An unsupervised change detection and recognition system for forestry

Tuomas Häme, Istvan Heiler (Corresponding Author), Jesus San Miguel-Ayanz

Research output: Contribution to journalArticleScientificpeer-review

110 Citations (Scopus)

Abstract

This article presents a new unsupervised method (AutoChange) for change detection and identification.
It uses, as an input, two images, acquired on different dates, and a parameter list given by the user.
Change detection and identification are performed in separate procedures, and the output is a five channel image estimating the change magnitude and characterizing the changed and unchanged areas. The method carries out the change analysis using homogeneous units selected from the images and only in the ultimate phase the whole image is classified.
Changes are detected and identified using clustering in two phases. First, clustering is performed on the earlier and later images to form the so called 'primary clusters'. Second, clustering is performed within the primary clusters of the later image to produce the 'secondary clusters'.
Then the change magnitude and change type are obtained by comparing the primary clusters in the earlier image to the secondary clusters in the later image.
The method, which was tested in southern Finnish Boreal forest using Landsat Thematic Mapper data, could reliably detect and identify clearcuts.
In addition, the method provided information on forest damage since the type of the spectral change was consistent on damaged areas despite a minor magnitude of the change.
Original languageEnglish
Pages (from-to)1079-1099
JournalInternational Journal of Remote Sensing
Volume19
Issue number6
DOIs
Publication statusPublished - 1998
MoE publication typeA1 Journal article-refereed

Fingerprint

forestry
detection
clearcutting
Landsat thematic mapper
boreal forest
method

Cite this

Häme, Tuomas ; Heiler, Istvan ; Miguel-Ayanz, Jesus San. / An unsupervised change detection and recognition system for forestry. In: International Journal of Remote Sensing. 1998 ; Vol. 19, No. 6. pp. 1079-1099.
@article{f9fec7162fb543f082d2387cf58c9a6f,
title = "An unsupervised change detection and recognition system for forestry",
abstract = "This article presents a new unsupervised method (AutoChange) for change detection and identification. It uses, as an input, two images, acquired on different dates, and a parameter list given by the user. Change detection and identification are performed in separate procedures, and the output is a five channel image estimating the change magnitude and characterizing the changed and unchanged areas. The method carries out the change analysis using homogeneous units selected from the images and only in the ultimate phase the whole image is classified. Changes are detected and identified using clustering in two phases. First, clustering is performed on the earlier and later images to form the so called 'primary clusters'. Second, clustering is performed within the primary clusters of the later image to produce the 'secondary clusters'. Then the change magnitude and change type are obtained by comparing the primary clusters in the earlier image to the secondary clusters in the later image. The method, which was tested in southern Finnish Boreal forest using Landsat Thematic Mapper data, could reliably detect and identify clearcuts. In addition, the method provided information on forest damage since the type of the spectral change was consistent on damaged areas despite a minor magnitude of the change.",
author = "Tuomas H{\"a}me and Istvan Heiler and Miguel-Ayanz, {Jesus San}",
year = "1998",
doi = "10.1080/014311698215612",
language = "English",
volume = "19",
pages = "1079--1099",
journal = "International Journal of Remote Sensing",
issn = "0143-1161",
publisher = "Taylor & Francis",
number = "6",

}

An unsupervised change detection and recognition system for forestry. / Häme, Tuomas; Heiler, Istvan (Corresponding Author); Miguel-Ayanz, Jesus San.

In: International Journal of Remote Sensing, Vol. 19, No. 6, 1998, p. 1079-1099.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - An unsupervised change detection and recognition system for forestry

AU - Häme, Tuomas

AU - Heiler, Istvan

AU - Miguel-Ayanz, Jesus San

PY - 1998

Y1 - 1998

N2 - This article presents a new unsupervised method (AutoChange) for change detection and identification. It uses, as an input, two images, acquired on different dates, and a parameter list given by the user. Change detection and identification are performed in separate procedures, and the output is a five channel image estimating the change magnitude and characterizing the changed and unchanged areas. The method carries out the change analysis using homogeneous units selected from the images and only in the ultimate phase the whole image is classified. Changes are detected and identified using clustering in two phases. First, clustering is performed on the earlier and later images to form the so called 'primary clusters'. Second, clustering is performed within the primary clusters of the later image to produce the 'secondary clusters'. Then the change magnitude and change type are obtained by comparing the primary clusters in the earlier image to the secondary clusters in the later image. The method, which was tested in southern Finnish Boreal forest using Landsat Thematic Mapper data, could reliably detect and identify clearcuts. In addition, the method provided information on forest damage since the type of the spectral change was consistent on damaged areas despite a minor magnitude of the change.

AB - This article presents a new unsupervised method (AutoChange) for change detection and identification. It uses, as an input, two images, acquired on different dates, and a parameter list given by the user. Change detection and identification are performed in separate procedures, and the output is a five channel image estimating the change magnitude and characterizing the changed and unchanged areas. The method carries out the change analysis using homogeneous units selected from the images and only in the ultimate phase the whole image is classified. Changes are detected and identified using clustering in two phases. First, clustering is performed on the earlier and later images to form the so called 'primary clusters'. Second, clustering is performed within the primary clusters of the later image to produce the 'secondary clusters'. Then the change magnitude and change type are obtained by comparing the primary clusters in the earlier image to the secondary clusters in the later image. The method, which was tested in southern Finnish Boreal forest using Landsat Thematic Mapper data, could reliably detect and identify clearcuts. In addition, the method provided information on forest damage since the type of the spectral change was consistent on damaged areas despite a minor magnitude of the change.

U2 - 10.1080/014311698215612

DO - 10.1080/014311698215612

M3 - Article

VL - 19

SP - 1079

EP - 1099

JO - International Journal of Remote Sensing

JF - International Journal of Remote Sensing

SN - 0143-1161

IS - 6

ER -