CPSC 425 Computer Vision - Winter 2016/17
Term 2 (January – April, 2017)
Computer vision, broadly speaking, is a research field aimed to enable computers to process and interpret visual data, as sighted humans can.
It is one of the most exciting areas of research in computing science and among the fastest growing technologies in today’s industry. This course provides an introduction to the fundamental principles and applications of computer vision (see topics).
Prerequisite: All of MATH 200, MATH 221 and either (a) CPSC 221 or (b) all of CPSC 260, EECE 320.
Instructor: Ali Madooei (madooei [at] cs.ubc.ca). Office hour: Fridays 3:00-4:00 p.m., ICCS 237.
TA: Amon Ge (amon [at] cs.ubc.ca). Office hours: Mondays 2:00-3:30 p.m., ICCS X337
TA: Kai Wu (kaywu [at] ece.ubc.ca). Office hours: Thursdays 3:30-5:00 p.m., Demco Table 3.
TA: Moumita Roy (moumita [at] cs.ubc.ca).
TA: Mir Rayat Imtiaz Hossain (rayat137 [at] cs.ubc.ca)
Here is a rough schedule and tentative list of topics and readings (subject to change).
- Week 1 - Welcome & Introduction / Image as Function
- Week 2 & 3 - Image Processing (Linear Filtering, Convolution, etc). - Section 4.1 from textbook
- Week 4 - Filters as Templates - Sections 4.5, 4.6, 4.7
- Week 5 - Image Feature Detection (Edges & Corners) - Sections 5.1, 5.2, 5.3
- Week 6 - Texture & Colour - Sections 6.1, 6,3, and 3.1, 3.2, 3.3
- Week 7 - Midterm (Review and Exam)
- Week 8 - Mid-term break!
- Week 9 - Image Feature Description (SIFT) - Section 5.4
- Week 10 - Model Fitting (RANSAC, The Hough Transform) - Sections 10.1, 10.4
- Week 11 - Camera Models, Stereo Geometry - Sections 1.1.1, 1.1.3 and 7.1.1, 7.2.1
- Week 12 - Motion and Optical Flow - Sections 7.4, 7.6, and 10.6.1
- Week 13 - Clustering and Image Segmentation - Sections 6.2.2 and 9.3.1, 9.3.3, 9.4.2
- Week 14 - Learning and Image Classification - Sections 15.1, 15.2 and 16.1.3, 16.1.4
|First Day of Classes
||3 January (Tuesday)
||17 January (Tuesday)
|Drop with W Deadline
||10 February (Friday)
||[Tentatively] 16 February (Thursday)
|Last Day of Classes
||6 April (Thursday)
||TBA (between 10 and 28 April)
Tuesdays and Thursdays, 11:00am-12:20pm, DMP 110.
We will post the lecture materials here.
- Please use this link to enroll yourself.
There are seven assignments given throughout the term.
The first is a self-study tutorial introduction to Python for computer vision (that is not marked). The other five are handed in to be marked.
Each assignment has a specific due date and time which will be announced here (a tentative schedule is posted).
||No due date (but try to complete it by Jan. 12)
||Due on Jan. 24
||Due in Week 5
||Due in Week 8
||Due in Week 10
||Due in Week 12
||Due in Week 14
- All assignments are to be done individually.
- There are no extensions to an assignment due date. Assignments handed in later on the due date are penalized 20% of the total mark. A further penalty of 20% of the total mark is assessed for each additional day late. An assignment that is five or more days late is worth 0% and will not be marked.
- To get top marks, programs must not only work correctly, but also must be clearly documented and easily understood. The material you hand in, including figures, must be legible.
There will be one midterm and one final exam (see important dates).
The midterm is closed-book. For the final exam, you are allowed one (standard) 8.5 × 11 handwritten double-sided sheet of notes.
In-class (clicker questions): 5%
Midterm exam: 25%
Final exam: 45%
The instructor reserves the right to change this scheme (but does not anticipate using that right).
The course uses the following textbook, which is recommended (but not required):
D.A. Forsyth and J. Ponce, Computer Vision: A Modern Approach (2nd edition), Pearson, 2012.
Another useful textbook (which can be downloaded from http://szeliski.org/Book/) is:
R. Szeliski, Computer Vision: Algorithms and Applications, Springer, 2010.
Here is another one which can also be freely downloaded as a PDF from SpringeLink, through UBC Library (must login using CWL).
R. Klette. Concise Computer Vision: An Introduction into Theory and Algorithms, Springer, London, 2014.
The following textbooks are also on reserve in the reading room:
- S.J.D. Prince, Computer vision : models, learning, and inference, Cambridge University Press, 2012.
- R. Hartley and A. Zisserman, Multiple view geometry in computer vision (2nd edition), Cambridge University Press, 2003.
- R.O. Duda, P.E. Hart, and D.G. Stork, Pattern classification (2nd edition), Wiley, 2001.
- L. Shapiro, and G.C. Stockman, Computer vision. Prentice Hall, 2001.
- V.S. Nalwa, A guided tour of computer vision. Addison-Wesley, 1993.
To have marking of any assessment reviewed (except the final exam): Write a note detailing (all) your objections, including which questions you believe were marked inappropriately and why, and staple the note to the entire assignment/exam.
Submit this to the instructor. This must be done no later than two weeks from the date the assignment/exam was returned in class. The instructor will review the marking (generally with input from any TA involved in the original marking).
The decision of the instructor is final.
For the final exam, there will be a period to review the exam with the instructor to learn from it. For marking disputes, see UBC’s Review of Assigned Standing policy.
- Extenuating Circumstances – If any unforeseen and unavoidable circumstances (e.g. illness)
have affected your ability to meet a deadline (or attend an examination), you should inform
the instructor as soon as possible (appropriate documentation may be required evidence for your claim.
- A student missing the final exam must request academic concession from the office of their dean or director as soon as possible.
- Academic conduct - Each student is responsible for understanding and abiding by the University and Departmental policies on academic conduct. Specifically: