Docsity
Docsity
Prepare for your exams
Prepare for your exams

Study with the several resources on Docsity

Earn points to download
Earn points to download

Earn points by helping other students or get them with a premium plan

Guidelines and tips
Guidelines and tips
Sell on Docsity
Sell on Docsity
Docsity AI
Docsity AI
Log inSign up

Prepare for your exams

Study with the several resources on Docsity

Find documents

Prepare for your exams with the study notes shared by other students like you on Docsity

Search for your university

Find the specific documents for your university's exams

Docsity AINEW

Summarize your documents, ask them questions, convert them into quizzes and concept maps

Explore questions

Clear up your doubts by reading the answers to questions asked by your fellow students

Earn points to download

Earn points by helping other students or get them with a premium plan

Share documents
download point icon20 Points

For each uploaded document

Answer questions
download point icon5 Points

For each given answer (max 1 per day)

All the ways to get free points
Get points immediately

Choose a premium plan with all the points you need

Study Opportunities

Choose your next study program

Get in touch with the best universities in the world. Search through thousands of universities and official partners

Community

Ask the community

Ask the community for help and clear up your study doubts

Free resources

Our save-the-student-ebooks!

Download our free guides on studying techniques, anxiety management strategies, and thesis advice from Docsity tutors

Lab 5: Image Segmentation with SPRING Software - Prof. Ludmila Moskal, Lab Reports of Environmental Science

University of Washington (UW) - SeattleEnvironmental Science
Prof. Ludmila Moskal

The steps to import, manipulate, and segment images using the spring software in a lab session for esrm430 class in spring 2008. Students will learn about image import, setting up databases, displaying images, using contrast tools, and image filtering. The lab involves working with grayscale and true color images, and producing segmentations with different similarity classes.

Typology: Lab Reports

Pre 2010

Uploaded on 03/10/2009

koofers-user-qt7
koofers-user-qt7 🇺🇸

9 documents

1 / 3

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
Page 1 of 3
NAME: ____________________________
ESRM430 SPRING 2008
Dr. L. Monika Moskal
Lab 5
Lab Objectives:
• Introduction to SPRING software, simple image manipulation and computer aided image segmentation
Tools:
• SPRING software
• Sample of the 1996 aerial panchromatic image of the Washington State Arboretum area at 25cm per pixel
resolution with image dimension of 2184 by 1812 pixels
• Sample of the 2006 true color image of UW campus at 25cm per pixel resolution and image dimension of 920 by
920
• Lots of patience ☺
What you will hand in:
• Screen captures of maps and a written discussion.
Task 1:
In this task you will import the 1996 panchromatic image to work with in the SPRING software. Note the image does not
have geocoordinates. We are only working with it as an example and will not need to worry about setting appropriate
geographic coordinates for the image. If you were to use this software for a project you will need to spend a substantial
amount of prepping to set up the imagery for import with geographic coordinates.
• First set up a directory on the computer to work from. I suggest using …ESRM430/Lab5
• Start the SPRING software
• In the main menu go to File>Database and create a database with a distinct name such as “1996photo”; hit the
Apply button before exiting the database dialog window
• Next go to File>DataModel and set up an appropriate model such as “image” hit the Create button and then the
Apply button; you can close the window now
• Next import the 1996 photo by going to File>Import
o Select the image you copied form the lab website or drive
o Format should be set to JPEG
o Entity should be set to Image
o Resolution is set to 0.25 by 0.25
o Projection is set to UTM-WGS84
Long: e 0 0 0.00
o Boundary box
X1 0.0
X2 2184
Y1 0.0
Y2 1812
o Project is the database name “1996photo”
o Category is the model you defined “image”
o Infolayer can be set to ‘image’
o Hit the Execute button and then the Close button
The program should still appear blank, don’t worry and move on to Task 2
pf3

Partial preview of the text

Download Lab 5: Image Segmentation with SPRING Software - Prof. Ludmila Moskal and more Lab Reports Environmental Science in PDF only on Docsity!

