Lab 5 Accuracy Assessment - Remote Sensing (GLS 612)

    Accuracy assessment is performed by comparing the two different maps created from remote sensing analysis to a reference map based on the different source. The important of accuracy assessment and error analysis is to permit the quantitative comparisons of different interpretations. In order to compared, the map need to be evaluated and the reference map, both must be accurately registered geometrically to each other. They also must use the same classification scheme and they should have been classified at the same level of detail. This type of assessment is called site-specific accuracy which is based on a comparison of the two maps at specific location for example; individual pixels in two digital images. In this type of comparison, it is clearly that the degree to which the pixels in one image spatially align with the pixels in the second image contributes to the accuracy assessment result. Errors in classification should be distinguished from errors in registration or positioning of boundaries. Another useful form of site-specific accuracy assessment is to compare field data or training data at a number of locations within the image, similar to the way spatial accuracy assessment using ground checkpoints is performed for digital orthophotos and terrain models.


My Lab 5 Report :

Lab 5 Accuracy Assessment (GLS 612)

Remote Sensing (GLS612) Syllabus Notes

This course introduces the students to the principles and developments of remote sensor systems, characteristics and interactions of electromagnetic radiation with the atmosphere and earth’s surface, digital image processing; applications in various disciplines. The course extends student’s knowledge on latest technology of remote sensing.

Remote sensing is the science (and to some extent, art) of acquiring information about the Earth's surface without actually being in contact with it. This is done by sensing and recording reflected or emitted energy and processing, analyzing, and applying that information".

Download Notes :

1. Introduction to Remote Sensing
2. Principle of Electromagnetic Radiation (EMR)
3. Spectral Response Pattern (EMR and Atmospheric Effects)
4. Interpreting Land Surface Features
5. Understanding the Image and Processing
6. Image Pre-Processing
7. Image Enhancement
8. Thematic Information Extraction (Classification)
9. Accuracy Assessment in Remote Sensed Information
10. Active Microwave Remote Sensing (RADAR and LiDAR)
11. Applications of Remote Sensing

Lab Assignment :

1. Lab 1 Introduction to ERDAS Imagine
2. Lab 2 Geometric Correction
3. Lab 3 Atmospheric Correction
4. Lab 4 Unsupervised Classification
5. Lab 4 Supervised Classification

Lab 1 Introduction to Erdas Imagine - Remote Sensing (GLS612)

   
ERDAS IMAGINE is tools application for remote sensing that used raster data. Ability ERDAS designed to prepare, display and enhance data image. It is a toolbox allowing the user to perform numerous operations on an image and generate an answer to specific geographical questions. By manipulated data image values and position is possible to see features that would not normally be visible and to locate positions of features that can be graphical. In this task, we use ERDAS Imagine 2013.

Software Used :

Erdas Imagine 2013

My Lab 1 Report

Lab 1 - Introduction to Erdas Imagine (GLS612)

Lab 1 Mangrove Changes Detection - Marine Resource Management (GLS617)

    

   Mangrove is located in the tropical and subtropical regions and brings good services for native people. It also inhabits on the shorelines and islands in sheltered coastal areas with locally variable topography and hydrology. Mangrove is one of the most threatened and vulnerability ecosystems. Based on the importance and vulnerable of mangrove ecosystems faced, many studies on mangrove have been conducted to solve these issues in difference scales, long-term monitoring and detecting mangrove by using remote sensing techniques. 

    The earth observation satellite data (such as Landsat) is useful for change detection applications. The distribution and abundance of mangrove in different regions of the world have been assessed with a variety of techniques. Change detection is a powerful tool to visualize, measure, and better to understand a trend in mangrove ecosystems.

