An evaluation of four different wavelet decomposition procedures for spatial feature discrimination in urban areas

Soe Myint, John Tyler, Nina Lam

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

Texture or spatial arrangement of neighborhood objects and features plays an important role in the human visual system for pattern recognition and image classification. The traditional spectral-based image processing techniques have proven inadequate for urban land use and land cover mapping from images acquired by the current generation of fine-resolution satellites. This is because of the high frequency spatial arrangements or complex nature of urban features. There is a need for an effective algorithm to digitally classify urban land use and land cover categories using high-resolution image data. Recent studies using wavelet transforms for texture analysis have generally reported better accuracy. Based on a high-resolution ATLAS image, this study illustrates four different wavelet decomposition procedures - the standard, horizontal, vertical, and diagonal decompositions - for urban land use and land cover feature extraction with the use of 33 × 33 pixel samples. The standard decomposition approach was found to be the most efficient approach in urban texture analysis and classification. For comparison purposes and to better evaluate the accuracy of wavelet approaches in image classification, spatial autocorrelation techniques (Moran's I and Geary's C) and the spatial co-occurrence matrix method were also examined. The results suggest that the wavelet transform approach is superior to all other approaches.

Original languageEnglish (US)
Pages (from-to)403-429
Number of pages27
JournalTransactions in GIS
Volume6
Issue number4
StatePublished - Oct 2002
Externally publishedYes

Fingerprint

wavelet
urban area
discrimination
land use
decomposition
evaluation
land cover
texture
image resolution
image classification
pattern recognition
transform
image processing
autocorrelation
pixel
matrix
analysis

ASJC Scopus subject areas

  • Geography, Planning and Development

Cite this

An evaluation of four different wavelet decomposition procedures for spatial feature discrimination in urban areas. / Myint, Soe; Tyler, John; Lam, Nina.

In: Transactions in GIS, Vol. 6, No. 4, 10.2002, p. 403-429.

Research output: Contribution to journalArticle

@article{80e7dadff08f49b2964ef746dd11d130,
title = "An evaluation of four different wavelet decomposition procedures for spatial feature discrimination in urban areas",
abstract = "Texture or spatial arrangement of neighborhood objects and features plays an important role in the human visual system for pattern recognition and image classification. The traditional spectral-based image processing techniques have proven inadequate for urban land use and land cover mapping from images acquired by the current generation of fine-resolution satellites. This is because of the high frequency spatial arrangements or complex nature of urban features. There is a need for an effective algorithm to digitally classify urban land use and land cover categories using high-resolution image data. Recent studies using wavelet transforms for texture analysis have generally reported better accuracy. Based on a high-resolution ATLAS image, this study illustrates four different wavelet decomposition procedures - the standard, horizontal, vertical, and diagonal decompositions - for urban land use and land cover feature extraction with the use of 33 × 33 pixel samples. The standard decomposition approach was found to be the most efficient approach in urban texture analysis and classification. For comparison purposes and to better evaluate the accuracy of wavelet approaches in image classification, spatial autocorrelation techniques (Moran's I and Geary's C) and the spatial co-occurrence matrix method were also examined. The results suggest that the wavelet transform approach is superior to all other approaches.",
author = "Soe Myint and John Tyler and Nina Lam",
year = "2002",
month = "10",
language = "English (US)",
volume = "6",
pages = "403--429",
journal = "Transactions in GIS",
issn = "1361-1682",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - An evaluation of four different wavelet decomposition procedures for spatial feature discrimination in urban areas

AU - Myint, Soe

AU - Tyler, John

AU - Lam, Nina

PY - 2002/10

Y1 - 2002/10

N2 - Texture or spatial arrangement of neighborhood objects and features plays an important role in the human visual system for pattern recognition and image classification. The traditional spectral-based image processing techniques have proven inadequate for urban land use and land cover mapping from images acquired by the current generation of fine-resolution satellites. This is because of the high frequency spatial arrangements or complex nature of urban features. There is a need for an effective algorithm to digitally classify urban land use and land cover categories using high-resolution image data. Recent studies using wavelet transforms for texture analysis have generally reported better accuracy. Based on a high-resolution ATLAS image, this study illustrates four different wavelet decomposition procedures - the standard, horizontal, vertical, and diagonal decompositions - for urban land use and land cover feature extraction with the use of 33 × 33 pixel samples. The standard decomposition approach was found to be the most efficient approach in urban texture analysis and classification. For comparison purposes and to better evaluate the accuracy of wavelet approaches in image classification, spatial autocorrelation techniques (Moran's I and Geary's C) and the spatial co-occurrence matrix method were also examined. The results suggest that the wavelet transform approach is superior to all other approaches.

AB - Texture or spatial arrangement of neighborhood objects and features plays an important role in the human visual system for pattern recognition and image classification. The traditional spectral-based image processing techniques have proven inadequate for urban land use and land cover mapping from images acquired by the current generation of fine-resolution satellites. This is because of the high frequency spatial arrangements or complex nature of urban features. There is a need for an effective algorithm to digitally classify urban land use and land cover categories using high-resolution image data. Recent studies using wavelet transforms for texture analysis have generally reported better accuracy. Based on a high-resolution ATLAS image, this study illustrates four different wavelet decomposition procedures - the standard, horizontal, vertical, and diagonal decompositions - for urban land use and land cover feature extraction with the use of 33 × 33 pixel samples. The standard decomposition approach was found to be the most efficient approach in urban texture analysis and classification. For comparison purposes and to better evaluate the accuracy of wavelet approaches in image classification, spatial autocorrelation techniques (Moran's I and Geary's C) and the spatial co-occurrence matrix method were also examined. The results suggest that the wavelet transform approach is superior to all other approaches.

UR - http://www.scopus.com/inward/record.url?scp=0036812095&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036812095&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0036812095

VL - 6

SP - 403

EP - 429

JO - Transactions in GIS

JF - Transactions in GIS

SN - 1361-1682

IS - 4

ER -