Transcript
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
Subject Geology
Paper No and Title Remote Sensing and GIS
Module No and Title Digital Image Fusion
Module Tag RS & GIS XI
Principal Investigator Co-Principal Investigator Co-Principal Investigator
Prof. Talat Ahmad
Vice-Chancellor
Jamia Millia Islamia
Delhi
Prof. Devesh K Sinha
Department of Geology
University of Delhi
Delhi
Prof. P. P. Chakraborty
Department of Geology
University of Delhi
Delhi
Paper Coordinator Content Writer Reviewer
Dr. Atiqur Rahman
Department of Geography,
Faculty of Natural Sciences,
Jamia Millia Islamia
Delhi
Dr. Iqbal Imam
Aligarh Muslim University
Aligarh
Dr. Atiqur Rahman
Department of Geography,
Faculty of Natural Sciences,
Jamia Millia Islamia
Delhi
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
Table of Content
1. Introduction
2. Concept of image fusion
2.1. At Pixel level
2.2. At Feature level
2.3. At Decision level
3. Objectives of image fusion
4. Image fusion techniques
4.1. Numerical Method
4.1.1. Multiplicative Algorithm
4.1.2. The Brovey transform image fusion technique
4.1.3. Fusion technique based on subtractive method
4.1.4. Wavelet image fusion technique
4.2. Colour related technique
4.2.1. The intensity-hue-saturation (IHS) image fusion technique
4.3. Statistical Method
4.3.1. Principal Component Analysis (PCA)
4.3.2. Fusion technique based on high-pass filter
4.4. Feature level technique
4.4.1. Ehlers method
5. Application of image fusion
5.1. Object identification
5.2. Classification
5.3. Change Detection
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
1. Introduction
In remote sensing, image fusion is the combination of two or more different images
to form a new image by using a certain algorithm to obtain more and better
information about an object or a study area.
Remote sensing image fusion is an effective way to use a large volume of data from
multisensor images. Most earth satellites such as SPOT, Landsat 7, IKONOS and
Quick Bird provide both panchromatic (PAN) images at a higher spatial resolution
and multispectral (MS) images at a lower spatial resolution and many remote sensing
applications require both high spatial and high spectral resolutions, especially for GIS
based applications. An effective image fusion technique can produce such remotely
sensed images. There are several benefits in using image fusion: wider spatial and
temporal coverage, decreased uncertainty, improved reliability, and increased
robustness of system performance.
The objective of information fusion is to improve the accuracy of image interpretation
and analysis by making use of complementary information. Many image fusion
techniques have been developed to merge a Pan image and a MS image into a
multispectral image with high spatial and spectral resolution simultaneously. An ideal
image fusion technique should have three essential factors, i.e. high computational
efficiency, preserving high spatial resolution and reducing colour distortion.
The image fusion is performed at three different processing levels, which are pixel
level, feature level and decision level according to the stage at which the fusion takes
place. In the past few years, many image fusion methods have been proposed, such as
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
intensity hue saturation- (IHS), Brovey transform (BT), principal component analysis
(PCA) and wavelets.
2. Concept of image fusion
Data fusion is a process dealing with data and information from multiple sources to
achieve refined /improved information for decision-making. A general definition of
image fusion is given as ‘Image fusion is the combination of two or more different
images to form a new image by using a certain algorithm’. Image fusion is performed
at three different processing levels according to the stage at which the fusion takes place:
2.1. At Pixel level
Image fusion at pixel level means fusion at the lowest processing level
referring to the merging of measured physical parameters. It uses raster data
that is at least co-registered but most commonly geocoded. The geocoding
plays an essential role because miss-registration causes artificial colours or
features in multisensor data sets, which falsify the interpretation. Later on, it
includes the re-sampling of image data to a common pixel spacing and map
projection.
2.2. At Feature level
Fusion at feature level requires the extraction of objects recognised in the
various data sources, e.g. using segmentation procedures. Features correspond
to characteristics extracted from the initial images, which are depending on
their environment such as extent, shape and neighbourhood. These similar
objects from multiple sources are assigned to each other and then fused for
further assessment using statistical approaches or Artificial Neural Networks
(ANN).
