clc
close all
I = imread('Image1.tif');
J = I(:, :, 1:3);
K = rgb2gray(J);
BW2 = edge(K,'sobel',50,'horizontal');
%h = ones(5,5) /25;
h = fspecial('gaussian', 100,0.5);
m = fspecial('sobel');
hvert = ( fspecial('sobel'));
I2 = imfilter(K,h);
I3 = imfilter(K,hvert);
%figure, imshow(I2);
figure,imshow(I3);
%figure, imshow(BW2);
%figure, imshow(BW2);
%figure, imshow(J);
focsuses on using sobel to find horizontal / vertical pieces of a poll.
Wednesday, April 24, 2013
Lab Notes 4/24/2013 (WEEK 4 LAB)
This week's topic is still more focused on the filters. The one we used, as in Gaussian Filter, is not appropriate to use in our image prosscessing. As the instructor reconmmened us to take a look at the Matlab's built in filters, we try to use the edge detection to apply the filter after with a conference with TA.
Do list :
1) Do more research about the filters
2) Try every filter that make sense with its definition
3) Apply the most correct filter and do more correction
In researching the filters:
1) sample filtering http://lodev.org/cgtutor/filtering.html
2) useful link for k-means courses.washington.edu/matlab2/Lesson_15.html
Notes for K-means :
Basically, K-means does classify the center of different things.
In a 2-dimensional space( 2D coordinates). As each point point has a specific value, what K-means do is to pick up the value and put them into a cluster. For instance, K has a value of 3, then the function will pick up things and separate them into 3 clusters.
For the process of K- means:
1) pick up the center
2) decide each pixel goes to
3) repeat the process until things stop changing
In order to separate things appropriately, a conclusion came to the surface that we need to figure out an appropriate value for the K.
*There is a built-in k-means command in the Matlab.
Here is the list of problems we faced during the lab:
1) we can not determine which filter to use
2) cannot figure out the value for the filters
Here is the list of good things we had:
1) the "sobel" filter gives us some confidence of figuring out the filter
Do list :
1) Do more research about the filters
2) Try every filter that make sense with its definition
3) Apply the most correct filter and do more correction
In researching the filters:
1) sample filtering http://lodev.org/cgtutor/filtering.html
2) useful link for k-means courses.washington.edu/matlab2/Lesson_15.html
Notes for K-means :
Basically, K-means does classify the center of different things.
In a 2-dimensional space( 2D coordinates). As each point point has a specific value, what K-means do is to pick up the value and put them into a cluster. For instance, K has a value of 3, then the function will pick up things and separate them into 3 clusters.
For the process of K- means:
1) pick up the center
2) decide each pixel goes to
3) repeat the process until things stop changing
In order to separate things appropriately, a conclusion came to the surface that we need to figure out an appropriate value for the K.
*There is a built-in k-means command in the Matlab.
Here is the list of problems we faced during the lab:
1) we can not determine which filter to use
2) cannot figure out the value for the filters
Here is the list of good things we had:
1) the "sobel" filter gives us some confidence of figuring out the filter
Filtering and Edge Detection
We researched more about filters and tried to test some of the filter examples we had. Edge Detection should be fine. There is a high chance that we will keep the canny edge detector for our program, the others we have tried were not as detailed as the canny.
Wednesday, April 17, 2013
Code Week3
clc
close all
I = imread('Image1.tif');
J = Image1(:, :, 1:3);
K = rgb2gray(J);
BW2 = edge(K,'canny');
%h = ones(5,5) /25;
for i = 1:10:360
h = fspecial('gaussian', 5, i);
I2 = imfilter(K,h);
figure, imshow(I2);
pause(0.5)
end
figure, imshow(BW2)
%to resize image
% imshow(image1(:, :, 1:3))
Filtering
These websites will help with finding the filtering style we choose to use.
http://www.mathworks.com/help/images/functionlist.html
http://opencv.org/
http://www.mathworks.com/help/images/functionlist.html
http://opencv.org/
Lab Notes 4/17/2013 (WEEK 3 LAB)
This week's topic is to use the MATLAB to do the Edge Detection and then the Gabor filtering. In short terms, it means to apply the filter to compare the similarity of the two objects, so that the data can be justified in a more correct way.
Here is the list of good things we had :
1.We have the best group numbers!
