 |
Downloadable:
|
|
Run unzip to
extract all the files.
|
|
List of
functions/data included in the file lab1.zip.
 |
sample_code.m
Sample code than you can use as a framework to start work with.
|
|
harrisCorner.m
Corner detection algorithm
|
|
show_image.m
Display an image
|
|
board1.bmp -
board9.bmp one sequence of testing images
|
|
computer1.bmp -
computer9 another sequence of testing images
|
|
|
Problem 1.
Feature detection.
|
Launch the
function "sample_code.m" to see how the corner detector works on the FIRST
image in the sequence to extract feature points. You don't need to code the
corner detector by yourself. We are supplying the codes for you to start
working with. You don't need to run the corner detector on other images
because the feature points on other images will be found by tracking in step
2.
|
|
|
Problem 2.
Feature tracking.
|
Track the feature
points on all other images in the sequence. You need to code this tracking
algorithm by yourself. You can use the SSD(sum-of-squared-differences), NCC
(normalized cross-correlation) criterion or any other method. You need to
determine the window size to get good results. There are two sequences of
images. One is a check board which is simpler. The other one is a real
scene. Check your algorithm on the simper one first and then try it on the
real scene.
|
|
|
Your Job.
|
Learn MATLAB if
you are still not familiar with it.
|
|
Both your MATLAB
codes and results must be turned in. If you insist on coding in C or C++, it
is fine too. But you must include clear instructions on how to execute your
files.
|
|
|
Copyright
acknowledgment: part of codes and documents by the courtesy of Professor
Stefano Soatto (UCLA), Jana Kosecka (GMU) etc.
|
