You are on page 1of 15

Pir Mehr Ali Shah

Arid Agriculture University, Rawalpindi


Office of the controller of Examinations
Mid Exam / Spring 2020 (Paper Duration 48 hours)
To be filled by Teacher

Course No.: RSG-404 Course Title: Advanced Remote Sensing Techniques


Total Marks: 12 Date of Exam: 22-06-2020
Degree: BS Geo-Informatics Semester: IV Section:………A……………………………
Marks
Q.No. 1 2 3 4 5 6 7 8 9 10 Obtained/
Total Marks
Marks
Obtaine
d
Total Marks in Words:
Name of the teacher:
Who taught the course:Signature of teacher / Examiner:

To be filled by Student

Registration No.: …18-ARID-3301 ……… Name:…Hamza Sadaqat…

Answer the following questions (Plagiarism will be checked, please avoid copying and
pasting).

Q.No.1. Download Landsat 8 and Sentinel 2 image of your hometown and subset it to the size of
10 by 10 km. Perform following tasks on it (you are supposed to take screenshot of your every
single step like a tutorial (if two students live in the same home, then one of them should change
study area by taking their grandparents’ home as study area in order to keep results different from
each other):
1) Annotate important places like your own house, hospital, school, playgrounds, croplands (for
villages)/parks/gardens (for cities).
2) Apply change detection on both satellite images from 2017 to 2020 and discuss what changes
happened there (quantitatively, means calculate change in area of places) and compare any
differences in Sentinel 2 and Landsat 8 results (if any). (Marks 04.)
Answer:
Annotate important places like your own house, hospital, school, playgrounds, croplands (for
villages)/parks/gardens (for cities).
Annotation map :
I have applied annotation of my home Tehsil villages.

Part II
2) Apply change detection on both satellite images from 2017 to 2020 and discuss what changes
happened there (quantitatively, means calculate change in area of places) and compare any
differences in Sentinel 2 and Landsat 8 results (if any).
Change Detection Results:
I have applied change detection.
Analysis on First Image 2010:
I classify image in 5 classes,
 Water
 Barren land
 Urban land
 Tree
 Agriculture greenry

Raster to Polygon for calculate the area:


Map of Land cover &Land Use Image 2010

Attribute Table :
Analysis on 2nd image:

I classify image in 5 classes,


 Water
 Barren land
 Urban land
 Tree
 Agriculture greenry

Raster to polygon for calculation of area:


Map of Land Cover & Land use 2020:

Attribute Table:


Q.No.2. a) Make a list of high resolution satellites and low resolution satellites who are in orbits
and provide following information in tabular form:

 Spatial resolution
 Spectral resolution,
 launching year
 Country who launched
 Area of research it can be used for.
Answer:

High Resolution Satellites


Name Launching Sensor Spectral Spectral Country Area of research it can be used for

name Resolutio Resolution who

year n launched
Cartosat-3 2019 MX 4 1.14 India Cartosat-3 is an advanced satellite, its
Cartosat-3 2019 PAN 1 0.28 India
imagery used in earth observation
Cartosat-2F 2018 HRMX 4 2.0 India
Cartosat-2F 2018 PAN 1 0.65 India purposes, surverys s, uban planning,
military and weather mapping.  

VividX2 2018 UHD 3 1.0 UK It is used for minning and


Camera commodities, land surveying and
mapping and precision agriculture.

WorldView-4 2017 MS 4 1.24 USA It is very high resolution satellite, een


WorldView-4 2017 PAN 1 0.31 USA
number plates of vehicles can be
detect, so it can be used in crime
analysis.
TeLEOS-1 2016 TeLEOS-1 1 1.0 Singapore It is used for mapping and surveying.
Imager
DMC-3 2015 VHRI-100 4 4.0 China It is used for master disaster
TripleSat MS monitoring.
DMC-3 2015 VHRI-100 1 1.0 China
TripleSat PAN
KOMPSAT-3A 2015 AEISS-A 4 2.2 Russia This is very high resolution satellite of
MS south korea. It is used for military
KOMPSAT-3A 2015 AEISS-A 1 0.55 Russia
purposes and land surverying and
PAN
used in GIS.