2. We figured out how to use the 'edge' command in Matlab.
3. Main W05 is open almost everyday during the week. And there will be software that we need installed.
4. A sample of using the 'imfilter' command in Matlab :
http://www-rohan.sdsu.edu/doc/matlab/toolbox/images/linfilt6.html
5. A sample of using the 'imshow' command in Matlab: imshow(image1(:,:, 1:3));
Here is the list of problems we faced during the lab:
1. We could not connect our digital storage to the computer. ( So that we had to use our personal computer) Drexel technology is problematic.
2.Matlab crushed at the first time when we tried to let it handle the data.
3.We had problem using the imfilter command at first.
4.We used and understood the 'imshow' in a wrong way.
Here is the list of good things we had :
1.We have the best group numbers!
2. We figured out how to use the 'edge' command in Matlab.
3. Main W05 is open almost everyday during the week. And there will be software that we need installed.
4. A sample of using the 'imfilter' command in Matlab :
http://www-rohan.sdsu.edu/doc/matlab/toolbox/images/linfilt6.html
5. A sample of using the 'imshow' command in Matlab: imshow(image1(:,:, 1:3));
Here is the list of problems we faced during the lab:
1. We could not connect our digital storage to the computer. ( So that we had to use our personal computer) Drexel technology is problematic.
2.Matlab crushed at the first time when we tried to let it handle the data.
3.We had problem using the imfilter command at first.
4.We used and understood the 'imshow' in a wrong way.
Wednesday, April 10, 2013
Lab Notes 4/10/2013 (WEEK 2 LAB)
Today we are performing georeferencing with ArcMap GIS.
First of all, the GIS is totally a new software to all of us, so we basically follow the instruction given by the lecturer.
Here is the one by one step for the instructions in the lab:
1. Remove the "Read only" for the file properties
2. Get the world map from USGS as the base map for our georeferencing.
3. Add our new map to the software and zoom to the area.
4. Set the green box to 128
5. Set 7~8 control points per image as the referencing points
6. Use "turn off the layer" to find the corresponding points for any mistakes and reference.
8. Save the control points
7. Update the georeferencing.
8. create the new image"Rectify". (transformation)
(For self-installing the ArcMap GIS, installing the service pack #5 is primary requested).
Here is the list of problems we faced during the lab:
1. We could not add the image into the GIS.
2. It was hard to choose control points
3. There are some houses gone in the new map, so that we cannot even reference to a point
First of all, the GIS is totally a new software to all of us, so we basically follow the instruction given by the lecturer.
Here is the one by one step for the instructions in the lab:
1. Remove the "Read only" for the file properties
2. Get the world map from USGS as the base map for our georeferencing.
3. Add our new map to the software and zoom to the area.
4. Set the green box to 128
5. Set 7~8 control points per image as the referencing points
6. Use "turn off the layer" to find the corresponding points for any mistakes and reference.
8. Save the control points
7. Update the georeferencing.
8. create the new image"Rectify". (transformation)
(For self-installing the ArcMap GIS, installing the service pack #5 is primary requested).
Here is the list of problems we faced during the lab:
1. We could not add the image into the GIS.
2. It was hard to choose control points
3. There are some houses gone in the new map, so that we cannot even reference to a point
Thursday, April 4, 2013
Project Design Proposal
ENGR 103 - Spring 2013
Freshman Engineering Design Lab
Freshman Engineering Design Lab
“Satellite
Image Processing”
Project Design
Proposal
Date
Submitted: April 10, 2013
|
Submitted
to:
|
Anu Pradhan, arp69@drexel.edu
James Worcester, james.worcester2@gmail.com
|
Group
Members:
|
Dongen Zhou, dz78@drexel.edu
|
Eddie Tang, et354@drexel.edu
|
|
Louis Rogowski, lwr@drexel.edu
|
|
Abstract:
1
Introduction
Discuss the motivation and goals of
the planned project. Discuss the learning objectives, major tasks, technical
challenges, and desired outcomes.
2
Deliverables
Describe in detail what you will
produce at the conclusion of the project: examples include physical prototypes,
computer models, simulation results, algorithms and programs, design studies,
lab test results.
3
Technical Activities
Elaborate on the major tasks of the
project and how these tasks will allow you to address the technical challenges
of the project.