2.3. At Decision level
Decision-or interpretation level fusion represents a method that uses value-
added data where the input images are processed individually for information
extraction. The obtained information is then combined applying decision rules
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
to reinforce common interpretation, resolve differences, and furnish a better
understanding of the observed objects.
3. Objectives of image fusion
Image fusion is a tool to combine multisource imagery using advanced image
processing techniques. It aims at the integration of disparate and complementary data
to enhance the information apparent in the images as well as to increase the reliability
of the interpretation. This leads to more accurate data and increased utility. It is also
stated that fused data provides for robust operational performance, i.e., increased
confidence, reduced ambiguity, improved reliability and improved classification.
Image fusion is applied to digital imagery in order to:
Image sharpening
Improve geometric corrections
Provide stereo-viewing capabilities for stereo-photogrammetry
Enhance certain features not visible in either of the single data alone
Complement data sets for improved classification
Detect changes using multi-temporal data
Substitute missing information in one image with signals from another sensor
image
Replace defective data.
4. Image Fusion Techniques
The standard methods of image fusion are based on Red-Green-Blue (RGB) to
Intensity-Hue-Saturation (IHS) transformation. The usual steps involved in satellite
image fusion are as follows:
Resize the low-resolution multispectral images to the same size as the
panchromatic image and co-register to coincide on a pixel-by-pixel basis
depending on the height variations in the area contained in the data.
Subsequently, the data can be fused using one of the fusion techniques
described herewith.
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
Transform the R, G and B bands of the multispectral image into IHS
components.
Modify the panchromatic image with respect to the multispectral image. This
is usually performed by histogram matching of the panchromatic image with
Intensity component of the multispectral images as reference.
Replace the intensity component by the panchromatic image and perform
inverse transformation to obtain a high-resolution multispectral image.
Following are some methods used for image fusion:
4.1. Numerical Method
4.1.1. Multiplicative Algorithm: In order to improve quality of spatial and
spectral information Multiplicative transformation is a simple
multiplication fusion method. Its fused image can reflect the mixed
message of low-resolution images and high-resolution images. The
fusion algorithm can be written as:
MLijk = (XSijk x PNij)1/2
Where,
MLijk is the fusion image pixel value,
XSijk is pixel value of multispectral image,
PNij is the pixel value of Panchromatic.
Multiplicative that is the simplest fusion technique. The Multiplicative
algorithm stretches the histogram of all the MS bands and decreases the
standard deviation values. This technique also helps in detection of small
targets like cars and trees, and facilitates the mapping of the buildings.
However, multiplicative fusion techniques cause changes in the colours
of the original images and make the photo-interpretation more difficult.
While using this technique for image fusion, colour of the vegetation
changes from green to blue when blue band is used in natural colour
combinations. Multiplicative algorithm improves the spatial resolution
of the input MS image. The resultant image is having darker tone than
the input MS image, which results in loss of shadow (Fig. 2).
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
Fig. 2 (a) Original PAN image, (b) Original MS image, (c) MLT-fused
image, (d) MB-fused image, (e) HPF-fused image, (f) SFIM-fused
image.
4.1.2. The Brovey transform image fusion technique: Brovey technique
(BT) was first introduced by Bob Brovey. It is also known as colour-
normalized fusion. It is a simple method to merge data from different
sensors, which can preserve the relative spectral contributions of each
pixel but replace its overall brightness with the high spatial resolution
image. The mathematical formulas of the Brovey transform can be
showed as a combination of the Panchromatic (PAN) and multispectral
(MS) images. Each MS image is multiplied by a ratio of the PAN image
and divided by the sum of the MS images. The fused R, G, and B images
are defined by the following equations:
Rnew = R / (R + G + B) ×PAN (1)
Gnew = G / (R + G + B) ×PAN (2)
Bnew = B / (R + G + B) ×PAN (3)
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
Many researchers used the BT to fuse a RGB image with a high-
resolution image. The BT image fusion is used to combine Landsat TM
and radar SAR (ERS-1) images. It also give improved image when Spot
image is fused with PAN image. The advantages of Brovey transform
image fusion technique is that; it is a simple and fast method to merge
the data from different sensors. It provide superior visual and high-
resolution multispectral image. It is very useful for visual interpretation.
