Unit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Image classification and land cover mapping
1. Introduction to Land Cover
Mapping Techniques using
Satellite Images
Kabir Uddin
GIS and Remote Sensing Analyst
International Centre for Integrated Mountain Development
Mountain Environment & Natural Resources’ Information System (MENRIS)
Kathmandu, Nepal
www.icimod.org
Email: kuddin@icimod.org kabir.Uddin.bd@gmail.com
2. Land Cover mapping
• Land cover is the physical material at the surface of
the earth. Land covers include grass, asphalt, trees,
bare ground, water, etc.
• The objective of any classification scheme is to
simplify the real world in order to facilitate
communication and decision making.
• Satellite Remote sensed data and GIS for land cover,
its changes is a key to many diverse applications such
as Environment, Forestry, Hydrology, Agriculture and
Geology. Natural Resource Management, Planning and
Monitoring programs depend on accurate information
about the land cover in a region.
3. Land cover mapping
• There are two primary methods for capturing information on land
cover: field survey and analysis of remotely sensed imagery.
4. Use of land cover mapping
• Local and regional planning
• Disaster management
• Vulnerability and risk Assessments
• Ecological management
• Monitoring the effects of climate change
• Wildlife management.
• Alternative landscape futures and conservation
• Environmental forecasting
• Environmental impact assessment
• Policy development
5. Application of land cover mapping
• Local and regional planning
• Disaster management
• Vulnerability and Risk Assessments
• Ecological management
• Monitoring the effects of climate change
• Wildlife management.
• Alternative landscape futures and conservation
• Environmental forecasting
• Environmental impact assessment
• Policy development
6. Application of land cover mapping
• Local and regional planning
• Disaster management
• Vulnerability and Risk Assessments
• Ecological management
• Monitoring the effects of climate change
• Wildlife management.
• Alternative landscape futures and conservation
• Environmental forecasting
• Environmental impact assessment
• Policy development
7. Application of land cover mapping
• Local and regional planning
• Disaster management
• Vulnerability and Risk Assessments
• Ecological management
• Monitoring the effects of climate change
• Wildlife management.
• Alternative landscape futures and conservation
• Environmental forecasting
• Environmental impact assessment
• Policy development
8. Application of land cover mapping
• Local and regional planning
• Disaster management
• Vulnerability and Risk Assessments
• Ecological management
• Monitoring the effects of climate change
• Wildlife management.
• Alternative landscape futures and conservation
• Environmental forecasting
• Environmental impact assessment
• Policy development
9. Application of land cover mapping
• Local and regional planning
• Disaster management
• Vulnerability and Risk Assessments
• Ecological management
• Monitoring the effects of climate change
• Wildlife management.
• Alternative landscape futures and conservation
• Environmental forecasting
• Environmental impact assessment
• Policy development
10. Application of land cover mapping
• Local and regional planning
• Disaster management
• Vulnerability and Risk Assessments
• Ecological management
• Monitoring the effects of climate change
• Wildlife management.
• Alternative landscape futures and conservation
• Environmental forecasting
• Environmental impact assessment
• Policy development
11. Application of land cover mapping
• Local and regional planning
• Disaster management
• Vulnerability and Risk Assessments
• Ecological management
• Monitoring the effects of climate change
• Wildlife management.
• Alternative landscape futures and conservation
• Environmental forecasting
• Environmental impact assessment
• Policy development
12. Application of land cover mapping
• Local and regional planning
• Disaster management
• Vulnerability and Risk Assessments
• Ecological management
• Monitoring the effects of climate change
• Wildlife management.