Deimos-2 2014 HiRAIS - 4 4.0 South It is used for disaster management


MS Korea and land mapping.
Deimos-2 2014 HiRAIS - 1 0.75 South
PAN Korea
Gaofen-2 2014 PMC-2 4 3.2 China It is constellation of 7 satellites, used
MS for GIS mapping, precesion agriculture
Gaofen-2 2014 PMC-2 1 0.8 China
and urban planning.
PAN
KazEOSat-1 2014 NAOMI 4 4.0 Kasakhstan Used for military purposes and GIS
(ms.) mapping.
SkySat-1 2014 MS 4 2.0 Russia It is used for spying and also capable
of video data.
Ikonos 1999 MS 4 4.0 USA Its data used for weather mapping and
Ikonos 1999 PAN 1 1.0 USA
urban mapping.
WorldView-3 2014 MS 8 1.24 USA It is very high resolution satellite, een
WorldView-3 2014 PAN 1 0..31 USA
number plates of vehicles can be
detect, so it can be used in crime
analysis
SPOT 6 2013 NAOMI 4 6.0 France It is very high resolution satellite used
MS for mapping of earth vegetation,
SPOT 6 2013 NAOMI 1 1.5 France
elevation and disaster management.
PAN
WorldView-2 2009 MS 8 1.84 USA It is very high resolution satellite, een
WorldView-2 2009 PAN 1 0.5 USA
number plates of vehicles can be
detect, so it can be used in crime
analysis
GeoEye-1 2008 MS 4 2.0 USA Its data used for ecologist to track the
GeoEye-1 2008 PAN 1 0.5 USA
animals. It is also used in google
maps.
QuickBird 2001 MS 4 2.4 USA Its data is used for environmental
QuickBird 2001 PAN 1 0.6 USA
analysis, land use, forest and
agricultural climates..
ALOS 2006 PRISM 1 2.5 JAPAN ALOS-1 used for stereo mapping.
OrbView-3 2003 MS 4 4.0 USA It is used in marine and ocean biology.
OrbView-3 2003 PAN 1 1.0 USA

Low Satellite resolution


Name Sensor Spectral Spatial Date Country Area of research it can be used

name Resolution Resolution of who for

(no. of bands) (m) lunch launched


Sentinel-3B OLCI 21 300.0 2018 Europe It is a earth observation satellite. Its
Sentinel-3 B SLSTR 9 500.0, 2018 Europe
data used for earth observation, land
1000.0
Sentinel-5 P Tropomi 7 3500.0, 2017 Europe mapping, urban mapping, time series
7000.0 analysis and GIS mapping..
Sentinel-3 A OLCI 21 300.0 2016 Europe
Sentinel-3 A SLSTR 9 500.0, 2016 Europe
1000.0
DSCOVR EPIC 10 25000.0 2015 USA
Landsat 8 TIRS 2 100.0 2013 USA It is earth observation satellite used
for earth observation. Its data used
for time series analysis, agriculture
mapping, forest mapping, urban
mapping etc.
NPP VIIRS 22 375.0, 750.0 2012 USA It is used in weather mapping
Envisat MERIS 15 300.0 2002 Europe Its data used for ocean, terrain and
atmosphere.
Meteosat GERB 7 40000.0 2002 French It is used for weather mapping.
MSG
Meteosat SEVIRI 12 1000.0, 2002 French
MSG 3000.0
SPOT 5 VEGETATIO 4 1000.0 2002 France Used for vegetation capturing, and
N2 elevation of earth.
TERRA MODIS 36 250.0, 2000 Japan Its data is used for terrain modeling..
500.0,
1000.0
SPOT 4 VEGETATIO 4 1000.0 1998 France Used for earth elevation model.
N1
IRS-1D WiFS 2 188.0 1997 India Used for military purposes.
OrbView-2 SeaWiFS 8 1130.0 1997 USA It is used for ocean study.
IRS-1C WiFS 2 188.0 1996 India It is used for GIS mapping and
surveing.
RESURS-01-1 MSU-S 2 240.0 1985 Russia It is used for monitoring natural earth
RESURS-01-1 MSU-SK 5 170.0, 600.0 1985 Russia
resources and urban planning, earth
observation etc.

b) Make a list of all satellites in geo-stationary/ non-synchronous orbits and provide following
information in tabular form:
 Spatial resolution
 Spectral resolution,
 launching year
 Country who launched
 Area of research it can be used for.
(Marks 04)
Answer:

Geo-Stationary Satellites
Name Spectral Spatial Launching Country Field of use

resolution resolution year who

(m) launched
HYLAS-1 0.23-12.5 30 2010 USA Used for the coast line observation
MICROMETER
AMC-4 100nm – 100 30 1999 Dutch It is used for weather monitoring and
micrometer weather mapping.
HIMAWARI- 8 bands 644 500-2000 2015 Japan It is used for aviation and surveying.
8 nm to2260
nm
SYNCOM-2 12 bands 500 1963 USA It is used for ocean study and also used
o.51 to 0.91 for weather monitoring
micrometer
GALAXY-25 28 kubands 25 1997 USA It is used for communication.
GOES-16 16 bands 1000 2016 USA Used for weather mapping
0.64 meter
METEOSAT- 12 bands 3000 2008 ESA It is used for weather monitoring and
8 disaster control
Echostar 12 band 500 2017 USA Weather monitoring and communication
Astra-1 14 band 2.5 1998 UK Telecommunication purposess


Not car

Q.No.3. Discuss all existing resources available in doing research on image classification by using
Machine Learning and Deep Learning practices in the context of remote sensing. Especially focus
what Google Company provides in this domain in comparison with its competitors like Facebook.
(Marks 04)
Answer:

Image Classification using Machine learning and Deep learning:

Machine Learning:

Machine learning is the study that gives ability to the computers or machines to learn without being
explicitly programmed”. A Machine Learning project run a piece of software that produced output
from B from given input A.
⛰⛪
input feature extraction classification output

Deep Learning:

It is the subset fo ML and type of artificial intelligence (AI), Deep learning makes the network
capable to learn unsupervised from the data which is unlabeled or unstructured. It works on the
principle of Deep Neural Networks.