3.1 Georeferencing
“ In simple
terms, georeferencing just means relating information to geographic
location.”[1] Specifically in processing satellite images, georeferencing is
being used to locate objects in the terms of geographical projections, or
coordinating systems. Since it is a process of creating a whole system, an
automatic georeferencing procedure can be done as: “ 1. Scanning a paper
topographic plan (map board) and obtaining a digital raster image; 2.
Referencing control points (using a coordinate grid) and transformation; 3.
Vectorization.”[2]
3.2 Sample Subsection 2
This is an example of a subsection.
To get the required formatting, use the Microsoft word “Heading 2” style. The
paragraph text here uses the “Normal” style.
4
Project Timeline
During spring term, you will have
approximately 10 weeks to complete your project. Provide a project timeline (a
Gannt chart) that shows the major tasks and their duration. If this project
requires you to learn a specific skill, time should be allocated for this in
your timeline. The following table is for illustration only and the specific
tasks listed will likely not apply.
Week
|
||||||||||
Task
|
1
|
2
|
3
|
4
|
5
|
6
|
7
|
8
|
9
|
10
|
Literature study
|
x
|
x
|
||||||||
Mechanical design
|
x
|
x
|
x
|
x
|
x
|
|||||
Electrical design
|
x
|
x
|
x
|
x
|
x
|
|||||
System integration
|
x
|
x
|
x
|
|||||||
Testing
|
x
|
x
|
x
|
|||||||
Final report preparation
|
x
|
x
|
x
|
Table 1: Sample freshman design
project timeline. To add captions like this one, right-click the table or figure
and select "Caption". Place all captions beneath their
figures/tables.
5
Facilities and Resources
Describe any resources you are
expected to use during the course of the project. This includes anything that is necessary for the
completion of the project and that your group does not already possess.
Examples include use of machine shop tools, rapid prototyping machine, faculty
research space and equipment, on or off-campus work space. If no resources are
needed, state this.
6
Expertise
Some projects may require group
members to have skills in certain areas prior to starting the project while
other projects may require group members to acquire these skills through the
course of the project. Describe any specialized skills that may be needed for
this project. Some examples include
- Familiarity with a specific software package
- Computer programming experience
- Knowledge of basic circuit theory
- Use of machine tools
7
Budget (if appropriate)
For any projects that require the
purchase of materials, either by the group or their advisor, a budget must be
provided. This should be organized by category, and for each expense category
there should be a brief description of the expense. For example, see the
following subsections.
Category
|
Projected Cost
|
Mechanical
Hardware
|
$23.45
|
Stepper
Motors
|
$57.01
|
Motor
Controller
|
$110.12
|
TOTAL
|
$190.58
|
Table 2: Sample freshman design
project budget. To add captions like this one, right-click the table or figure
and select "Caption". Place all captions beneath their
figures/tables.
7.1 Mechanical Hardware
Overview description of this
category, and how this component fits into the project. If there are more than
one subcomponents to this budget category, consider creating a table like Table
2.
7.2 Stepper Motors
Overview description of this
category, and how this component fits into the project. If there are more than
one subcomponents to this budget category, consider creating a table like Table
2.
7.3 Motor Controller
Overview description of this
category, and how this component fits into the project. If there are more than
one subcomponents to this budget category, consider creating a table like Table
2.
Reference:
[1] Ricker, Kim M. "Georeferencing: The Geographic
Associations of Information." Portal : Libraries and the Academy 7.3
(2007): 387-8. ProQuest. Web. 4 Apr. 2013.
[2]
Titova, O. A., and A. V. Chernov. "Method for the Automatic Georeferencing
and Calibration of Cartographic Images." Pattern Recognition and
Image Analysis 19.1 (2009): 193-6. ProQuest. Web. 4
Apr. 2013.
Wednesday, April 3, 2013
Research for Proposal
Check the slides they upload for more info.
Research the following:
1. Georeferencing.
2. ESRI ArcMap
3. Filters
4. K-means.
and some way to make them work togeather, post whatever you find on the blog.
Booyah!
Research the following:
1. Georeferencing.
2. ESRI ArcMap
3. Filters
4. K-means.
and some way to make them work togeather, post whatever you find on the blog.
Booyah!
Subscribe to:
Posts (Atom)