The disadvantage of this technique is that it ignores the requirement of
high quality synthesis of spectral information. It produces spectral
distortion. Results from Brovey transformation are presented in Fig. 3.
Fig. 3: Brovey transformation
4.1.3. Fusion technique based on subtractive method: Subtractive
Resolution merge uses a subtractive algorithm to PAN for sharpening
multi-spectral (MS) images. Specifically, it was designed for
Quickbird, Ikonos and Formosat images that simultaneously acquire
data in PAN and MS, with all 4 MS bands present. A ratio between the
MS and PAN image pixels sizes of approximately 4:1 is considered. By
using this technique, fused images of highly preserved spatial and
spectral resolution are produced. The subtractive image fusion method
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
is a fast, user-friendly and radiometrically accurate technique for
merging PAN and MS data. This method uses a subtractive algorithm
to PAN sharpen MS images. The input consists of overlapping PAN
and MS images. The output is a MS image that retains the spectral
contents of the MS image while maintaining the spatial detail of the
PAN image. This algorithm was designed specifically to provide a
solution that was fast, yet produced quality results for the most common
types of merges. Specifically, it was designed for QuickBird, IKONOS
and FORMOSAT images that have simultaneous acquisition of the
PAN and MS images, with all four MS bands present, and a ratio
between the MS and PAN image pixels sizes of approximately 4:1. The
MS and PAN images to be fused with this approach should have
roughly a 4:1 pixel size ratio. In addition, PAN and MS images should
be from the same system (QuickBird, IKONOS, and so on) and should
be acquired simultaneously. The output-fused image has lighter tone
than the input MS image, which results in merging of shadow with dark
tone areas.
4.1.4. Wavelet image fusion technique: Invented in 1980, Wavelet theory is
related to multi-resolution analysis theory. It extracts spatial details
from a high-resolution PAN image and then adds them to the MS bands.
Due to its multi-resolution analysis (MRA) characteristic, in recent
year, Wavelet transform has been introduced in image fusion domain.
The MRA depends on the discrete wavelet. The wavelets are
characterized by using two functions, which are the scaling function
f(x), and the wavelet function or mother wavelet. Mother wavelet ψ(x)
undergoes translation and scaling operations to give self-similar
wavelet series. The traditional wavelet-based image fusion can be
performed by decomposing the two input images separately into
approximate coefficients and detailed coefficients then high detailed
coefficients of the multi-spectral image are replaced with those of the
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
PAN image. The new wavelet coefficients of the multi-spectral image
are transformed with the inverse wavelet transform to obtain the fusion
multi-spectral image. The wavelet image fusion technique can improve
the spatial resolution while preserve the spectral characteristics at a
maximum degree. However, the method discards low frequency
component of the PAN image completely and then by performing the
inverse PC transform. In the output-fused image, the colour seems not
being smoothly integrated into the spatial features. Details of small
objects are lost and the edges of buildings are also distorted in the output
image. The results of image fusion by wavelet transformation are
presented in Fig. 4.
Fig. 4 Wavelets based image fusion
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
4.2. Colour related technique
4.2.1. The intensity-hue-saturation (IHS) image fusion technique: The
intensity-hue-saturation (IHS) technique is a standard procedure in
image fusion, with the major limitation that only three bands are
involved. The IHS fusion technique is used for sharpening. This
technique works best in image analysis for colour enhancement, feature
enhancement, improvement of spatial resolution and the fusion of
disparate data sets. The IHS fusion technique converts a colour image
from the red, green, and blue (RGB) space into the IHS colour space.
The intensity band (I) in the IHS space is replaced by a high-resolution
PAN image and then transformed back into the original RGB space
together with the previous hue band (H) and the saturation band (S),
resulting in an IHS fused image.
Four steps used in IHS:
Transform the red, green, and blue (RGB) channels
(corresponding to three multispectral bands) to IHS
components.
Match the histogram of the panchromatic image with the
intensity component.
