Land cover classification using LiDAR height texture and ANNs

doi:10.11834/jrs.20119282

Views : 0 下载量: 984 CSCD: 11 更多指标

PDF
Export
Share
Collection
Album

Land cover classification using LiDAR height texture and ANNs
Vol. 15, Issue 3, Pages: 539-553(2011)
Published： 2011 ，
DOI： 10.11834/jrs.20119282

扫描看全文

[1]乔纪纲,刘小平,张亦汉.基于LiDAR高度纹理和神经网络的地物分类[J].遥感学报,2011,15(03):539-553.

Land cover classification using LiDAR height texture and ANNs. [J]. Journal of Remote Sensing 15(3):539-553(2011)
[1]乔纪纲,刘小平,张亦汉.基于LiDAR高度纹理和神经网络的地物分类[J].遥感学报,2011,15(03):539-553. DOI： 10.11834/jrs.20119282.

Land cover classification using LiDAR height texture and ANNs. [J]. Journal of Remote Sensing 15(3):539-553(2011) DOI： 10.11834/jrs.20119282.

摘要

使用LiDAR单一数据进行点云分割工作时

基于斜率的严格分割LiDAR点云的方法不能很好的适应复杂地物的分类工作。本文将LiDAR粗分割后的点云转换为高度图像和反射强度图像

并求取高度图像GLCM高度纹理。将4种GLCM高度纹理、地面粗糙系数、平均高度和平均反射强度共7种纹理作为识别地面覆盖物的特征

并利用后向传播神经网络（BP-ANN）方法对LiDAR数据进行地物识别。实验表明

这种方法能够从LiDAR独立数据源中有效的实现地物分类

实验获得的精度大于90%。与传统的最大似然法进行对比

BP-ANN的分类精度高于最大似然法。当预设地面类型能同时满足被光学影像和LiDAR数据识别的条件时

LiDAR高度纹理分类与光学影像分类结果的一致性达到76.5%。

Abstract

The method of strict slope threshold algorithm is not sufficient to achieve complex object identification or ground features classification from LiDAR data.In this research

artificial intelligence is used to classify the ground features based on the LiDAR height texture.Average elevation image

average intensity image and ground roughness index image are derived from LiDAR points.Then

4 GLCM texture features including entropy

various

second moment and homogeneity texture are measured.Finally

BP-ANNs are used to classify the texture measure into five ground feature types.A coastal area of Zhujiang Delta

South of China

is taken as the study area.The method employed in this research can efficiently work with single LiDAR data source and the accuracy of classification result is > 90%

and the classification accuracy of Maximal Likelihood method（ML） is 86.8% for comparison.When the result of ANNs classification is compared with the result of optical image classification

it can be found that 76.5% sample points are in accord.

关键词

LiDAR高度纹理人工神经网络地面粗糙度分类

Keywords

LiDARheight textureArtificial Neural Network（ANNs）ground roughness indexclassification

references

Alert me when the article has been cited

提交

Net primary productivity estimation of Dongting Lake wetland

Diversity features collaboration technology for monitoring forests before and after hurricanes by remote sensing

Indicative features for identifying corn and soybean using remote sensing imagery at middle and later growth season

Deep fusion of hyperspectral images and multi-source remote sensing data for classification with convolutional neural network

Object-oriented crop classification for GF-6 WFV remote sensing images based on Convolutional Neural Network

相关机构

Research Center of Forestry Remote Sensing & Information Engineering, Central South University of Forestry & Technology

Key Laboratory of Forestry Remote Sensing Based Big Data & Ecological Security for Hunan Province, Central South University of Forestry & Technology

Key Laboratory of State Forestry & Grassland Administration on Forest Resources Management and Monitoring in Southern Area, Central South University of Forestry & Technology

Research Institute of Forest Resources Information Techniques, ChineseAcademy of Forestry

School of Electronic Engineering, Xidian University

Postal code：100190
Tel：010-58887052 Email：nrsb@aircas.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备20021838号-9 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