Assessment of classifiers and remote sensing features of hyperspectral imagery and stereo-photogrammetric point clouds for recognition of tree species in a forest area of high species diversity

Sakari Tuominen (Corresponding Author), Roope Näsi, Eija Honkavaara, Andras Balazs, Teemu Hakala, Niko Viljanen, Ilkka Pölönen, Heikki Saari, Harri Ojanen

Research output: Contribution to journalArticleScientificpeer-review

9 Citations (Scopus)

Abstract

Recognition of tree species and geospatial information on tree species composition is essential for forest management. In this study, tree species recognition was examined using hyperspectral imagery from visible to near-infrared (VNIR) and short-wave infrared (SWIR) camera sensors in combination with a 3D photogrammetric canopy surface model based on RGB camera stereo-imagery. An arboretum with a diverse selection of 26 tree species from 14 genera was used as a test area. Aerial hyperspectral imagery and high spatial resolution photogrammetric color imagery were acquired from the test area using unmanned aerial vehicle (UAV) borne sensors. Hyperspectral imagery was processed to calibrated reflectance mosaics and was tested along with the mosaics based on original image digital number values (DN). Two alternative classifiers, a k nearest neighbor method (k-nn), combined with a genetic algorithm and a random forest method, were tested for predicting the tree species and genus, as well as for selecting an optimal set of remote sensing features for this task. The combination of VNIR, SWIR, and 3D features performed better than any of the data sets individually. Furthermore, the calibrated reflectance values performed better compared to uncorrected DN values. These trends were similar with both tested classifiers. Of the classifiers, the k-nn combined with the genetic algorithm provided consistently better results than the random forest algorithm. The best result was thus achieved using calibrated reflectance features from VNIR and SWIR imagery together with 3D point cloud features; the proportion of correctly-classified trees was 0.823 for tree species and 0.869 for tree genus.

Original languageEnglish
Article number714
JournalRemote Sensing
Volume10
Issue number5
DOIs
Publication statusPublished - 1 May 2018
MoE publication typeA1 Journal article-refereed

Fingerprint

species diversity
imagery
remote sensing
reflectance
near infrared
genetic algorithm
sensor
infrared imagery
digital image
forest management
spatial resolution
canopy
method

Keywords

  • Dense point cloud
  • Genetic algorithm
  • Hyperspectral imagery
  • Machine learning
  • Photogrammetry
  • Random forest
  • Reflectance calibration
  • Tree species recognition
  • UAV

Cite this

@article{1eec6c15f13f4bc58709e04ce021adfd,
title = "Assessment of classifiers and remote sensing features of hyperspectral imagery and stereo-photogrammetric point clouds for recognition of tree species in a forest area of high species diversity",
abstract = "Recognition of tree species and geospatial information on tree species composition is essential for forest management. In this study, tree species recognition was examined using hyperspectral imagery from visible to near-infrared (VNIR) and short-wave infrared (SWIR) camera sensors in combination with a 3D photogrammetric canopy surface model based on RGB camera stereo-imagery. An arboretum with a diverse selection of 26 tree species from 14 genera was used as a test area. Aerial hyperspectral imagery and high spatial resolution photogrammetric color imagery were acquired from the test area using unmanned aerial vehicle (UAV) borne sensors. Hyperspectral imagery was processed to calibrated reflectance mosaics and was tested along with the mosaics based on original image digital number values (DN). Two alternative classifiers, a k nearest neighbor method (k-nn), combined with a genetic algorithm and a random forest method, were tested for predicting the tree species and genus, as well as for selecting an optimal set of remote sensing features for this task. The combination of VNIR, SWIR, and 3D features performed better than any of the data sets individually. Furthermore, the calibrated reflectance values performed better compared to uncorrected DN values. These trends were similar with both tested classifiers. Of the classifiers, the k-nn combined with the genetic algorithm provided consistently better results than the random forest algorithm. The best result was thus achieved using calibrated reflectance features from VNIR and SWIR imagery together with 3D point cloud features; the proportion of correctly-classified trees was 0.823 for tree species and 0.869 for tree genus.",
keywords = "Dense point cloud, Genetic algorithm, Hyperspectral imagery, Machine learning, Photogrammetry, Random forest, Reflectance calibration, Tree species recognition, UAV",
author = "Sakari Tuominen and Roope N{\"a}si and Eija Honkavaara and Andras Balazs and Teemu Hakala and Niko Viljanen and Ilkka P{\"o}l{\"o}nen and Heikki Saari and Harri Ojanen",
year = "2018",
month = "5",
day = "1",
doi = "10.3390/rs10050714",
language = "English",
volume = "10",
journal = "Remote Sensing",
issn = "2072-4292",
publisher = "MDPI",
number = "5",

}

Assessment of classifiers and remote sensing features of hyperspectral imagery and stereo-photogrammetric point clouds for recognition of tree species in a forest area of high species diversity. / Tuominen, Sakari (Corresponding Author); Näsi, Roope; Honkavaara, Eija; Balazs, Andras; Hakala, Teemu; Viljanen, Niko; Pölönen, Ilkka; Saari, Heikki; Ojanen, Harri.