Input feature extraction + classification output

Image classification using deep learning and Machine


learning:

Image classification is done by using supervised learning method and in which we define a set of
target objects to identify the image of interest and after that train the model to recognize the
objects using labeled photos. It involves extraction of useful information and features from the
image.
Tools and libraries:

Following are the tools and programing libraries used for the image classification in remote sensing:

 TensorFlow: It is an open source platform and providing

implementation of machine learning model and training that Not car

model.

 Keras: It is library used for the implementation of Neural Network architecture. Keras

provide API for layer stacking of neural network.


 Pandas: It is library used in data analysis and data sciences and used for data modification.

 Matplotlib: It is used in Machine Learning for visualization of classified features.

 Numpy: it used for mathematical computation and algorithem for operations of data
structures.

Algorithms used for Image classification in Remote sensing:

Following algorithms used for image classification:


 K-Nearest Neighbor algorithm (KNN)

KNN is used for identification of objects based on the closest training model in the feature
space. .

 Support Vector Machine (SVM) algorithm

SSVM is used for non-linear classification and it is done by using kernel trick.

 Ensemble Learning algorithm

It is a technique used to aggregate the group of predictors.

 Multi-layer Perceptron (MLP)

In MLP there can be more than one non-linear layer can be hidden between input and output.

 Convolutional neural networks (CNNs)

CNNs have is used to manage the to achieve superhuman performance by increasing the

power of computation and outperformer architecture that used in this model.

 Stochastic Gradient Descent (SGD) Classifier

It has the ability to classify the images in linear categories.


Image Classification done by following steps:

 Image Classification
It means to label the objects and features in the image or photograph

 Image Classification With Localization


It involve the method to giving class label to the group of and image to show the location of
that object.

 Object Detection
Object detection is the most challenging and important part of the image classification, it
involves recognition of object.

 Object Segmentation
It involves to segmentation of objects in an image on the basis of pixels, also involves
segmentation of pixel in which a line draw around the object.

 Image Style Transfer


In this task, a style has given to the new image on the basis of previous image style.

 Image Colorization
It involves to giving color to the simple grey style image.

 Image Reconstruction
This part involves filling of damage or missing part in the image.

 Image Super-Resolution
In this task, high resolution given to an image.

 Image Synthesis
It is the task in which model is train on the basis of object style. For example the physical
orientation of zebra and horses are same, but the color pattern is different, so this is
classified using this model.

Deep learning and machine learning and widely used in remote sensing for image
classification, object recognition, feature extraction from the image.

Google services in Machine Learning and Deep Learning:

 Open source Algorithms:

Google provides built in algorithms of image classification of machine learning and deep
learning. User from all over the world can write and implement code on Google Cloud.
 Google Cloud

Google provides Google cloud at there developer can write and run code and built in
function. No need of any other software, so that’s why it is very popular in public.
 Deployment of Trained model:

Google provide platform where user can deploy his model.


 Free Algorithms:
Google provides free built in algorithms including Linear learner algorithms, wide and deep
algorithm and image classification algorithm
 Cloud AutoML

Cloud AutoML is a suite provide by the google for image classification and object
recognition.
 ML Kit

This kit is capable of detecting face, text and identifying landmarks and other features from
the object.
It can be run in API or cloud
Provides easy ways to deployment of the model.
 Security

Google has high security to protect our cloud credentials.


 AI hub

Google AI hub provides platform where user can share their model and project from end to
end pile line of ML.
 TenserFlow

Google provides TenserFlow which is an open source machine learning platform.


 CoLaboratory

Google provides research products about ML in that. It also provides Jupyter notebook in
which we have a large package of all ML tools.

Facebook Services in Machine learning:

Facebook developers has made the algorithms that ranks ads and feeds. Facebook has strong object
recognition and image recognition algorithms i.e if any user of two billions user of facebook upload
picture of another person, Facebook notify the person about this by detecting face.

 PyTorch:

PyTorch is created by facebook to facilitate their users and developers. It is easy to use and
debug as compared to TenserFlow
 ONNX

It is open source frame work by facebook to facilitate the developers to make model and
deployment of that model.
 Detectron

Research platform by facebook.


 Duckling

Library by facebook to detect text.


 Glow
It is the compiler of machine learning
 StarSpace

It is neural network model.

Google is providing more services in machine learning image processing and classification as
compared to its competitors like facebook and Microsoft.



You might also like