Replace the intensity component with the stretched
panchromatic image; and
Inverse transform IHS channels to RGB channels. The resultant
colour composite will then have a higher spatial resolution in
terms of topographic texture information.
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
The HSI components can be defined as follows:
I = (R+ G+ B)/3 (1)
H= (B-R)/3(I-R), S=1-R/I, when R= Minimum (R, G, B) (2)
H= (R-G)/3(I-G), S=1-G/I, when G= Minimum (R, G, B) (3)
H= (G-B)/3(I-B), S=1-B/I, when B= Minimum (R, G, B) (4)
Where, I, H, S stand for intensity, hue and saturation components
respectively; R, G, B mean Red, Green, and Blue bands of multi-
spectral image. The advantage with this technique is that it is a simple
method to merge the images attributes. It provides high spatial quality
and better visual effect. It gives the best result for fusion of remote
sensing images. Besides these, it does not require radiometric
corrections or radiometric enhancements. 2. It does not require the
assessment of training areas. 3. It produces a new data set in which the
burned areas are well discriminated. The disadvantage is that, it
produces a significant colour distortion with respect to the original
image. It suffers from artifacts and noise, which tends to higher contrast.
The major limitation is that only three bands are involved (Fig. 5).
Fig. 5 Intensity-hue-saturation image fusion technique
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
4.3. Statistical Method
4.3.1. Principal Component Analysis (PCA): Principal Component
Analysis (PCA) is mathematical method that transforms interrelated
variables into the unrelated variable. The verbosity of image can be
decreased or eliminated using this technique.
This is a spatial domain technique of image fusion, in which pixel values
are modified to achieve the final results. The advantage of PCA is that
the redundancy of data is decreased and large amounts of inputs are
decreased without the actual loss of the information at the output image.
The fusion is accomplished by weighted average of images to be fused.
Eigen vector related to the largest Eigen value of the covariance
matrices of each source are used to obtain weights for each source
image. It computes a compress and best description of the data set. The
first principal component is fixed along the direction with utmost
variance and the second principal component lie in the subspace
perpendicular to the first. The third principal component is taken along
the direction with utmost variance and in the subspace perpendicular to
the first two and so on.
The information flow diagram of PCA-based image fusion algorithm is
shown in Fig. 1. The input images (images to be fused) I1 (x, y) and I2
(x, y) are arranged in two column vectors and their empirical means are
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
subtracted. The resulting vector has a dimension of n x 2, where n is
length of the each image vector. Eigenvector and eigenvalues for this
resulting vector are computed and the eigenvectors corresponding to the
larger eigenvalue obtained. The normalized components P1 and P2 (i.e.,
P1 + P2 = 1) are computed from the obtained eigenvector.
4.3.2. Fusion technique based on high-pass filter: The high-pass filter
(HPF) image fusion technique allows us to combine high-resolution
PAN data with lower-resolution MS data, resulting in an output with
both excellent detail and a realistic representation of spectral contents
of the original MS scene.
The process involves a convolution using a HPF on the high-resolution
data and then combining this with the lower-resolution MS data. The
general steps of HPF algorithm are as follows:
Read pixel sizes from image files and calculate R, the ratio of
MS cell size to high-resolution cell size.
High pass filter the high spatial resolution image.
Resample the MS image to the pixel size of the high-pass image.
Add the HPF image to each MS band. The HPF image is
weighted relative to the global standard deviation of the MS
band.
Stretch the new MS image to match the mean and standard
deviation of the original (input) MS image.
The output-fused image has lighter tone than the input MS
image. In addition, the texture of the image is very smooth and
the sharpness is less, which results in less clarity of objects.