NAME: ____________________________

ESRM430 SPRING 2008

Dr. L. Monika Moskal Lab 5

Lab Objectives:

  • Introduction to SPRING software, simple image manipulation and computer aided image segmentation

Tools:

  • SPRING software
  • Sample of the 1996 aerial panchromatic image of the Washington State Arboretum area at 25cm per pixel resolution with image dimension of 2184 by 1812 pixels
  • Sample of the 2006 true color image of UW campus at 25cm per pixel resolution and image dimension of 920 by 920
  • Lots of patience ☺

What you will hand in:

  • Screen captures of maps and a written discussion.

Task 1: In this task you will import the 1996 panchromatic image to work with in the SPRING software. Note the image does not have geocoordinates. We are only working with it as an example and will not need to worry about setting appropriate geographic coordinates for the image. If you were to use this software for a project you will need to spend a substantial amount of prepping to set up the imagery for import with geographic coordinates.

  • First set up a directory on the computer to work from. I suggest using …ESRM430/Lab
  • Start the SPRING software
  • In the main menu go to File>Database and create a database with a distinct name such as “1996photo”; hit the Apply button before exiting the database dialog window
  • Next go to File>DataModel and set up an appropriate model such as “image” hit the Create button and then the Apply button; you can close the window now
  • Next import the 1996 photo by going to File>Import o Select the image you copied form the lab website or drive o Format should be set to JPEG o Entity should be set to Image o Resolution is set to 0.25 by 0. o Projection is set to UTM-WGS ƒ Long: e 0 0 0. o Boundary box ƒ X1 0. ƒ X2 2184 ƒ Y1 0. ƒ Y2 1812 o Project is the database name “1996photo” o Category is the model you defined “image” o Infolayer can be set to ‘image’ o Hit the Execute button and then the Close button

The program should still appear blank, don’t worry and move on to Task 2

Task 2: Once you have imported the image open the Control Panel (5 th^ color icon from the left on the main menu) and make the settings the same as the example to the right. Since this is a monocromatic image (grayscale) you are selecting the M to display it. Color images would use the RGB display. Hit the Reset button (2 nd^ color button from the right that looks like a red left pointing arrow); this should draw the image for you on the screen. Use the navigational tools to explore the image.

Task 3: To understand what pixel values in imagery represent and how some simple tools such as histograms can help us interpret them you will use the contrast tool. In the main menu go to Image>Contrast…. Zoom out to the full extent of the image.

  1. Describe the shape of the histogram for the full image. How does the histogram relate to the visual image that you are seeing? You can screen capture the histogram and include it in your write up; to do so click on the Contrast window then press the following buttons together: Ctrl, Alt, Print Screen. This will save the window to the clipboard, you can now paste it to your word write up document.

Now navigate the image so that one of the water areas is in the center of the screen and begin zoom in (+) and observe the changes in the histogram as you increase the resolution of the image.

  1. What happens to the histogram?
  2. If you were to center your display on one of the HWY overpasses, what do you expect to see in the histogram?
  3. How about for vegetation?

Task 4: Image filtering and enhancements allow us to better visually interpret an image. In the main menu go to Image>Filtering… Select the Edge Detection filter and produce an image that you include in your write up.

  1. Discuss the Edge Detection image you created.

Task 5: In this next section you will be working with the UW 2006 true color image. Close the previous database and set up a new SPRING database to work with this file. The image dimensions are 920 by 920. Since this is not a monochromatic image you will need to set up the multicolor bands to display the image properly (see last page of the handout to see how the Control Panel needs to be set up).

Segmentation relies on the pixel values and the spatial characteristics of an image. Although the algorithms used in segmentation are often proprietary they rely on the fundamental of spatial autocorrelation which we will discuss in class. In this final task you will produce 2 segmentations of the panchromatic image. The 1st^ segmentation will use the least number of similarity classes (3), the second segmentation will use a larger number of similarity classes (30).

Set up the segmentations as per my instructions using similarity values of 3, 30. Your method should always be Region Grow and Area (pixels) should always be 100. You will use all three bands in the segmentation. An example of the segmentation dialog is on the last page of this handout.