In: Remote Sensing, Vol. 10, No. 5, 714, 01.05.2018.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Assessment of classifiers and remote sensing features of hyperspectral imagery and stereo-photogrammetric point clouds for recognition of tree species in a forest area of high species diversity

AU - Tuominen, Sakari

AU - Näsi, Roope

AU - Honkavaara, Eija

AU - Balazs, Andras

AU - Hakala, Teemu

AU - Viljanen, Niko

AU - Pölönen, Ilkka

AU - Saari, Heikki

AU - Ojanen, Harri

PY - 2018/5/1

Y1 - 2018/5/1

N2 - Recognition of tree species and geospatial information on tree species composition is essential for forest management. In this study, tree species recognition was examined using hyperspectral imagery from visible to near-infrared (VNIR) and short-wave infrared (SWIR) camera sensors in combination with a 3D photogrammetric canopy surface model based on RGB camera stereo-imagery. An arboretum with a diverse selection of 26 tree species from 14 genera was used as a test area. Aerial hyperspectral imagery and high spatial resolution photogrammetric color imagery were acquired from the test area using unmanned aerial vehicle (UAV) borne sensors. Hyperspectral imagery was processed to calibrated reflectance mosaics and was tested along with the mosaics based on original image digital number values (DN). Two alternative classifiers, a k nearest neighbor method (k-nn), combined with a genetic algorithm and a random forest method, were tested for predicting the tree species and genus, as well as for selecting an optimal set of remote sensing features for this task. The combination of VNIR, SWIR, and 3D features performed better than any of the data sets individually. Furthermore, the calibrated reflectance values performed better compared to uncorrected DN values. These trends were similar with both tested classifiers. Of the classifiers, the k-nn combined with the genetic algorithm provided consistently better results than the random forest algorithm. The best result was thus achieved using calibrated reflectance features from VNIR and SWIR imagery together with 3D point cloud features; the proportion of correctly-classified trees was 0.823 for tree species and 0.869 for tree genus.

AB - Recognition of tree species and geospatial information on tree species composition is essential for forest management. In this study, tree species recognition was examined using hyperspectral imagery from visible to near-infrared (VNIR) and short-wave infrared (SWIR) camera sensors in combination with a 3D photogrammetric canopy surface model based on RGB camera stereo-imagery. An arboretum with a diverse selection of 26 tree species from 14 genera was used as a test area. Aerial hyperspectral imagery and high spatial resolution photogrammetric color imagery were acquired from the test area using unmanned aerial vehicle (UAV) borne sensors. Hyperspectral imagery was processed to calibrated reflectance mosaics and was tested along with the mosaics based on original image digital number values (DN). Two alternative classifiers, a k nearest neighbor method (k-nn), combined with a genetic algorithm and a random forest method, were tested for predicting the tree species and genus, as well as for selecting an optimal set of remote sensing features for this task. The combination of VNIR, SWIR, and 3D features performed better than any of the data sets individually. Furthermore, the calibrated reflectance values performed better compared to uncorrected DN values. These trends were similar with both tested classifiers. Of the classifiers, the k-nn combined with the genetic algorithm provided consistently better results than the random forest algorithm. The best result was thus achieved using calibrated reflectance features from VNIR and SWIR imagery together with 3D point cloud features; the proportion of correctly-classified trees was 0.823 for tree species and 0.869 for tree genus.

KW - Dense point cloud

KW - Genetic algorithm

KW - Hyperspectral imagery

KW - Machine learning

KW - Photogrammetry

KW - Random forest

KW - Reflectance calibration

KW - Tree species recognition

KW - UAV

UR - http://www.scopus.com/inward/record.url?scp=85047571087&partnerID=8YFLogxK

U2 - 10.3390/rs10050714

DO - 10.3390/rs10050714

M3 - Article

AN - SCOPUS:85047571087

VL - 10

JO - Remote Sensing

JF - Remote Sensing

SN - 2072-4292

IS - 5

M1 - 714

ER -