Panchromatic wavelet texture features fused with
multispectral bands for improved classification of
high-resolution satellite imagery
Arko Lucieer
Centre for Spatial Information Science (CenSIS)
School of Geography and Environmental Studies
University of Tasmania
Hobart, Tasmania, Australia
Email: Arko.Lucieer@utas.edu.au
Harald van der Werff
Earth Systems Analysis
International Institute for Geo-Information Science
and Earth Observation (ITC)
Enschede, The Netherlands
Email: vdwerff@itc.nl
I. INTRODUCTION
The availability of high-resolution satellite imagery
has rapidly increased over the last six years since the
introduction of commercial satellite imagery such as
Quickbird, IKONOS, and OrbView. A unique charac-
teristic of these sensors is that they combine a very
high-resolution (< 1 m) panchromatic band with four
(lower resolution) multispectral bands. Many studies
have focused on combining these five bands of different
spatial resolutions to obtain a multispectral image at the
spatial resolution of the panchromatic band. This process
is often referred to as pansharpening [1].
The emphasis of image processing techniques for
these high-resolution images has shifted from traditional
pixel-based techniques to contextual and object-oriented
approaches as the size of the object of interest is often
larger than one pixel. Many studies have explored the
use of texture measures for improving classification or
segmentation results by including the spatial domain [2],
[3], [4], [5].
This study presents a novel approach in combining
textural information from the panchromatic band with
spectral information from the multispectral bands for
improved image classification. Firstly, we develop a
texture measure based on wavelet coefficients of the
panchromatic band that can be aggregated to the reso-
lution of the multispectral bands. Secondly, we combine
the texture measures with the spectral information in the
multispectral bands in a fuzzy classification framework.
Thirdly, we illustrate our approach with a case study
of vegetation and land cover classification based on a
Quickbird image of subantarctic Macquarie Island.
II. METHODS
In our methodology, we work with a Quickbird image
that contains four multispectral bands (B, G, R, NIR) at
2.4 m resolution and one panchromatic band at 0.6 m
resolution. This means that each multispectral pixel
contains 16 panchromatic pixels (4 by 4). We assume
that the panchromatic band contains most information
about the spatial characteristics or structural pattern of
the land cover classes. The multispectral pixels on the
other hand are only used for their spectral content.
It should be stressed that the approach described here
can be applied to other imagery that combine a high-
resolution panchromatic band with multispectral bands.
In order to generate a measure describing the texture
of the local neighbourhood of a multispectral image
pixel, we define a neighbourhood of 16 by 16 panchro-
matic pixels centred around a multispectral pixel (black
pixels in Fig. 1). A wavelet decomposition based on the
Daubechies wavelet is then applied to this panchromatic
image block. We assume that characteristic patterns at
this image scale are depicted by high frequency changes
in pixel values. We therefore only use the small-scale
wavelet coefficients to quantify texture. The structure of
the wavelet coefficient matrix is effectively a measure
for texture.
To illustrate the effectiveness of the texture measure,
five small images of 16 by 16 pixels were generated
with an increasing random noise. The mean grey level
is 127 and the random noise levels are 0%, 2%, 5%,
15%, and 40% for the five image respectively (Fig. 2(a)).
The histograms in Fig. 2(b) show the distribution of the
high-frequency wavelet coefficients. The more noise in