Highforest-forest parameter estimation from high resolution remote sensing data

Heikki Astola, Catherine Bounsaythip, Jussi Ahola, Tuomas Häme, Eija Parmes, Laura Sirro, Brita Veikkanen

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

6 Citations (Scopus)

Abstract

The aim of the study was to develop a tool for the estimation of forest variables using high-resolution satellite data. The tool included modular operative software. The image analysis methodology focused on the reduction of the known problems of the previous satellite image based methods, i.e. the saturation of the estimates at higher biomass levels and uncertainty in tree species estimation. Modern contextual image analysis methods were combined with the spectral information of the imagery. In the test application the tool used images from the Ikonos satellite with a ground resolution of one and four meters. The developed Forestime software estimated the forest variables by segmenting the imagery to 'micro-stands', by computing stand-wise image feature vectors for the stands from the input satellite image, and by combining ground reference data with clusters from an unsupervised clustering stage. The estimates are produced as weighted sums of the input sample class probabilities. The target variables in the study were stem volume, average stem diameter, stem number and tree species proportions. The RMSE% for total stem volume was 37.4 % (% of mean), for average stem diameter 23.4 %, for stem number 87 %, for pine percentage 111 %, for spruce percentage 47 %, and for broad-leaved tree percentage 137 %.
Original languageEnglish
Title of host publicationProceedings of the International Society for Photogrammetry and Remote Sensing XXth Congress
EditorsOrhan Altan
Place of PublicationIstanbul
PublisherInternational Society for Photogrammetry and Remote Sensing ISPRS
Pages335-341
Number of pages6
VolumeXXXV Part B7
Publication statusPublished - 2004
MoE publication typeNot Eligible
EventXXth ISPRS Congress - Istanbul, Turkey
Duration: 12 Jul 200423 Jul 2004

Conference

ConferenceXXth ISPRS Congress
CountryTurkey
CityIstanbul
Period12/07/0423/07/04

Fingerprint

stem
remote sensing
image analysis
imagery
software
parameter estimation
satellite data
saturation
methodology
biomass
satellite image
method

Keywords

  • remote sensing
  • forestry
  • automation
  • estimation
  • inventory
  • high resolution

Cite this

Astola, H., Bounsaythip, C., Ahola, J., Häme, T., Parmes, E., Sirro, L., & Veikkanen, B. (2004). Highforest-forest parameter estimation from high resolution remote sensing data. In O. Altan (Ed.), Proceedings of the International Society for Photogrammetry and Remote Sensing XXth Congress (Vol. XXXV Part B7, pp. 335-341). Istanbul: International Society for Photogrammetry and Remote Sensing ISPRS.
Astola, Heikki ; Bounsaythip, Catherine ; Ahola, Jussi ; Häme, Tuomas ; Parmes, Eija ; Sirro, Laura ; Veikkanen, Brita. / Highforest-forest parameter estimation from high resolution remote sensing data. Proceedings of the International Society for Photogrammetry and Remote Sensing XXth Congress. editor / Orhan Altan. Vol. XXXV Part B7 Istanbul : International Society for Photogrammetry and Remote Sensing ISPRS, 2004. pp. 335-341
@inproceedings{4537ab1b5cf24b739e8dfe98866fb167,
title = "Highforest-forest parameter estimation from high resolution remote sensing data",
abstract = "The aim of the study was to develop a tool for the estimation of forest variables using high-resolution satellite data. The tool included modular operative software. The image analysis methodology focused on the reduction of the known problems of the previous satellite image based methods, i.e. the saturation of the estimates at higher biomass levels and uncertainty in tree species estimation. Modern contextual image analysis methods were combined with the spectral information of the imagery. In the test application the tool used images from the Ikonos satellite with a ground resolution of one and four meters. The developed Forestime software estimated the forest variables by segmenting the imagery to 'micro-stands', by computing stand-wise image feature vectors for the stands from the input satellite image, and by combining ground reference data with clusters from an unsupervised clustering stage. The estimates are produced as weighted sums of the input sample class probabilities. The target variables in the study were stem volume, average stem diameter, stem number and tree species proportions. The RMSE{\%} for total stem volume was 37.4 {\%} ({\%} of mean), for average stem diameter 23.4 {\%}, for stem number 87 {\%}, for pine percentage 111 {\%}, for spruce percentage 47 {\%}, and for broad-leaved tree percentage 137 {\%}.",
keywords = "remote sensing, forestry, automation, estimation, inventory, high resolution",
author = "Heikki Astola and Catherine Bounsaythip and Jussi Ahola and Tuomas H{\"a}me and Eija Parmes and Laura Sirro and Brita Veikkanen",
year = "2004",
language = "English",
volume = "XXXV Part B7",
pages = "335--341",
editor = "Orhan Altan",
booktitle = "Proceedings of the International Society for Photogrammetry and Remote Sensing XXth Congress",
publisher = "International Society for Photogrammetry and Remote Sensing ISPRS",

