Image information extraction techniques gazi

Image Information
Extraction Techniques
Md. Yousuf Gazi, Lecturer, Department of Geology, University of Dhaka (yousuf.geo@du.ac.bd)

Outlines:
• Introduction
• Visual Image interpretation
• Digital Image processing
- Image pre-processing
- Image enhancement and transformations

Introduction
• Interpretation and analysis of remote
sensing imagery involves the
identification and/or measurement of
various targets in an image in order to
extract useful information about them.
- Targets may be a point, line, or area
feature. This means that they can have
any form, from a bus in a parking lot or
plane on a runway, to a bridge or
roadway, to a large expanse of water or a
field.

• Much interpretation and identification of
targets in remote sensing imagery is
performed manually or visually, i.e. by a
human interpreter.
• When remote sensing data are available in
digital format, digital processing and
analysis may be performed using a
computer.

Visual Interpretation
• Recognizing targets is the key to
interpretation and information
extraction.
• Observing the differences between
targets and their backgrounds
involves comparing different
targets based on any, or all, of the
visual elements of tone, shape,
size, pattern, texture, shadow,
and association.

Tone
• Tone refers to the relative brightness or
color of objects in an image. Generally, tone
is the fundamental element for
distinguishing between different targets or
features.
• Variations in tone also allows the elements
of shape, texture, and pattern of objects to
be distinguished.

Shape
• Shape refers to the general form, structure, or
outline of individual objects.
• Shape can be a very distinctive clue for
interpretation.
• Straight edge shapes typically represent urban or
agricultural (field) targets, while natural features,
such as forest edges, are generally more irregular in
shape, except where man has created a road or clear
cuts.
• Farm or crop land irrigated by rotating sprinkler
systems would appear as circular shapes.

Size
• Size of objects in an image is a function of scale.
• It is important to assess the size of a target relative
to other objects in a scene, as well as the absolute
size, to aid in the interpretation of that target.
• A quick approximation of target size can direct
interpretation to an appropriate result more
quickly.

Pattern
• Pattern refers to the spatial arrangement
of visibly discernible objects.
• Typically an orderly repetition of similar
tones and textures will produce a distinctive
and ultimately recognizable pattern.
• Orchards with evenly spaced trees, and urban
streets with regularly spaced houses are good
examples of pattern.

Texture
• Texture refers to the arrangement and frequency of
tonal variation in particular areas of an image.
• Rough textures would consist of a mottled tone where
the grey levels change abruptly in a small area, whereas
smooth textures would have very little tonal variation.
• Smooth textures are most often the result of uniform,
even surfaces, such as fields, asphalt, or grasslands.
• A target with a rough surface and irregular structure,
such as a forest canopy, results in a rough textured
appearance.
•
• Texture is one of the most important elements for
distinguishing features in radar imagery.

Shadow
• Shadow is also helpful in interpretation as it may
provide an idea of the profile and relative height of
a target or targets which may make identification
easier.
• However, shadows can also reduce or eliminate
interpretation in their area of influence, since targets
within shadows are much less (or not at all) discernible
from their surroundings.
• Shadow is also useful for enhancing or identifying
topography and landforms, particularly in radar
imagery.

Association
• Association takes into account the relationship between other
recognizable objects or features in proximity to the target of
interest.
• The identification of features that one would expect to
associate with other features may provide information to
facilitate identification.
• In the example given above, commercial properties may be
associated with proximity to major transportation routes,
whereas residential areas would be associated with
schools, playgrounds, and sports fields.
• In our example, a lake is associated with boats, a marina,
and adjacent recreational land.

Digital Image processing
▪ Pre-processing
• Error correction
- Radiometric corrections
- Geometric corrections

Sources of Radiometric Distortion
▪ When image data is recorded by sensors on satellites and aircraft
it can contain errors in geometry and in the measured
brightness values of the pixels can result from the effect of the
atmosphere.
▪ Absorption by atmospheric molecules is a selective process that
converts incoming energy into heat. In particular, molecules of
oxygen, carbon dioxide, ozone and water attenuate the radiation
very strongly in certain wavebands.
▪ Scattering by atmospheric particles is then the dominant
mechanism that leads to radiometric distortion in image data.
▪ Transmittance. In the absence of atmosphere, transmittance is
100%. However because of scattering and absorption not all of
the available solar irradiance reaches the ground.
▪ Sky irradiance. Because the radiation is scattered on its travel
down through the atmosphere a particular pixel will be irradiated
both by energy on the direct path in Fig. and also by energy
scattered from atmospheric constituents. A pixel can also receive
some energy that has been reflected from surrounding pixels and
then, by atmospheric scattering, is again directed downwards.
▪ Path radiance. Again because of scattering alone, radiation can
reach the sensor from adjacent pixels and also via diffuse
scattering of the incoming radiation that is actually scattered
towards the sensor by the atmospheric constituents before it
reaches the ground.

Sources of Geometric Distortion
• There are potentially many more sources of geometric
distortion of image data than radiometric distortion and
their effects are more severe. They can be related to a
number of factors, including
(i) the rotation of the earth during image acquisition,
(ii) The relative motions of the platform, its scanners and
the earth
(iii) the wide field of view of some sensors,
(iv) the curvature of the earth,
(v) sensor non-idealities,
(vi) uncontrolled variations in the position and attitude
of the remote sensing platform
(vii) panoramic effects related to the imaging geometry.

