Digital Image Processing III: Supervised Classification Objective | GEO 4093, Lab Reports of Geology

Material Type: Lab; Class: Principles of Remote Sensing; Subject: Geology; University: University of Texas - San Antonio; Term: Fall 2008;

Typology: Lab Reports

Pre 2010

Uploaded on 08/18/2009

koofers-user-gbu
koofers-user-gbu 🇺🇸

10 documents

1 / 6

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
Lab Instructions
Lab 6, due 7:00 pm October 20, 2008
EES5053/GEO4093: Remote Sensing, UTSA
Student Name: ___________________
Digital Image Processing III: Supervised Classification
Objective: In this lab, you will compute all bands’ radiance, stack
individual bands together, and classify the image (study area) using
unsurprised and supervised classification methods. Finally, you will
calculate the flooded area.
Part I: Concepts and short questions:
1. Summarize the differences between multispectral remote sensing and hyperspectral
remote sensing
2. Using a table to summarize four multispectral remote sensors and four hyperspectral
remote sensors in terms of their resolution and coverage (spatial, spectral, radiometrical,
and temporal), sensor type (whiskbroom, pushbroom, or linear and area array), and their
major applications. (if you cannot get all of those information from the text book and
from the lecture notes, you are encouraging to search those from the Internet).
3. Summarize three EOS satellites (Terra, Aqua, Aura) in terms of the launching time,
major sensors, and purposes.
Part II:
1. Preparation:
(1). Create a Lab6 directory under c:\UserData_ENVI\yourname\. Today we will use
the atmospherically corrected image that you processed in Lab4:
p27r40_July8_2002DOS.img. You do not need to copy this image from Lab4 to
Lab6, but directly open it from Lab4, while save your results to Lab6 directory.
2. Background
1
pf3
pf4
pf5

Partial preview of the text

Download Digital Image Processing III: Supervised Classification Objective | GEO 4093 and more Lab Reports Geology in PDF only on Docsity!

Lab Instructions Lab 6, due 7:00 pm October 20, 2008 EES5053/GEO4093: Remote Sensing, UTSA Student Name : ___________________

Digital Image Processing III: Supervised Classification

Objective: In this lab, you will compute all bands’ radiance, stack

individual bands together, and classify the image (study area) using unsurprised and supervised classification methods. Finally, you will calculate the flooded area.

Part I: Concepts and short questions:

  1. Summarize the differences between multispectral remote sensing and hyperspectral remote sensing
  2. Using a table to summarize four multispectral remote sensors and four hyperspectral remote sensors in terms of their resolution and coverage (spatial, spectral, radiometrical, and temporal), sensor type (whiskbroom, pushbroom, or linear and area array), and their major applications. (if you cannot get all of those information from the text book and from the lecture notes, you are encouraging to search those from the Internet).
  3. Summarize three EOS satellites (Terra, Aqua, Aura) in terms of the launching time, major sensors, and purposes.

Part II:

1. Preparation:

(1). Create a Lab6 directory under c:\UserData_ENVI\yourname. Today we will use the atmospherically corrected image that you processed in Lab4: p27r40_July8_2002DOS.img. You do not need to copy this image from Lab4 to Lab6, but directly open it from Lab4, while save your results to Lab6 directory.

2. Background

On June 30 - July 8, 2002 , a tropic storm hit the central and south-central parts of Texas. During the 8 days, the storm fell as much as 35 inches of rainfall, with heaviest depths occurring in the Texas Hill Country northwest of San Antonio. The floods caused twelve deaths and damage to about 48,000 homes. Nearly 250 flood rescue calls were reported, more than 130 roads were closed, and thousands of homes and businesses lost electrical power and telephone service.

3. Calculate the Radiance

In the lab 5, you calculated the radiance and reflectance of band 3 and band 4. In this lab, you are required to compute the radiance of band 1, band 2, band 5, band 6 and band 7 using band math tool based on equation (1), table 1, and figure 1 as you did in lab

  1. (Caution: for band 6, please use the band 9-high gain for the gain and offset calculation, i.e. 0.037059DN+3.200000 for band 6).* Output the results to lab6 and name them as Radiance-b1.img, Radinace-b2.img, Radiance-b5.img, Randiance-b6.img, Radiance-b7.img, respectively. L (^)   gain * DNoffset (1) Table 1 Detector gain offset Abs Calib?

1 | 15 0.775686 -6.20000 FALSE 2 | 12 0.795686 -6.39999 FALSE 3 | 8 0.619216 -5.00000 FALSE 4 | 7 0.965490 -5.10001 FALSE 5 | 14 0.125725 -0.99999 FALSE 6 | 8 0.066823 0.000000 FALSE 7 | 10 0.043726 -0.35000 FALSE 8 | 27 0.971765 -4.70000 FALSE 9 | 8 0.037059 3.200000 FALSE 

Then the following window will popup. change the parameters to the same as the window below and save your result to Memory (or your Lab6 directory). The classified results will appear in the Available Band List. Open the classification image, copy and paste one to your homework.

6. Supervised Classification

Training sites

To do a supervised classification, you need to first select training sites. Supposing you already know many classes in your image, and you need to tell them what they are using the ROI tool. For example, the ROI window below is what I did for my study: And the ROIs are on the image below. You can see for each type of ROI, I have marked multi-places on the image to represent the variation of the same class. You might use different classes and different areas.