UWB and UW Seal

Homework assignments
Lecture materials
Wikipedia content


Message board
Assignment dropbox

UWB Information Technologies
UWB Quantitative Skills Center
UWB Writing & Communication Center

CSS 587 – Advanced Topics in Computer Vision – Spring 2018

University of Washington, Bothell – School of STEM – Computing & Software Systems


Professor:                   Dr. Clark F. Olson                  Class:                 T/Th 5:45-7:45 pm, UW2 - 340

                                    Office: UW1 – 271B              Office Hours:    T/Th 4:30-5:30 pm

                                    Phone: (425) 352-5288                                      or by appointment

                                    E-mail: cfolson@uw.edu                   


Lab: UW1-310           Lab tutor schedule – see https://www.uwb.edu/qsc/schedule/css



This is a project-oriented course to introduce students to computer vision research. An overview of computer vision and discussion of fundamental techniques will be presented. Students are expected to read and understand current research papers. Teams of students will implement (and potentially extend) computer vision algorithms using an open source computer vision library (OpenCV). Each team will lead a discussion on the topic of their project. The projects will culminate with demonstrations at the end of the quarter.


Topics and Learning Objectives

Students will:

  • Demonstrate understanding of fundamental computer vision techniques
  • Read, understand, and lead discussion on current research in computer vision
  • Use and extend established open-source computer vision libraries
  • Collaborate with others in developing computer vision software
  • Use good software engineering practices in the implementation of computer vision algorithms 

Textbook (optional, but recommended)

  • Adrian Kaehler and Gary Bradski, Learning OpenCV 3: Computer Vision in C++ with the OpenCV Library, O’Reilly Media, 2017.

You might also consider:

  • Robert Laganière, OpenCV 3 Computer Vision Application Programming Cookbook, Packt Publishing, 2017.

·         Daniel Lelis Baggio, et al., Mastering OpenCV3, Packt Publishing, 2017.

·         Prateek Joshi, David Millan Escriva, and Vinicius Godoy, OpenCV By Example, Packt Publishing, 2016.


Reference books

  • Linda G. Shapiro and George C. Stockman, Computer Vision, Prentice Hall, 2001.


  • David Forsyth and Jean Ponce, Computer Vision: A Modern Approach, Prentice Hall, 2nd edition, 2011.               http://luthuli.cs.uiuc.edu/~daf/book/book.html (1st edition)
  • Richard Szeliski, Computer Vision: Algorithms and Applications, Spring, 2010.



Assignments / Grading

Students will complete three introductory assignments and a substantial course project. They will lead discussion in their topic area and present their work to the class. A student who achieves 80% of the possible points should expect to receive a successful grade in the course.


Assignments: 25%      Project: 45%   Presentations: 20%     Participation: 10%


Class policies

Assignments are due prior to class on the due date. The submission site will mark assignments as late promptly at the start of class. Assignments (except presentations and demonstrations) can be turned in up to 5 days late (including weekends) with a 10% grade reduction per day. Introductory assignments are to be completed independently. Please be very careful to adhere to the student code of conduct:



Message board



Assignment dropbox



Tentative Schedule (subject to change)



Suggested reading


Mar 26-28

Introduction, OpenCV

Skim early chapters 1-6

Program 0 “due”

Apr 3-5

Fundamental algorithms:

 Filtering, edges, primitives

Chapter 10, 12

 (except segmentation)


Program 1 due

Apr 10-12

Fundamental algorithms:

  Features, motion

Chapter 16 (through 511)

Chapter 17


Program 2 due

Apr 17-19

No class on Monday

Fundamental algorithms: SIFT


Chapter 16 (though end)


Program 3 due

Apr 24-26

Panoramas, Photosynth

Object recognition


Chapter 13, web


Project proposal

May 1-3

Fundamental algorithms:

  Segmentation, stereo

Chapter 12(segmentation)

Chapter 18, 19 (skim)


May 8-10

Design reviews


Project design

May 15-17

Misc. topics such as mapping, image databases, classification



May 22-24

Topic discussions

Research papers


May 29-31

Topic discussions

Research papers


June 7



Project due


See also: School of STEM Course Policies