• Alternative landscape futures and conservation
• Environmental forecasting
• Environmental impact assessment
• Policy development
14. Presentation status of land
cover in the HKH region
• No up to date land cover data is available
• Legends used are different due to
differences in objectives
• Not possible for comparisons from one
place to another or one year to another
year
• Harmonization of legends an important
aspect for developing land cover database
15. Steps of land cover mapping
Legend development and classification scheme
Data acquisition
Image rectification and enhancement
Field training information
Image segmentation
Generate image index
Assign rules
Draft land cover map
Validation and refining of land cover
Land cover map
Change assessment
17. Data acquisition
Sl No Launch Satellite/ Band/Resolution Scale Quicklook
Sensor
1 Jun 2014 WorldView-2 Very high-resolution with 8 Band (Pan and Multi)* 5000
- Panchromatic 31 cm
- Multispectral 1.24 m
- Short-wave infrared 3.7 m
2 Oct 2009 WorldView-2 Very high-resolution with 8 Band (Pan and Multi)* 5000
-Panchromatic 46 cm
-Multispectral 1.85 m (red, blue, green, near-IR, red
edge, coastal, yellow, near-IR2)
3 Oct 2001 Quickbird High-resolution with 5 Band (Pan and Multi)* 10000
- Panchromatic 61 cm
-Multispectral 2.44 m
4 Sep 2009 Cartosat-2 High-resolution 10000
-Panchromatic 1 m
18. Data acquisition
5 Jan 2006 ALOS High-resolution 50000
-Panchromatic 2.5m
-Multispectral 10m
6 Oct 2003 IRS LISS IV MX High medium resolution 50000
-Multi (Green, Red and NIR) 5.8 m
7 Apr 2009 Landsat7 ETM+ Medium-resolution with 8 Band (Pan and Multi)* 100000
-Panchromatic 150m
-Multispectral 30m (TR 60m)
8 Apr 2009 Landsat5 TM Medium-resolution with 7 Band 100000
-Multispectral 30m (TR 120m)
19. Data acquisition
185 Km
Landsat image
Spatial resolution 15m, 30 m
Swath 185 Km
20. Data acquisition
185 Km
Landsat image
Spatial resolution 15m, 30 m
Swath 185 Km
60 Km
ASTER and SPOT image
Swath 60 Km
21. Data acquisition
185 Km
Landsat image
Spatial resolution 15m, 30 m
Swath 185 Km
60 Km
ASTER and SPOT image
Swath 60 Km
16 Km
QuickBird, Swath 16 Km
22. Data acquisition
185 Km
Landsat image
Spatial resolution 15m, 30 m
Swath 185 Km
60 Km
ASTER and SPOT image
Swath 60 Km
16 Km
QuickBird, Swath 16 Km
IKONOS, Swath 10 Km
23. Field samples collection
Sig Id: 517
Grassland
X-Coord Y-Coord
86.95601 26.52447
Permanent fresh water lakes
Grass land-Imperata type
24. Sig Id: 112
X-Coord Y-Coord
86.94518 26.64141
Grass land -Imperata type
29. Image analysis for land cover mapping
• The process of sorting pixels into a number of data categories
based on their data file values
• The process of reducing images to information classes
30. Image analysis assumptions
• Similar features will have similar spectral
responses.
• The spectral response of a feature is unique
with respect to all other features of interest.
• If we quantify the spectral response of a
known feature, we can use this information to
find all occurrences of that feature.
31. Classification
There are different types of classification
procedures:
● Unsupervised
● Supervised
● Knowledgebase
● Object base
● Others
32. Unsupervised classification
– The process of automatically segmenting an image
into spectral classes based on natural groupings found
in the data
– The process of identifying land cover classes and
naming them
ISODATA Class Names Label
Class 1 Bare
Class 2 Agriculture
Class 3 Forest
Class 4 Grass
Class 5 Water
33. Supervised classification
– the process of using samples of known identity (i.e., pixels already
assigned to information classes) to classify pixels of unknown
identity (i.e., all the other pixels in the image)
34. Object Based Classification (OBIA)
• Object-Based Image Analysis also called Geographic
Object-Based Image Analysis (GEOBIA) and it is a sub-
discipline of geoinformation science. Object – based
image analysis a technique used to analyze digital
imagery. OBIA developed relatively recently compared
to traditional pixel-based image analysis.
• Pixel-based image analysis is based on the information
in each pixel, object based image analysis is based on
information from a set of similar pixels called objects or
image objects.
35. Elements of object recognition
• Visual/Digital
– Shape
– Size
– Tone / colour
– Texture
– Shadow
– Site
– Association
– Pattern
36. eCognition/Definiens
• eCognition/Definiens software employs a flexible
approach to image analysis, solution creation and
adaption
• Definiens Cognition Network Technology® has
been developed by Nobel Laureate, Prof. Dr. Gerd
Binnig and his team
• In 2000, Definiens (eCognition) came in market
• In 2003 Definiens Developer along with Definiens
eCognition™ Server was introduced. Now,
Definiens Developer 8 with updated versions is
available
37. Steps for object base classification
Image Segmentations
Variable Operations
Rule Set
Rule Set
Land Cover Map
38. Segmentation
• The first step of an eCognition image analysis is to cut the image
into pieces, which serve as building blocks for further analysis – this
step is called segmentation and there is a choice of several
algorithms to do this.
• The next step is to label these objects according to their attributes,
such as shape, color and relative position to other objects.
40. Types of Segmentation
Chessboard segmentation
Chessboard segmentation is the
simplest segmentation available as it just
splits the image into square objects with
a size predefined by the user.
41. Types of Segmentation
Quadtree based segmentation
Quadtree-based segmentation is similar to
chessboard segmentation, but creates
squares of differing sizes.
Quadtree-based segmentation, very
homogeneous regions typically produce
larger squares than heterogeneous
regions. Compared to multiresolution
segmentation,quadtree-based
segmentation is less heavy on resources.
42. Types of Segmentation
Contrast split segmentation
Contrast split segmentation is similar to the
multi-threshold segmentation approach.
