通讯作者: Deming Kong;Lijun Xu;Xiaolu Li;Shuyang Li