Show simple item record

dc.contributor.authorLee, Juheonen
dc.contributor.authorCai, Xiaohaoen
dc.contributor.authorLellmann, Janen
dc.contributor.authorDalponte, Micheleen
dc.contributor.authorMalhi, Yadvinderen
dc.contributor.authorButt, Nathalieen
dc.contributor.authorMorecroft, Mikeen
dc.contributor.authorSchönlieb, Carola-Bibianeen
dc.contributor.authorCoomes, Daviden
dc.date.accessioned2016-05-31T15:03:24Z
dc.date.available2016-05-31T15:03:24Z
dc.date.issued2016-06-27en
dc.identifier.issn1939-1404
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/256126
dc.description.abstractRemote sensing of individual tree species has many applications in resource management, biodiversity assessment, and conservation. Airborne remote sensing using light detection and ranging (LiDAR) and hyperspectral sensors has been used extensively to extract biophysical traits of vegetation and to detect species. However, its application for individual tree mapping remains limited due to the technical challenges of precise coalignment of images acquired from different sensors and accurately delineating individual tree crowns (ITCs). In this study, we developed a generic workflow to map tree species at ITC level from hyperspectral imagery and LiDAR data using a combination of well established and recently developed techniques. The workflow uses a nonparametric image registration approach to coalign images, a multiclass normalized graph cut method for ITC delineation, robust principal component analysis for feature extraction, and support vector machine for species classification. This workflow allows us to automatically map tree species at both pixel- and ITC-level. Experimental tests of the technique were conducted using ground data collected from a fully mapped temperate woodland in the UK. The overall accuracy of pixel-level classification was 91%, while that of ITC-level classification was 61%. The test results demonstrate the effectiveness of the approach, and in particular the use of robust principal component analysis to prune the hyperspectral dataset and reveal subtle difference among species.
dc.description.sponsorshipDepartment for Environment, Food and Rural Affairs
dc.languageEnglishen
dc.language.isoenen
dc.publisherIEEE
dc.subjecthyperspectral imagingen
dc.subjectLiDARen
dc.subjectimage registrationen
dc.subjectimage segmentationen
dc.subjectspecies classificationen
dc.subjectPCAen
dc.subjectSVMen
dc.subjectWytham Woodsen
dc.titleIndividual tree species classification from airborne multi-sensor imagery using robust PCAen
dc.typeArticle
dc.description.versionThis is the author accepted manuscript. The final version is available from IEEE via http://dx.doi.org/10.1109/JSTARS.2016.2569408en
prism.endingPage2567
prism.publicationDate2016en
prism.publicationNameIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensingen
prism.startingPage2554
prism.volume9en
dc.identifier.doi10.17863/CAM.62
dcterms.dateAccepted2016-04-29en
rioxxterms.versionofrecord10.1109/JSTARS.2016.2569408en
rioxxterms.versionAMen
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2016-06-27en
dc.contributor.orcidCoomes, David [0000-0002-8261-2582]
dc.identifier.eissn2151-1535
rioxxterms.typeJournal Article/Reviewen
pubs.funder-project-idEPSRC (EP/M00483X/1)
pubs.funder-project-idEPSRC (EP/N014588/1)
pubs.funder-project-idEPSRC (EP/J009539/1)
pubs.funder-project-idAlan Turing Institute (unknown)
pubs.funder-project-idEuropean Commission Horizon 2020 (H2020) Marie Sk?odowska-Curie actions (691070)
pubs.funder-project-idLeverhulme Trust (RPG-2015-250)
pubs.funder-project-idEPSRC (EP/H023348/1)
pubs.funder-project-idEuropean Commission Horizon 2020 (H2020) Marie Sk?odowska-Curie actions (777826)


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record