Forest cover-type classification using SPOT4 and SPOT5 images

Su Fen Wang, Chi Chuan Cheng, Yeong Kuan Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This study focuses on the forest cover-type classification using remote sensing techniques. The SPOT4 and SPOT5 images, which cover the Chilanshan mountainous area located in the northeastern part of Taiwan, are applied to classify forest cover types into three classes using supervised classification approach. The classified three classes are natural Chamaecyparis formosensis forests, coniferous plantations, and nature broadleaf forests, respectively. To improve the classification accuracy of forest cover types, SPOT5 image (spatial resolution is 10m) and SPOT4 image (spatial resolution is 20m) were integrated together by the mosaic technique. In addition, the ground permanent samples established for continuous forest inventory were also used to assess the classification accuracy of forest cover types. The result indicates that the classification accuracy in SPOT5 is better than in SPOT4 because of the finer resolution. However, among these three classes, the natural broadleaf forests have low accuracy due to the complicated stand structure.

Original languageEnglish
Title of host publicationAsian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006
Pages985-989
Number of pages5
Publication statusPublished - 2006 Dec 1
Event27th Asian Conference on Remote Sensing, ACRS 2006 - Ulaanbaatar, Mongolia
Duration: 2006 Oct 92006 Oct 13

Publication series

NameAsian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006

Other

Other27th Asian Conference on Remote Sensing, ACRS 2006
CountryMongolia
CityUlaanbaatar
Period06-10-0906-10-13

Fingerprint

Remote sensing

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Wang, S. F., Cheng, C. C., & Chen, Y. K. (2006). Forest cover-type classification using SPOT4 and SPOT5 images. In Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006 (pp. 985-989). (Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006).
Wang, Su Fen ; Cheng, Chi Chuan ; Chen, Yeong Kuan. / Forest cover-type classification using SPOT4 and SPOT5 images. Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006. 2006. pp. 985-989 (Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006).
@inproceedings{5feca1c8e24544abaac059ed01fd76b0,
title = "Forest cover-type classification using SPOT4 and SPOT5 images",
abstract = "This study focuses on the forest cover-type classification using remote sensing techniques. The SPOT4 and SPOT5 images, which cover the Chilanshan mountainous area located in the northeastern part of Taiwan, are applied to classify forest cover types into three classes using supervised classification approach. The classified three classes are natural Chamaecyparis formosensis forests, coniferous plantations, and nature broadleaf forests, respectively. To improve the classification accuracy of forest cover types, SPOT5 image (spatial resolution is 10m) and SPOT4 image (spatial resolution is 20m) were integrated together by the mosaic technique. In addition, the ground permanent samples established for continuous forest inventory were also used to assess the classification accuracy of forest cover types. The result indicates that the classification accuracy in SPOT5 is better than in SPOT4 because of the finer resolution. However, among these three classes, the natural broadleaf forests have low accuracy due to the complicated stand structure.",
author = "Wang, {Su Fen} and Cheng, {Chi Chuan} and Chen, {Yeong Kuan}",
year = "2006",
month = "12",
day = "1",
language = "English",
isbn = "9781604231380",
series = "Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006",
pages = "985--989",
booktitle = "Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006",

}

Wang, SF, Cheng, CC & Chen, YK 2006, Forest cover-type classification using SPOT4 and SPOT5 images. in Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006. Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006, pp. 985-989, 27th Asian Conference on Remote Sensing, ACRS 2006, Ulaanbaatar, Mongolia, 06-10-09.

Forest cover-type classification using SPOT4 and SPOT5 images. / Wang, Su Fen; Cheng, Chi Chuan; Chen, Yeong Kuan.

Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006. 2006. p. 985-989 (Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Forest cover-type classification using SPOT4 and SPOT5 images

AU - Wang, Su Fen

AU - Cheng, Chi Chuan

AU - Chen, Yeong Kuan

PY - 2006/12/1

Y1 - 2006/12/1

N2 - This study focuses on the forest cover-type classification using remote sensing techniques. The SPOT4 and SPOT5 images, which cover the Chilanshan mountainous area located in the northeastern part of Taiwan, are applied to classify forest cover types into three classes using supervised classification approach. The classified three classes are natural Chamaecyparis formosensis forests, coniferous plantations, and nature broadleaf forests, respectively. To improve the classification accuracy of forest cover types, SPOT5 image (spatial resolution is 10m) and SPOT4 image (spatial resolution is 20m) were integrated together by the mosaic technique. In addition, the ground permanent samples established for continuous forest inventory were also used to assess the classification accuracy of forest cover types. The result indicates that the classification accuracy in SPOT5 is better than in SPOT4 because of the finer resolution. However, among these three classes, the natural broadleaf forests have low accuracy due to the complicated stand structure.

AB - This study focuses on the forest cover-type classification using remote sensing techniques. The SPOT4 and SPOT5 images, which cover the Chilanshan mountainous area located in the northeastern part of Taiwan, are applied to classify forest cover types into three classes using supervised classification approach. The classified three classes are natural Chamaecyparis formosensis forests, coniferous plantations, and nature broadleaf forests, respectively. To improve the classification accuracy of forest cover types, SPOT5 image (spatial resolution is 10m) and SPOT4 image (spatial resolution is 20m) were integrated together by the mosaic technique. In addition, the ground permanent samples established for continuous forest inventory were also used to assess the classification accuracy of forest cover types. The result indicates that the classification accuracy in SPOT5 is better than in SPOT4 because of the finer resolution. However, among these three classes, the natural broadleaf forests have low accuracy due to the complicated stand structure.

UR - http://www.scopus.com/inward/record.url?scp=84865637016&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865637016&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84865637016

SN - 9781604231380

T3 - Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006

SP - 985

EP - 989

BT - Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006

ER -

Wang SF, Cheng CC, Chen YK. Forest cover-type classification using SPOT4 and SPOT5 images. In Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006. 2006. p. 985-989. (Asian Association on Remote Sensing - 27th Asian Conference on Remote Sensing, ACRS 2006).