Forest cover classification by optimal segmentation of high resolution satellite imagery

So Ra Kim, Woo-Kyun Lee, Doo Ahn Kwak, Greg S. Biging, Peng Gong, Jun Hak Lee, Hyun Kook Cho

Research output: Contribution to journalArticle

32 Citations (Scopus)

Abstract

This study investigated whether high-resolution satellite imagery is suitable for preparing a detailed digital forest cover map that discriminates forest cover at the tree species level. First, we tried to find an optimal process for segmenting the high-resolution images using a region-growing method with the scale, color and shape factors in Definiens® Professional 5.0. The image was classified by a traditional, pixel-based, maximum likelihood classification approach using the spectral information of the pixels. The pixels in each segment were reclassified using a segment-based classification (SBC) with a majority rule. Segmentation with strongly weighted color was less sensitive to the scale parameter and led to optimal forest cover segmentation and classification. The pixel-based classification (PBC) suffered from the "salt-and-pepper effect" and performed poorly in the classification of forest cover types, whereas the SBC helped to attenuate the effect and notably improved the classification accuracy. As a whole, SBC proved to be more suitable for classifying and delineating forest cover using high-resolution satellite images.

Original languageEnglish
Pages (from-to)1943-1958
Number of pages16
JournalSensors
Volume11
Issue number2
DOIs
Publication statusPublished - 2011 Feb 1

Fingerprint

Satellite Imagery
satellite imagery
Satellite imagery
high resolution
Pixels
pixels
Color
peppers
color
Forests
Image resolution
classifying
Maximum likelihood
Salts
Satellites
salts

Keywords

  • Digital forest cover map
  • High resolution
  • Pixel-based classification
  • Satellite image
  • Segment-based classification

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Atomic and Molecular Physics, and Optics
  • Analytical Chemistry
  • Biochemistry

Cite this

Kim, S. R., Lee, W-K., Kwak, D. A., Biging, G. S., Gong, P., Lee, J. H., & Cho, H. K. (2011). Forest cover classification by optimal segmentation of high resolution satellite imagery. Sensors, 11(2), 1943-1958. https://doi.org/10.3390/s110201943

Forest cover classification by optimal segmentation of high resolution satellite imagery. / Kim, So Ra; Lee, Woo-Kyun; Kwak, Doo Ahn; Biging, Greg S.; Gong, Peng; Lee, Jun Hak; Cho, Hyun Kook.

In: Sensors, Vol. 11, No. 2, 01.02.2011, p. 1943-1958.

Research output: Contribution to journalArticle

Kim, SR, Lee, W-K, Kwak, DA, Biging, GS, Gong, P, Lee, JH & Cho, HK 2011, 'Forest cover classification by optimal segmentation of high resolution satellite imagery', Sensors, vol. 11, no. 2, pp. 1943-1958. https://doi.org/10.3390/s110201943
Kim, So Ra ; Lee, Woo-Kyun ; Kwak, Doo Ahn ; Biging, Greg S. ; Gong, Peng ; Lee, Jun Hak ; Cho, Hyun Kook. / Forest cover classification by optimal segmentation of high resolution satellite imagery. In: Sensors. 2011 ; Vol. 11, No. 2. pp. 1943-1958.
@article{ba6ae22c66ce4e6098b376d1f81086ad,
title = "Forest cover classification by optimal segmentation of high resolution satellite imagery",
abstract = "This study investigated whether high-resolution satellite imagery is suitable for preparing a detailed digital forest cover map that discriminates forest cover at the tree species level. First, we tried to find an optimal process for segmenting the high-resolution images using a region-growing method with the scale, color and shape factors in Definiens{\circledR} Professional 5.0. The image was classified by a traditional, pixel-based, maximum likelihood classification approach using the spectral information of the pixels. The pixels in each segment were reclassified using a segment-based classification (SBC) with a majority rule. Segmentation with strongly weighted color was less sensitive to the scale parameter and led to optimal forest cover segmentation and classification. The pixel-based classification (PBC) suffered from the {"}salt-and-pepper effect{"} and performed poorly in the classification of forest cover types, whereas the SBC helped to attenuate the effect and notably improved the classification accuracy. As a whole, SBC proved to be more suitable for classifying and delineating forest cover using high-resolution satellite images.",
keywords = "Digital forest cover map, High resolution, Pixel-based classification, Satellite image, Segment-based classification",
author = "Kim, {So Ra} and Woo-Kyun Lee and Kwak, {Doo Ahn} and Biging, {Greg S.} and Peng Gong and Lee, {Jun Hak} and Cho, {Hyun Kook}",
year = "2011",
month = "2",
day = "1",
doi = "10.3390/s110201943",
language = "English",
volume = "11",
pages = "1943--1958",
journal = "Sensors (Switzerland)",
issn = "1424-8220",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "2",

}

TY - JOUR

T1 - Forest cover classification by optimal segmentation of high resolution satellite imagery

AU - Kim, So Ra

AU - Lee, Woo-Kyun

AU - Kwak, Doo Ahn

AU - Biging, Greg S.

AU - Gong, Peng

AU - Lee, Jun Hak

AU - Cho, Hyun Kook

PY - 2011/2/1

Y1 - 2011/2/1

N2 - This study investigated whether high-resolution satellite imagery is suitable for preparing a detailed digital forest cover map that discriminates forest cover at the tree species level. First, we tried to find an optimal process for segmenting the high-resolution images using a region-growing method with the scale, color and shape factors in Definiens® Professional 5.0. The image was classified by a traditional, pixel-based, maximum likelihood classification approach using the spectral information of the pixels. The pixels in each segment were reclassified using a segment-based classification (SBC) with a majority rule. Segmentation with strongly weighted color was less sensitive to the scale parameter and led to optimal forest cover segmentation and classification. The pixel-based classification (PBC) suffered from the "salt-and-pepper effect" and performed poorly in the classification of forest cover types, whereas the SBC helped to attenuate the effect and notably improved the classification accuracy. As a whole, SBC proved to be more suitable for classifying and delineating forest cover using high-resolution satellite images.

AB - This study investigated whether high-resolution satellite imagery is suitable for preparing a detailed digital forest cover map that discriminates forest cover at the tree species level. First, we tried to find an optimal process for segmenting the high-resolution images using a region-growing method with the scale, color and shape factors in Definiens® Professional 5.0. The image was classified by a traditional, pixel-based, maximum likelihood classification approach using the spectral information of the pixels. The pixels in each segment were reclassified using a segment-based classification (SBC) with a majority rule. Segmentation with strongly weighted color was less sensitive to the scale parameter and led to optimal forest cover segmentation and classification. The pixel-based classification (PBC) suffered from the "salt-and-pepper effect" and performed poorly in the classification of forest cover types, whereas the SBC helped to attenuate the effect and notably improved the classification accuracy. As a whole, SBC proved to be more suitable for classifying and delineating forest cover using high-resolution satellite images.

KW - Digital forest cover map

KW - High resolution

KW - Pixel-based classification

KW - Satellite image

KW - Segment-based classification

UR - http://www.scopus.com/inward/record.url?scp=79952074186&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952074186&partnerID=8YFLogxK

U2 - 10.3390/s110201943

DO - 10.3390/s110201943

M3 - Article

C2 - 22319391

AN - SCOPUS:79952074186

VL - 11

SP - 1943

EP - 1958

JO - Sensors (Switzerland)

JF - Sensors (Switzerland)

SN - 1424-8220

IS - 2

ER -