}

Astola, H, Bounsaythip, C, Ahola, J, Häme, T, Parmes, E, Sirro, L & Veikkanen, B 2004, Highforest-forest parameter estimation from high resolution remote sensing data. in O Altan (ed.), Proceedings of the International Society for Photogrammetry and Remote Sensing XXth Congress. vol. XXXV Part B7, International Society for Photogrammetry and Remote Sensing ISPRS, Istanbul, pp. 335-341, XXth ISPRS Congress, Istanbul, Turkey, 12/07/04.

Highforest-forest parameter estimation from high resolution remote sensing data. / Astola, Heikki; Bounsaythip, Catherine; Ahola, Jussi; Häme, Tuomas; Parmes, Eija; Sirro, Laura; Veikkanen, Brita.

Proceedings of the International Society for Photogrammetry and Remote Sensing XXth Congress. ed. / Orhan Altan. Vol. XXXV Part B7 Istanbul : International Society for Photogrammetry and Remote Sensing ISPRS, 2004. p. 335-341.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Highforest-forest parameter estimation from high resolution remote sensing data

AU - Astola, Heikki

AU - Bounsaythip, Catherine

AU - Ahola, Jussi

AU - Häme, Tuomas

AU - Parmes, Eija

AU - Sirro, Laura

AU - Veikkanen, Brita

PY - 2004

Y1 - 2004

N2 - The aim of the study was to develop a tool for the estimation of forest variables using high-resolution satellite data. The tool included modular operative software. The image analysis methodology focused on the reduction of the known problems of the previous satellite image based methods, i.e. the saturation of the estimates at higher biomass levels and uncertainty in tree species estimation. Modern contextual image analysis methods were combined with the spectral information of the imagery. In the test application the tool used images from the Ikonos satellite with a ground resolution of one and four meters. The developed Forestime software estimated the forest variables by segmenting the imagery to 'micro-stands', by computing stand-wise image feature vectors for the stands from the input satellite image, and by combining ground reference data with clusters from an unsupervised clustering stage. The estimates are produced as weighted sums of the input sample class probabilities. The target variables in the study were stem volume, average stem diameter, stem number and tree species proportions. The RMSE% for total stem volume was 37.4 % (% of mean), for average stem diameter 23.4 %, for stem number 87 %, for pine percentage 111 %, for spruce percentage 47 %, and for broad-leaved tree percentage 137 %.

AB - The aim of the study was to develop a tool for the estimation of forest variables using high-resolution satellite data. The tool included modular operative software. The image analysis methodology focused on the reduction of the known problems of the previous satellite image based methods, i.e. the saturation of the estimates at higher biomass levels and uncertainty in tree species estimation. Modern contextual image analysis methods were combined with the spectral information of the imagery. In the test application the tool used images from the Ikonos satellite with a ground resolution of one and four meters. The developed Forestime software estimated the forest variables by segmenting the imagery to 'micro-stands', by computing stand-wise image feature vectors for the stands from the input satellite image, and by combining ground reference data with clusters from an unsupervised clustering stage. The estimates are produced as weighted sums of the input sample class probabilities. The target variables in the study were stem volume, average stem diameter, stem number and tree species proportions. The RMSE% for total stem volume was 37.4 % (% of mean), for average stem diameter 23.4 %, for stem number 87 %, for pine percentage 111 %, for spruce percentage 47 %, and for broad-leaved tree percentage 137 %.

KW - remote sensing

KW - forestry

KW - automation

KW - estimation

KW - inventory

KW - high resolution

M3 - Conference article in proceedings

VL - XXXV Part B7

SP - 335

EP - 341

BT - Proceedings of the International Society for Photogrammetry and Remote Sensing XXth Congress

A2 - Altan, Orhan

PB - International Society for Photogrammetry and Remote Sensing ISPRS

CY - Istanbul

ER -

Astola H, Bounsaythip C, Ahola J, Häme T, Parmes E, Sirro L et al. Highforest-forest parameter estimation from high resolution remote sensing data. In Altan O, editor, Proceedings of the International Society for Photogrammetry and Remote Sensing XXth Congress. Vol. XXXV Part B7. Istanbul: International Society for Photogrammetry and Remote Sensing ISPRS. 2004. p. 335-341