CMSC733 Computer Processing of Pictorial Information
|
General Information |
|
|
|
Announcements:
Description
This class will provide a
general, graduate level introduction to computer vision. We will attempt to
give students a broad understanding of all important topics in computer vision.
Prerequisites
Knowledge
of and comfort with mathematics will be very helpful. At a minimum, students
should know multivariable calculus, probability and linear algebra. No
knowledge of computer vision will be assumed, but we will go quickly, so some
background in computer vision will certainly be helpful.
Text
There is no single required text.
Required readings for the class will be listed below, and will be available
online. Three books that will be useful are:
A draft of Richard Szeliski's
computer vision book is available online. There
will be some required readings from this book.
Introductory Techniques for 3-D
Computer Vision by Trucco and Verri. This is more of an
undergraduate text, and a bit old, so many topics are not covered. However, the
fundamentals are explained very clearly.
Computer Vision: A Modern Approach by Forsyth and
Requirements
Assigned work for the class will consist of problem sets
(40% of grade), a take-home midterm (20%), and a final exam (40%).
Homework assignments are to be written up neatly and clearly, and
programming assignments must be clear and well-documented. Programs should be
written inMatlab. A full paper copy of all of the
homework must be turned in. In addition, we will ask you to email a copy of all
code to the TA, Hao Zhou, at: zhhoper at gmail.
Problem Sets
(These problem sets are listed to give you an idea of what
will be required. They may change, so do not start on them until the date on
which they are assigned).
|
|
Assigned |
Due |
|
|
Problem Set 1 |
9/16/14 |
9/30/14 |
Edge Detection. Implement 2D
edge detection, paper and pencil problems about convolution. Problem Set You
will also use the following Matlab files: test_smooth_image.m, test_image_gradient.m, test_gradient_magnitude_direction.m, interpolate_gradients.m, and the images: swanbw.jpg, swanedges.jpg,
swanedges_h.jpg |
|
Problem Set 2 |
9/30/14 |
10/14/14 |
Normalized Cut and Texture
Synthesis. Problem
Set. To test your normalized cut
code, you will use the routine: test_normalized_cut_points.m. My results with this
routine are here
and here. For texture synthesis, look at
the Efros and Leung paper. You can use the brick image to
test your code. |
|
Problem Set 3 |
10/14/14 |
10/28/14 |
E-M and Mosaicing.
Problem Set. For the mosaicing
problem, you will use these images: Image
1 Image
2 and this matlab code. |
|
Midterm |
10/28/14 |
11/4/14 |
|
|
Problem Set 4 |
11/11/14 |
11/25/14 |
Stereo matching with graph cuts.
Problem Set. First test image pair: I1L.jpg I1R.jpg Second test image pair: T3bw.jpg T4bw.jpg Tresult.jpg |
|
Problem Set 5 |
11/25/14 |
12/9/14 |
Bag of words classification. Problem Set. ps5.m |
|
Review for Final |
12/2/14 |
|
Class Schedule
This
schedule should be considered more of a guideline than a rigid plan.
Lectures
|
Class |
Topic |
Required |
Background |
Problem Sets |
|
1.
9/2 |
Introduction |
|
|
|
|
2.
9/4 |
Fourier
1 |
This
material is covered in many standard techniques. You might look at:A Wavelet Tour of
Signal Processing , by Mallat for this and
material on wavelets. Chapters 2 and 3 are on the Fourier Transform. I
also like the discussion in Elementary Functional Analysis by Shilov (This is part of the Dover Classics series, so
there is a cheap paperback edition). Some of this material is discussed in Forsyth and |
|
|
|
3. 9/9 |
Fourier
2 |
Szeliski, 3.2 and 3.4 |
||
|
4.
9/11 |
Diffusion
and smoothing |
Diffusion
Phenomena, by Ghez, Sections 1.1-1.4 (available from
instructor) |
|
|
|
5.
9/16 |
Edge
Detection |
|
Canny edge detector |
|
|
6.
9/18 |
Non-linear
Diffusion |
"A review
of nonlinear diffusion filtering," by Joachim Weickert.
In Scale-Space Theory in Computer Vision, Lecture Notes in Computer
Science, Vol. 1252, Springer, Berlin, pp. 3-28, 1997. |
See
also Weickert's book: Anisotropic
Diffusion in Image Processing |
|
|
7.
9/23 |
Bilateral
Filtering and Normalized Cut |
Carlo Tomasi and Roberto Manduchi. Bilateral Filtering for Gray and Color Images. ICCV 1998. Jianbo Shi and Jitendra Malik. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence , 22(8):888-905, August 2000. |
Michael Elad. On the Origin of the Bilateral Filter and ways to improve it. IEEE Trans. on Image Processing, 2002. |
|
|
8.
9/25 |
Attend
Talk: Visual
Recognition for the People and of the People: Tamara Berg AV
Williams 2460 |
|
|
|
|
9.
9/30 |
Texture |
Texture Synthesis by Non-parametric Sampling by Efros and Leung. Web page contains links to the paper and pseudocode. |
|
Texture synthesis |
|
|
K-means,
E-M, Color Quantization and Background Subtraction |
E-M, Mean shift,
Mixtures of Gaussians Adaptive
background mixture models for real-time tracking, by Stauffer and Grimson |
Forsyth
and E-M tutorial by Szeliski, Section 5.3 |
|
|
13.
10/14 |
Matching:
SIFT and RANSAC |
David G. Lowe, "Distinctive image
features from scale-invariant keypoints,"
International Journal of Computer Vision, 60, 2 (2004), pp. 91-110. |
|
Mosaicing |
|
14.
10/16 |
Geometric
transformations and mosaicing |
|
||
|
15.
10/21 |
Biological
Vision |
|
||
|
16.
10/23 |
Cameras,
perspective projection |
Projective
Geomery for Image Analysis by Mohr and Triggs |
|
|
|
17.
10/28 |
Projective
geometry |
|
Midterm |
|
|
18.
10/30 |
Stereo
geometry |
Slides,
Szeliski, 11-11.1.1 |
|
|
|
19.
11/4 |
Markov
Processes and Markov Random Fields |
|
|
|
|
20.
11/6 |
Graph cuts for segmentation, stereo and MRFs |
Interactive Graph Cuts for Optimal Boundary &
Region Segmentation of Objects in N-D images. |
|
|
|
21.
11/11 |
Sliding window detection |
Rapid object detection
using a boosted cascade of simple features by Viola and Jones |
|
|
|
22.
11/13 |
CNNs |
|
Graph cut stereo |
|
|
23.
11/18 |
Stereo
matching (continued): dynamic programming and graph cuts |
Szeliski, 11.3-11.5.1 Fast approximate energy minimization via graph cuts, by Boykov, Veksler, and Zabih |
|
|
|
23.
11/18 |
|
|
||
|
24.
11/20 |
Structure-from-motion
with perspective, the Essential matrix |
Szeliski,
7.2 through 7.2.1 |
|
|
|
25.
11/25 |
Classification:
Bag of Words |
Slides (from Andrew Zisserman) Text
(from Kristin Grauman) |
|
Bag of words classifier |
|
26.
12/2 |
Optical
Flow, corner detection, Motion Flow |
Handout
available from instructor |
|
|
|
27.
12/4 |
Deep
Learning and Classification |
|
||
|
28.
12/9 |
Fine-grained
classification |
|
|
|
|
29.
12/11 |
Conclusions |
|
||
|
12/15
8:00-10:00 |
FINAL |
|
|
|