4.4. Feature level technique
4.4.1. Ehlers method: The Ehlers fusion algorithm was invented by Prof.
Manfred Ehlers. This fusion technique is based on an IHS transform
coupled with an adaptive Fourier domain filtering. This method is
extended to include more than three bands by using multiple IHS
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
transforms until the number of bands is exhausted. Using fast Fourier
transform (FFT) technique, the spatial components to be enhanced or
suppressed can be directly accessed. The panchromatic spectrum is
filtered with an inverse HPF and the intensity spectrum is filtered with
a low-pass filter. After filtering, both the images are transformed back
into the spatial domain with an inverse FFT and added together to form
a fused intensity component with the high-frequency information from
the high-resolution PAN image and the low-frequency information
from the low-resolution MS image. As the last step, an inverse IHS
transformation produces a fused RGB image. These steps can be
repeated with successive three-band selection until all bands are fused
with the PAN image. The Ehlers fusion shows the best spectral
preservation but also takes the highest computation time. The Ehlers
fusion technique improves the resolution of the fused image, but it
decreases the tonal variance in the resulting image. Some buildings are
found to be merged with other objects. The trees part is clearer in the
fused image.
5. Application of Image Fusion
Following are some application of image fusion:
5.1. Object identification
Image fusion technique increases the capability for enhancing features. The
feature enhancement capability of image fusion is visually apparent in
VIR/VIR combinations that often results in images that are superior to the
original data. In order to maximize the amount of information extracted from
satellite image data useful products can be found in fused images.
5.2. Classification
New image after fusion increases the classification accuracy. Classification is
one of the key tasks of remote sensing applications. The classification
accuracy of remote sensing images is improved when multiple source image
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
data are introduced to the processing. Images from microwave and optical
sensors offer complementary information that helps in discriminating the
different classes.
5.3. Change Detection
Change detection is the process of identifying differences in the state of an
object or phenomenon by observing it at different times. Image fusion plays
greater role in this by making the objects more clear. Change detection is the
process of identifying differences in the state of an object or phenomenon by
observing it at different times. Image fusion for change detection takes
advantage of the different configurations of the platforms carrying the sensors.
The combination of these temporal images in same place enhances
information on changes that might have occurred in the area observed.
Frequently Asked Questions-
Q1. What do you mean by image fusion in remote sensing?
Ans: In remote sensing, image fusion is the combination of two or more different
images to form a new image by using a certain algorithm to obtain more and
better information about an object or a study area. The objective of information
fusion is to improve the accuracy of image interpretation and analysis. Merging
of a PAN image with high spatial resolution and MS image with low spatial
resolution to get a multispectral image with high spatial and spectral resolution
simultaneously is a typical example of image fusion in remote sensing.
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
Q2. How image fusion is done? Discuss the standard method in brief?
Ans: The standard methods of image fusion are based on Red-Green-Blue (RGB) to
Intensity-Hue-Saturation (IHS) transformation. Following are the steps usually
taken in satellite image fusion:
Resize the low-resolution multispectral images to the same size as the
panchromatic image and co-register to coincide on a pixel-by-pixel basis
depending on the height variations in the area contained in the data.
Subsequently, the data can be fused using one of the fusion techniques
described herewith.
Transform the R, G and B bands of the multispectral image into IHS
components.
Modify the panchromatic image with respect to the multispectral image.
This is usually performed by histogram matching of the panchromatic image
with Intensity component of the multispectral images as reference.
Replace the intensity component by the panchromatic image and perform
inverse transformation to obtain a high-resolution multispectral image
Q3. What is the application of image fusion in remote sensing?
Ans: Following are the main application of image fusion in remote sensing:
Object identification: Image fusion enhances the features and these enhanced
features are visually apparent in VIR/VIR combinations and new fused images
are superior to the original data.
Classification: New image after fusion increases the classification accuracy. The
classification accuracy of remote sensing images is improved when multiple
source image data are introduced to the processing. Images from microwave and
optical sensors offer complementary information that helps in discriminating the
different classes.
Change Detection: Change detection is the process of identifying differences in
the state of an object or phenomenon by observing it at different times. Image
fusion plays greater role in this by making the objects more clear. Image fusion
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
for change detection takes advantage of the different configurations of the
platforms carrying the sensors. The combination of these temporal images in
same place enhances information on changes that might have occurred in the
area observed.
Q4. Discuss the Principal Component Analysis (PCA) technique used for image
fusion in remote sensing?