Atmospheric Corrections
• Effects of Scattering (wavelength)
– Mie Scattering
– Rayleigh Scattering
• Effect of Haze
– Usually over large cities/Industrial Complexes
– Combination scattering and absorption
• Both sensor error and haze correcting programs are in-built
most IP software
• Special programs are built to correct atmospheric effect with
some user inputs

Radiometric Correction
• Relative Correction between image set using
one image as the reference
– Dark Pixel method
– PIFs (Pseudo Invariant Features)
• Absolute Correction converts DN values to
percent reflectance
– requires atmospheric corrections
– Sensor calibration
– Observation geometry

Panoramic Distortion
pθ = βh sec2θ = p sec2θ

Earth Curvature
Earth rotation effects

Geometric Correction
• These images have to corrected to produce accurate
Maps and GIS layers
• Corrections are done against reference Ground Control
Points collected from
– Existing Maps with known accuracy
– Existing Georeferenced images
– GPS/DGPS data
• Mathematical transformation is done to change the
image’s geometric co-ordinates to the reference co-
ordinates
Methods of Geometric correction:
1.Using satellite header file (satellite
onboard GPS)
2.Image to image registration
3.Image to map registration
4.Manually entered GCPs (Ground
Control Points)

Geometric Correction
• Also known as Georectification, Georeferencing, Co-
registration
• Images from the older sensors do not have any map
information. They are aligned along the satellite
orbit
• Images from recent sensors are delivered with some
workable geometric corrections

Sensor Errors
• Line Dropouts
– Values from Adjacent lines are used
• Pixel Dropouts
– Values from Adjacent pixels are used
• De-Striping
– Fourier and Inverse Fourier analysis

Image Enhancement
• The objective of the second group of image
processing functions grouped under the term of
image enhancement, is solely to improve the
appearance of the imagery to assist in visual
interpretation and analysis.
• Examples of enhancement functions include
contrast stretching to increase the tonal
distinction between various features in a scene,
and spatial filtering to enhance (or suppress)
specific spatial patterns in an image.

Image Enhancement
• Some are considered pre-processing and some
are hard to categorize
• Contrast, Color manipulations and Filtering are
definitely pre-processing
• Resolution Merging, Image Fusion, Band
Ratioing (indices), and Principal Component
Analysis (PCA) can also fall under information
Extraction

Contrast Manipulations
• Stretching a part of the Histogram to
enhance certain features. Various ways of
doing it
• Thresholding
• Level Slicing

• Linear Contrast Stretch: This involves identifying
lower and upper bounds from the histogram (usually
the minimum and maximum brightness values in the
image) and applying a transformation to stretch this
range to fill the full range.
• Equalized Contrast Stretch: This stretch assigns more
display values (range) to the frequently occurring
portions of the histogram. In this way, the detail in
these areas will be better enhanced relative to those
areas of the original histogram where values occur less
frequently.
• The linear contrast stretch enhances the contrast in the
image with light toned areas appearing lighter and dark
areas appearing darker, making visual interpretation
much easier. This example illustrates the increase in
contrast in an image before (left) and after (right) a
linear contrast stretch.
Before Linear Stretch After Linear Stretch

Convolution Filtering
• Low Pass- A low-pass filter is designed to emphasize
larger, homogeneous areas of similar tone and reduce
the smaller detail in an image. Thus, low-pass filters
generally serve to smooth the appearance of an
image.
• High Pass- do the opposite and serve to sharpen the
appearance of fine detail in an image,
• Directional Filters- Directional, or edge detection
filters are designed to highlight linear features, such
as roads or field boundaries.
• Edge enhance
• Edge detect

Resolution Merge & Image Fusion
• High resolution pan images merged with Low resolution
multispectrals
• Brovey method:
- Brovey, is also called the color normalization transform
because it involves a red-green-blue (RGB) color transform
method. The Brovey transformation was developed to avoid
the disadvantages of the multiplicative method.
- The formulae used for the Brovey transform can be described
as follows
- Red = (band1/Σ band n)∗ High Resolution Band
- Green = (band2/Σ band n)∗ High Resolution Band
- Blue = (band3/Σ band n)∗ High Resolution Band
- High resolution band = PAN band .
- Multiplicative method
- Principal Component method
- Optical images fused with Radar images

Principal Component Analysis
• Image data in different bands
are highly correlated and
therefore redundant
• PCA reduces these
Redundancy by reprojecting
the Data in different Axes
• New bands of data are
created
• Data is in the earlier bands,
noises later
• Can be subjected to further
analysis
Image Transformations
Original DN Values Transformed DNs and PC Axis
DNpc = a11DNA+a12 DNB

Band or Spectral Ratioing
• Compensates for brightness variation in scene
(shadowed vs. illuminated area)
• Very useful in vegetation studies specially in
differentiating stress
– Simple Ratio
– Vegetation Index
– Normalized Difference Vegetation Index

Vegetation Indices
• Simple Ratio – NIR/Red band
– High reflection from Chlorophyll in NIR
and absorption in Red allows
identification
– High values are healthy vegetation
• NDVI allows –
– Net production calculation
– Monitor Phenological patterns
– Length of Growing season
NDVI =
NIR − red
NIR + red

Other Ratios in ERDAS Imagine
• Mostly for Vegetation and Minerals
• Vegetation Index – NIR-Red
• Iron Oxide – Red/Blue
• Clay Minerals – Landsat Band 5/7
• Ferrous Minerals - Landsat Band 5/4
• For other sensors not supported by ERDAS write custom
models

Other Image Transformations
• Textural; Rough or smooth
– Segment and classify based on Texture
• Tasseled Cap
– Alters data structure axes to match viewing
axes for vegetation, soil and water
• RGB-IHS Transformation
– Transform color to Intensity, Hue & Saturation
• Decorrelation Stretch
– for highly correlated data saturation is
exaggerated along PC axes

Image information extraction techniques gazi

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to Image information extraction techniques gazi

Similar to Image information extraction techniques gazi (20)

More from Md. Yousuf Gazi

More from Md. Yousuf Gazi (18)

Recently uploaded

Recently uploaded (20)

Image information extraction techniques gazi