The
contrast split segments the scene into dark
and bright image objects based on a
threshold
value that maximizes the contrast between
them.
43. Types of Segmentation
Contrast split segmentation
Contrast split segmentation is similar to the
multi-threshold segmentation approach.
The contrast split segments the scene into
dark and bright image objects based on a
threshold value that maximizes the contrast
between them.
44. Types of Segmentation
Spectral difference segmentation
Spectral difference segmentation lets you
merge neighboring image objects if the
difference between their layer mean
intensities is below the value given by the
maximum spectral difference. It is designed
to refine existing segmentation results, by
merging spectrally similar image objects
produced by previous segmentations and
therefore is a bottom-up segmentation.
45. Types of Segmentation
Multiresolution segmentation
Multiresolution Segmentation groups areas
of similar pixel values into objects.
Consequently homogeneous areas result
in larger objects, heterogeneous areas in
smaller ones.
The Multiresolution Segmentation
algorithm1 consecutively merges pixels or
existing image objects. Essentially, the
procedure identifies single image objects of
one pixel in size and merges them with
their neighbors, based on relative
homogeneity criteria.
46. Multiresolution Segmentation,
Parameters
Scale
•The value of the scale parameter affects image
segmentation by determining the size of image
objects;
•Defines the minimum size of the object through
threshold value;
•The larger the scale parameter, the more objects
can be fused and the larger the objects grow;
47. Generating arithmetic Feature
The Normalized Difference Vegetation Index (NDVI) is a standardized index
allowing to generate an image displaying greenness (relative biomass)
Index values can range from -1.0 to 1.0, but vegetation values typically range
between 0.1 and 0.7.
NDVI is related to vegetation is that
healthy vegetation reflects very well in
the near infrared part of the spectrum.
It can be seen from its
mathematical definition that the NDVI
of an area containing a dense
vegetation canopy will tend to positive
values (say 0.3 to 0.8) while clouds
and snow fields will be characterized
by negative values of this index.
NDVI = (NIR - red) / (NIR + red)
48. Land and Water Masks (LWM)
Index values can range from 0 to 255, but water
values typically range between 0 to 50
Water Mask = infra-red) / (green + .0001) * 100
(ETM+) Water Mask = Band 5) / (Band 2 + .0001) *
100
63. Software for Object Based
Classification
• eCognition/Definiens
• IDRISI
• ERDAS Imagine
• ENVI
• SPRING
• MADCAT
64. Accuracy Assessment
Goals:
– Assess how well a classification worked
– Understand how to interpret the usefulness of
someone else’s classification
• Some possible sources
– Aerial photo interpretation
– Ground truth with GPS
– GIS layers
– Google earth image
65. Sampling Methods
Simple Random Sampling :
observations are randomly placed.
Stratified Random Sampling : a
minimum number of observations
are randomly placed in each
category.
66. Sampling Methods
Systematic Sampling : observations
are placed at equal intervals
according to a strategy.
Systematic Non-Aligned Sampling :
a grid provides even distribution of
randomly placed observations.
67. Sampling Methods
Cluster Sampling : Randomly
placed “centroids” used as a base
of several nearby observations.
The nearby observations can be
randomly selected, systematically
selected, etc...
68. Accuracy Equations
Number of samples correctly classified in a given class
Pr oducer ' s accuracy = X 100
Total number of samples chosen for that class
Number of samples correctly classified in a given
class from the selected samples in that group
User ' s accuracy = X 100
Total number of samples classified in that
group out of entire samples selected
Total Number of reference samples chosen
Overall accuracy = X 100
Total number of correctly classified samples
69. Accuracy Assessment: Compare
• Example:
Reference Plot Class determined from Class claimed on Agreement?
ID Number reference source classified map
1 Conifer Conifer Yes
2 Hardwood Conifer No
3 Water Water Yes
4 Hardwood Hardwood Yes
5 Grass Hardwood No
72. Overall (Total) Accuracy
• Total accuracy
– Total Accuracy: Number of correct plots / total number of plots
Class types determined from
reference source 50 + 13 + 8
Accuracy
Total
=
100
*100 = 71%
# Conifer Hardwood Water Totals
Class types Plots
determined Conifer 50 5 2 57
Diagonals represent
from sites classified
classified Hardwo 14
od
13 0 27 correctly according to
map reference data
Water 3 5 8 16
Total 67 23 10 100 Off-diagonals were
s mis-classified
Total Number of reference samples chosen
Overall accuracy = X 100
Total number of correctly classified samples
73. Change detection
One common type of multitemporal analysis is
change detection
Change detection involves the direct comparison
of two or more images to identify how areas
change over time
2001 2003
As you know land cover change is a significant contributor to environmental change. Land cover data documents how much of a region is covered by forests, wetlands, impervious surfaces, agriculture, and other land and water types.