Show simple item record

dc.contributor.authorJahan, F
dc.contributor.authorAwrangjeb, M
dc.contributor.editorD. Li, J. Gong, B. Yang, H. Wu, R. Lindenbergh, J. Boehm, M. Rutzinger, et al.
dc.date.accessioned2017-11-29T03:07:46Z
dc.date.available2017-11-29T03:07:46Z
dc.date.issued2017
dc.identifier.issn1682-1750
dc.identifier.doi10.5194/isprs-archives-XLII-2-W7-711-2017
dc.identifier.urihttp://hdl.handle.net/10072/354644
dc.description.abstractLand cover classification has many applications like forest management, urban planning, land use change identification and environment change analysis. The passive sensing of hyperspectral systems can be effective in describing the phenomenology of the observed area over hundreds of (narrow) spectral bands. On the other hand, the active sensing of LiDAR (Light Detection and Ranging) systems can be exploited for characterising topographical information of the area. As a result, the joint use of hyperspectral and LiDAR data provides a source of complementary information, which can greatly assist in the classification of complex classes. In this study, we fuse hyperspectral and LiDAR data for land cover classification. We do a pixel-wise classification on a disjoint set of training and testing samples for five different classes. We propose a new feature combination by fusing features from both hyperspectral and LiDAR, which achieves competent classification accuracy with low feature dimension, while the existing method requires high dimensional feature vector to achieve similar classification result. Also, for the reduction of the dimension of the feature vector, Principal Component Analysis (PCA) is used as it captures the variance of the samples with a limited number of Principal Components (PCs). We tested our classification method using PCA applied on hyperspectral bands only and combined hyperspectral and LiDAR features. Classification with support vector machine (SVM) and decision tree shows that our feature combination achieves better classification accuracy compared to the existing feature combination, while keeping the similar number of PCs. The experimental results also show that decision tree performs better than SVM and requires less execution time.
dc.description.peerreviewedYes
dc.languageEnglish
dc.publisherInternational Society for Photogrammetry and Remote Sensing (ISPRS)
dc.publisher.placeGermany
dc.relation.ispartofconferencenameISPRS Geospatial Week 2017
dc.relation.ispartofconferencetitleInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
dc.relation.ispartofdatefrom2017-09-18
dc.relation.ispartofdateto2017-09-22
dc.relation.ispartoflocationWuhan, China
dc.relation.ispartofpagefrom711
dc.relation.ispartofpageto718
dc.relation.ispartofissue2W7
dc.relation.ispartofvolume42
dc.subject.fieldofresearchGeomatic engineering
dc.subject.fieldofresearchPhotogrammetry and remote sensing
dc.subject.fieldofresearchcode4013
dc.subject.fieldofresearchcode401304
dc.titlePixel-Based Land Cover Classification by Fusing Hyperspectral and LiDAR Data
dc.typeConference output
dc.type.descriptionE1 - Conferences
dc.type.codeE - Conference Publications
dcterms.licensehttp://creativecommons.org/licenses/by/4.0/
dc.description.versionVersion of Record (VoR)
gro.facultyGriffith Sciences, School of Information and Communication Technology
gro.rights.copyright© The Author(s) 2017. This is an Open Access article distributed under the terms of the Creative Commons Attribution 4.0 International (http://creativecommons.org/licenses/by/4.0/) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
gro.hasfulltextFull Text
gro.griffith.authorAwrangjeb, Mohammad


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record