|
This course is intended for beginning
graduate students and
advanced undergraduates. We assume students have a rudimentary
understanding of linear algebra, calculus, and are able to program in
some type of structured language. There will be 4 homework assignments, not all equally weighted,
and a final project. Grading will be approximately 60% on the homework
assignments, and 40% on the final project. Secondary: 518 EE/CS Building
Meetings:
M W, 11:15-12:30pm, EE/CSci 3-111
Professor:
Paul Schrater
E-mail:
schrater AT umn DOT edu
Office:
Primary: S211 Elliott Hall,
Office hours:
Mon 12:30-1:30pm or by appointment
Teaching Assistant:
Esha Nerurkar, nerurkar AT cs DOT umn DOT edu
Office hours:
Wed 12:30-1:30 pm EE/CS 2-209
Final Project Assignment: Your final project will involve one of the following
1) Simulation or experiments. For example, implemented a computer vision system for a particular application, e.g. motion estimation, shape estimation, tracking, etc.
2) Literature survey (with critical evaluation) on a given topic.
3) Theoretical work (detailed derivations, extensions of existing work, etc)
In all cases, the work should be written up as a 10-15 page paper. More difficult projects will get better grades if sucessfully completed. You may work in groups of 1-4 students. However, the content must be sufficient for the size of the group. You will be evaluated in terms of the care with which you set up and thought through the goals and implementation, and in terms of the competence of the execution.
Every paper should have the following:
Introduction- Regardless of form, the write up should include a survey of related work (from the primary computer vision literature, e.g. journal and conference papers). The survey will introduce the topic and help explain the choices you made developing your work. For example, if you implement a tracking algorithm from a particular research paper, give an overview of tracking, describe the basic set of approaches to the tracking problem, and explain both the pros and cons of the algorithm by referring to related work. For a literature survey, this section should be a topic overview, without going into particular details.
Project description- Main section that explains and describes methods and theory used in project. For a literature review, I prefer directed reviews - the review should answer a question like - Are model-based or image-based methods better for object recognition. The main section should lay out arguments and evidence for possible answers to the question.
Simulations, experiments and theoretical work should also have:
Results- Figures, plots, tables, images, etc, with text to describe outcomes of the project.
The project schedule is:
March 9: Topic selection. One or two pages explaining the project
with a list of references.
April 6: Partial report (3 to 5 pages).
May 11: Final report (10 to 15 pages, single spaced).
Cheating and Plagarism
The homework and programming assignments
must not be the result of
cooperative work. Each student
must work individually in order to understand the material in depth.
You may discuss the issues but by
no means, copy the homework or the programming assignment of somebody
else. All work in the projects
and the programming assignment must properly cite sources. For example,
if you quote a source in your
project, you must include the quotation in quotation marks and clearly
indicate the source of the quotation.
Any student caught cheating will receive an F as a class grade
and the University policies for cheating
and plagiarism will be followed.
| Week | Mon/Wed | Suggested Readings | Notes | Assignment |
| 1 (1/21) |
Introduction |
Course Syllabus, Matlab Primer Chap 1, 2 |
Lecnotes1 |
HW1
due 2/13 SolnKey1 Features2D.mat Features3D.mat |
| 2 (1/26-28) |
Camera Models Camera Calib/Radiometry |
Chaps 3.1.1,3.2,4 |
Lecnotes2 Lecnotes3 |
|
| 3 (2/2-2/4) |
Radiometry/Image formation Shape from Shading |
Chap 4,5,6 | Lecnotes4 LecNotes5 |
HW2 due 3/4 |
| 4
(2/9-11) |
Representing Measuring Color/ Reflectance estimation |
Chap 6 |
LecNotes6 | |
| 5
(2/16-2/18) |
Linear Filters/ Linear Filters and image representation Edge detection |
Chap 7 &8 | LecNotes7 | |
| 6 (2/23-2/25) |
Edge detection/Texture | Chap 8 Freeman paper |
LecNotes8 | HW3 due 3/30 |
| 7 (3/2-3/4) |
Texture/Segmentation | Chap 9 |
LecNotes9 LecNotes10 |
|
| 8 (3/9-3/11) |
||||
| 10
(3/23-25) |
Segmentation by Clustering | Chap 14 |
LecNotes10 LecNotes11 |
|
| 11 (3/30-4/1) |
Segmentation by Fitting |
Chap 15 Chap16 |
LecNotes12 |
|
| 12 (4/6-8) |
Multiple-view geometry |
Chap 10,11, parts of 13 | Stereo |
|
| 13 (4/13-15) |
Multiple-view geometry/ Good Features for geometric analysis: SIFT |
Chap 13 and supplemental reading | Features |
HW4 DUE April 27th Extra credit tutorial and code automatic.zip |
| 14 (4/20-22) |
Motion Estimation/Tracking | Chap 13,17 | MotionEstTracking |
|
| 15 (4/27-29) |
Recognition |
Chap 18 | RecognitionI |
|
| 16 (5/4-6) | Finding images in libraries | Chap 22,23, 25 | ShortCourseNotesEdited.pdf |