Ans: Principal Component Analysis (PCA) is mathematical method that transforms
interrelated variables into the unrelated variable. This is a spatial domain
technique of image fusion, in which pixel values are modified to achieve the
final results. The fusion is accomplished by weighted average of images to be
fused. Eigen vector related to the largest Eigen value of the covariance matrices
of each source are used to obtain weights for each source image. It computes a
compress and best description of the data set into; (i) First PCA, (ii) Second
PCA and (iii) Third PCA.
The figure shows the flow diagram of PCA-based image fusion algorithm. The
input images (images to be fused) I1 (x, y) and I2 (x, y) are arranged in two
column vectors and their empirical means are subtracted. The resulting vector
has a dimension of n x 2, where n is length of the each image vector. Eigenvector
and eigenvalues for this resulting vector are computed and the eigenvectors
corresponding to the larger eigenvalue obtained. The normalized components P1
and P2 (i.e., P1 + P2 = 1) are computed from the obtained eigenvector.
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
Q5. How image fusion is performed at the processing level of Pixel?
Ans: Images can be fused at Pixel level, Feature level and Decision level. Image
fusion at pixel level means fusion at the lowest processing level referring to the
merging of measured physical parameters. It uses raster data that is at least co-
registered but most commonly geocoded. The geocoding plays an essential role
because miss-registration causes artificial colours or features in multisensor data sets,
which falsify the interpretation. Later on, it includes the re-sampling of image data to
a common pixel spacing and map projection.
Multiple Choice Questions-
1. Images can be fused at the level of
(a) Pixel
(b) Feature
(c) Decision level
(d) All of the above
Ans: d
2. Which of the following statement is not true with respect to image fusion?
(a) Image fusion does not require registration of images.
(b) Transformation of R, G and B bands of the multispectral image into IHS
components.
(c) Replacement of the intensity component by the panchromatic image and
performing inverse transformation to obtain a high resolution
multispectral image.
(d) Fusion of data by using one of the fusion techniques.
Ans: a
3. In subtractive method of image Fusion, a ratio between the MS and PAN image
pixels sizes is considered to be approximately
(a) 4:1
(b) 5:1
(c) 1:4
(d) All of the above
Ans: a
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
4. Which of the following statement is not true with respect to IHS
(a) Transform the red, green, and blue (RGB) channels to IHS components.
(b) No need to match the histogram of the panchromatic image with the
intensity component.
(c) Replace the intensity component with the stretched panchromatic image
(d) Inverse transform IHS channels to RGB channels
Ans: b
5. In the following technique Fourier domain filtering is needed while doing the
image fusion?
(a) The intensity-hue-saturation (IHS) image fusion technique
(b) Principal Component Analysis (PCA)
(c) Ehlers method
(d) Wavelet image fusion technique
Ans: c
Suggested Readings:
1. Dahiya, S., Garg, P. K., & Jat, M. K. (2013). A comparative study of various
pixel-based image fusion techniques as applied to an urban
environment. International Journal of Image and Data Fusion, 4(3), 197-213.
2. Sahu, D. K., & Parsai, M. P. (2012). Different image fusion techniques–a
critical review. International Journal of Modern Engineering Research
(IJMER), 2(5), 4298-4301.
3. Helmy, A. K., Nasr, A. H., & El-Taweel, G. S. (2010). Assessment and
evaluation of different data fusion techniques. International Journal of
Computers, 4(4), 107-115.
4. Kaur, A., & Khullar, S. (2013). Image Fusion using HIS, PCA and Wavelet
Technique. International Journal of Computer Science and Communication
Engineering, 2(2).
GEOLOGY
Paper: Remote Sensing and GIS
Module: Digital Image Fusion
5. Lemeshewsky, G. P. (2002, July). Multispectral image sharpening using a
shift-invariant wavelet transform and adaptive processing of multiresolution
edges. In Aero Sense 2002 (pp. 189-200). International Society for Optics and
Photonics.
6. Prasad, N., Saran, S., Kushwaha, S. P. S., & Roy, P. S. (2001). Evaluation of
various image fusion techniques and imaging scales for forest features
interpretation. Current Science, 1218-1224.
7. Zhang, Y. (2004). Understanding image fusion. Photogrammetric engineering
and remote sensing, 70(6), 657-661.
top related