The University of Southampton
University of Southampton Institutional Repository

Individual tree species classification from airborne multisensor imagery using robust PCA

Individual tree species classification from airborne multisensor imagery using robust PCA
Individual tree species classification from airborne multisensor imagery using robust PCA
Remote 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.
Hyperspectral imaging, Wytham Woods, image registration, image segmentation, light detection and ranging (Lidar), principal component analysis (PCA), species classification, support vector machine (SVM)
1939-1404
2554-2567
Lee, Juheon
cd382ebf-0bcc-47b8-a60d-68c6540d31bb
Cai, Xiaohao
de483445-45e9-4b21-a4e8-b0427fc72cee
Lellmann, Jan
fb63d608-5e00-4087-8023-d5ba5d7bf7cf
Dalponte, Michele
f2c62e40-39c7-42f8-8831-04bc394a8819
Malhi, Yadvinder
5b0b372b-4a85-4018-9559-903c2bbbe15d
Butt, Nathalie
9557f2ac-89f4-4754-880e-9bc64736c423
Morecroft, Mike
f8909813-b7dd-4c5a-a082-1694e3a07788
Schonlieb, Carola Bibiane
a42e0ee1-9df4-41b3-ae0e-adab80249811
Coomes, David A.
4e3d573c-fda0-4ddc-a621-6a682ff615ca
Lee, Juheon
cd382ebf-0bcc-47b8-a60d-68c6540d31bb
Cai, Xiaohao
de483445-45e9-4b21-a4e8-b0427fc72cee
Lellmann, Jan
fb63d608-5e00-4087-8023-d5ba5d7bf7cf
Dalponte, Michele
f2c62e40-39c7-42f8-8831-04bc394a8819
Malhi, Yadvinder
5b0b372b-4a85-4018-9559-903c2bbbe15d
Butt, Nathalie
9557f2ac-89f4-4754-880e-9bc64736c423
Morecroft, Mike
f8909813-b7dd-4c5a-a082-1694e3a07788
Schonlieb, Carola Bibiane
a42e0ee1-9df4-41b3-ae0e-adab80249811
Coomes, David A.
4e3d573c-fda0-4ddc-a621-6a682ff615ca

Lee, Juheon, Cai, Xiaohao, Lellmann, Jan, Dalponte, Michele, Malhi, Yadvinder, Butt, Nathalie, Morecroft, Mike, Schonlieb, Carola Bibiane and Coomes, David A. (2016) Individual tree species classification from airborne multisensor imagery using robust PCA. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9 (6), 2554-2567, [7500049]. (doi:10.1109/JSTARS.2016.2569408).

Record type: Article

Abstract

Remote 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.

This record has no associated files available for download.

More information

Accepted/In Press date: 29 April 2016
e-pub ahead of print date: 27 June 2016
Published date: June 2016
Keywords: Hyperspectral imaging, Wytham Woods, image registration, image segmentation, light detection and ranging (Lidar), principal component analysis (PCA), species classification, support vector machine (SVM)

Identifiers

Local EPrints ID: 438759
URI: http://eprints.soton.ac.uk/id/eprint/438759
ISSN: 1939-1404
PURE UUID: 303f5f66-9b19-43ac-8ed9-f51897dce28f
ORCID for Xiaohao Cai: ORCID iD orcid.org/0000-0003-0924-2834

Catalogue record

Date deposited: 24 Mar 2020 17:30
Last modified: 17 Mar 2024 04:01

Export record

Altmetrics

Contributors

Author: Juheon Lee
Author: Xiaohao Cai ORCID iD
Author: Jan Lellmann
Author: Michele Dalponte
Author: Yadvinder Malhi
Author: Nathalie Butt
Author: Mike Morecroft
Author: Carola Bibiane Schonlieb
Author: David A. Coomes

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×