Computer Vision - CMPT 762, Spring 2020

When: (Tue 9:30-10:20) & (Thu 9:30-11:20)
Where: AQ 3153 (Tue) & RCB 8100 (Thu)

Instructor: Yasutaka Furukawa (furukawa-at-mark-sfu.ca)
Office hours: 3:30pm - 5:00pm Thursdays at TASC-I 8023

TA: Supriya Baswaraj Pandhre
walle
Schedule Projects
Piazza

Course Description

Computer vision is the process of automatically extracting information from images and video. This course covers imaging geometry (camera calibration, stereo, and panoramic image stitching), and algorithms for video surveillance (motion detection and tracking), segmentation and object recognition. Students with non-standard backgrounds (such as video art, or the use of imaging in physics and biology) are encouraged to contact the instructor.

Prerequisites: Solid background on linear algebra and coding experiences.

Grading

  • 6 coding assignments (ranging from 11% to 22% each)
  • The last 2 assignments can be replaced by one final project (worth the same points)
Students are encouraged to use MATLAB (with the Image Processing Toolkit) for the coding assignments. MATLAB is very easy to use and also makes the grading consistent. The grading is not relative. Based on the total points, we apply the following numeric-score to alphabet conversion rule to determine the final grades: A+ (>=95), A (>=90), A- (>=85), B+ (>=80), B (>=75), B- (>=70), C+ (>=65), C (>=60), C- (>=55), D (>=50).
The final project can be of any programming language. If you believe that the grading has an error, please report the error to the instructor (not the TAs) for correction within 2 weeks from the grade releasing period.

Late Policy and Mercy Rule

For a late submission, penalty of 20% score reduction per 12 hours is applied. If one submits an assignment within 12 hours after the deadline, the score becomes 80%. Within 24 hours, 60%, and so on.

One can use 5 free late-days at total. For example, one can use two late-days for project 2 and three late-days for project 5. When you submit your assignment, please include at the top of the write-up (or right after the title), how many free late-days you want to use. You cannot later change the number of late-days retrospectively. You cannot split 5 late-days in the unit of hours. It is in an increment of days for each project. You cannot use free late-days for the final deadline (hw6 or final project) so as not to delay the final grade upload.

Textbook

There is no required textbook for the course. However, the course material closely follows a free online textbook Computer Vision: Algorithms and Applications by Richard Szeliski for the most lectures.

Announcement, Questions and Discussion

We will use Piazza for announcement, questions and discussion. Here is the link. It is your responsibility to read all the posts on Piazza. Important announcements will be given there. Please register.

Academic Integrity

You are encouraged to talk about and discuss coding assignments and projects with your class-mates. You are allowed to use existing code/library (e.g., optimization library or vector calculus library), in which case, you have to explicitly describe it in your report. Besides the above case, every single line of code must be written by you, and you are not allowed to copy from other sources. Writing the code by exactly or closely following existing code is not technically copy-and-paste, but is also considered to be copy-and-paste. Use your fair judgement. You know what is good and bad. When in doubt, consult the instructor. You are expected to maintain the highest standards of academic integrity and refrain from the forms of misconduct.

Acknowledgements

Huge thanks to Ioannis Gkioulekas, Kris Kitani, and Svetlana Lazebnik for sharing the course slides and coding assignments.