COMPUTER SCIENCE 426 - Computer Vision
Larry Davis
A. V. Williams 2113
lsd@umiacs.umd.edu
405-6718
Office hours: Monday, Wednesday 2:00-3:00
To get to the on the internet for
image archives, papers and research descriptions click
here.
Teaching Assistant: Yanqing
Zeng (yzeng@cs.umd.edu)
Online tutorials
One good set of tutorial notes can be found here.
These contain segments on perspective image formation, motion, etc.
Class FAQ.
SYLLABUS
Introduction - January 28; February 2,4
- Introduction
- Image formation (updated 2/2/99)
Binary vision systems - February 4, 9, 16,18
- Segmentation and connected components(updated 2/3/99)
- Pattern Recognition
- Special lecture on Thursday February 11 - Prof. Aaron Bobick, M.I.T.
Media Laboratory
Grey scale vision systems -February 23; March 2, 4, 9.
3-D Vision: March 9, 11,16, 18, ; April 6, 8, 13
- Geometry of image formation
- Calibrating cameras
- Recognizing 3D objects from models
Motion and Navigation - April 15,20,22, 27
- Time-varying image analysis
Color - April 29; May 4
- Forming and analyzing color images
Projects
- First programing project (current)
- This project will be officially handed out on February 16 and will
be due on
- You can click here to obtain information
about the machines supporting the class accounts.
- The TA's home page
contains a copy of the assignment as well as a pointer to the ftp site
that you can use to download the images in the training set.
- The project description covered in class on 3/17 is here ( PS
, PDF )
-
Second programming project
- Powerpoint presentation
- Some notes on the project
- Final presentation on project
Course requirements
- Tests - There will be three exams during the semester; each is worth
20% of your grade
- Test 1 is scheduled for February 25 and will cover the
material up to February 18
- Test 2 is scheduled for April 1 and will cover the material
through March 25
- Test 3 will be the last day of class and will cover the remaining topics
- Projects - There will be two projects worth a total of 40% of your
grade.
Things for you to think about for Test 1
- Example test
- The first exam will cover the material presented in class through the
lecture of February 18.
- There are many definitions of terms in the notes and book. You
should know the definitions of all technical terms introduced in the lectures.
They are listed below, with links to the definitions.
- Things to make sure you know for test 1:
- Applying the lensmakers equation to determine the distance behind the
lens at which a point will be brought into focus
- How to prove that normalized central moments are invariant to scale
changes of sets of pixels
Things for you to think about for Test 2
- In constructing an image pyramid, we replace each 2x2 nonoverlapping
neighborhood of pixels at level i with a single pixel at level (i-1). If
the original image is 2^n x 2^n, then how many pixels are there, in total,
in an image pyramid? Be able to prove your result using induction.
- In coarse fine template matching we correlate a reduced resolution
template against a reduced resolution image, and at those locations where
the correlation is sufficiently high we correlate the full resolution template
against a window of the full resolution image. Suppose that you have an
1000x1000 full resolution image and a 25x25 full resolution template. Brute
force template matching requires 1000^2 x 25^2 operations. Suppose that
we reduce both the template and image to 200 x 200 and 5 x 5, respectively,
and also suppose that when the correlation of the 5x5 template to the 200x200
image is sufficiently high, then we correlate the 25x25 template against
the 5x5 window of the full resolution image centered at the high correlation
position. At what point does this two stage matching algorithm become less
efficient than the brute force algorithm? That is, how many pixels in the
200x200 image can have above threshold correlations with the 5x5 reduced
template before we do more work using the two stage method?
- Perspective imaging - know how 3-D points project ino 2-D images, what
vanishing points are and why parallel lines give rise to vanshing points
in images; how stereo images are formed, what conjugate points and lines
are.
Things for you to think about for Test 3
Example test
- Motion - understand the geometry of time-varying images (especially
what the focus of expansion is, how optical flow relates to 3-D motion);
algorithms for estimating optical flow, especially the gradient based technique
and the related aperture problem. Understand basic technqiues for overcoming
the constraints imposed by the aperture problem.
- 3-D object recognition - how polyhedral objects are represented, what
the problem of pose estimation is, how it can be solved using n-point perspective
models, Hough transforms and geometric hashing.
- Color - How illumination, surface reflectance and spectral sensitivity
of receptors combine. Basic ideas on how one can recover estimates of illumination
functions and reflectance functions from images.
Terms and definitions
- Image formation
- refracted ray
- Lensmaker's equation
- Optical power
- Accommodation
- Depth of field
- Chromatic abberation
- Statistical Pattern Recognition
- Segmentation by thresholding
- pixel
- intensity or grey level
- noise
- blur
- binary image
- thresholding
- histogram
- Connected Component Analysis
- 4-neighbors
- 8-neighbors
- 4-adjacent
- path
- foreground
- connected
- connected component
- background
- boundary
- interior
- Edge and Local Feature Detection
- gradient
- convolution
- separable function
- non-maxima supressiont
- simple point
- end point
- junction
- curvature
- Correlation matching
- template
- pyramid
- Sum of squared differences
- Hough transform
- Distance Transform
- Chamfer matching
- Hausdorff distance