Software Used :

Erdas Imagine 2013

Microsoft Excell 2016

Method Used :

 1. Model Maker :-

    a. NDWI

    b. NDVI

    c. NDBI

 2. Unsupervised Classification

 3. Matrix Union Tools

Satellite Image Used :

Satellite Images 2005, 2008 and 2014

Result Image Output :

NDWI + NDVI + NDBI

Unsupervised + Matrix Analysis

My Report and Procedure of Mangrove Changes Detection :

Lab 1 Mangrove Changes Detection (GLS617)

Lab 4 Unsupervised Classification - Remote Sensing (GLS612)

   
Digital image classification techniques group pixels to represent land cover features. Land cover could be forested, urban, agricultural and other types of features.  There are three main image classification techniques. One of them is Unsupervised classification where the outcomes (groupings of pixels with common characteristics) are based on the software analysis of an image without the user providing sample classes. The computer uses techniques to determine which pixels are related and groups them into classes. The user can specify which algorithm the software will use and the desired number of output classes but otherwise does not aid in the classification process. However, the user must have knowledge of the area being classified when the groupings of pixels with common characteristics produced by the computer have to be related to actual features on the ground (such as wetlands, developed areas, coniferous forests, etc.). For this project, there are 30 samples and we need to class category into 5 classes which is water bodies, forest, vegetation, bare land and urban. Proceed the same step for different algorithm, K-mean and Isodata.

Software Used :

Erdas Imagine 2013

Satellite Image Used :

Satellite Images 2005 and 2008

Result of Unsupervised Classification :

Unsupervised Images

My Report and Procedure of Unsupervised Classification :

Lab 4 Unsupervised Classification (GLS612)

Lab 4 Supervised Classification - Remote Sensing (GLS612)

   

Supervised classification is based on the idea that a user can select sample pixels in an image that are representative of specific classes and then direct the image processing software to use these training sites as references for the classification of all other pixels in the image. Training sites (also known as testing sets or input classes) are selected based on the knowledge of the user. The user also sets the bounds for how similar other pixels must be to group them together. These bounds are often set based on the spectral characteristics of the training area, plus or minus a certain increment (often based on "brightness" or strength of reflection in specific spectral bands). The user also designates the number of classes that the image is classified into. Many analysts use a combination of supervised and unsupervised classification processes to develop final output analysis and classified maps.

Software Used : 

Erdas Imagine 2013

Image Used :

Satellite Images 2005 and 2008

Result of Supervised Classification :

Supervised Image + Aoi + Signature Editor

My Report and Procedure of  Supervised Classification :

Lab 4 Supervised Classsification (GLS612)

Lab 3 Atmospheric Correction - Remote Sensing (GLS612)

   

The atmosphere influences the amount of electromagnetic energy that is sensed by the detectors of an imaging system and these effects the wavelength transmitted. When electromagnetic radiation travels through the atmosphere, it may be absorbed or scattered by the several particles of the atmosphere. Atmospheric absorption affects mainly on visible and infrared bands which reduces the solar radiance within the absorption bands of the atmospheric gases. Atmospheric scattering is important only in the visible and near infrared regions. Scattering of radiation is caused by the gases and aerosols in the atmosphere which affects the degradation of the remote sensing images. Most noticeably, the solar radiation scattered by the atmosphere towards the sensor without first reaching the ground produces a hazy appearance of the image. However, there are a method that uses in term of correcting the atmospheric haze effects. One of them is Dark Object Subtraction Technique in image base atmospheric correction method which is simple and effective as they require the image data to estimate the radiance of the wavelength.

Software Used :

Erdas Imagine 2013

Image Used :

Satellite Images 2005 and 2008

DOS Product + Model Maker

My Report and Procedure :

Lab 3 Atmospheric Correction (GLS612)

Lab 2 Geometric Correction - Remote Sensing (GLS612)

    

Geometric correction and orthorectification are two possible ways of tying down remotely sensed imagery to an already geometrically corrected image or to geographic reference points. Usually this techniques of geometric correction such as polynomial transformation, which was used in this exercise, are based on general functions not directly related to any specific distortion or error sources. Within this exercise the methodology of how a geometric correction using the polynomial model was performed as well as how an orthorectification was performed using ERDAS Imagine software.

Software Used :

Erdas Imagine 2013


Image Used and Result Resampling

Satellite Images and Resample


My Report and Procedure

Lab 2 - Geometric Correction (GLS612)