CS 117: Project in Computer Vision

Instructor: Charless Fowlkes
Lectures: TuTh 3:30-5pm, ICS 253
Office Hours: W 1-2pm, Th 5-6pm, or by appointment

Students will undertake construction of a computer vision system. This year's topic will be automatically building 3D models from photographs.

The suggested textbook is Introductory Techniques for 3D Computer Vision, by Trucco and Verri. We will not follow it closely but it is useful as an alternate presentaiton of the material we will discuss in class. Relevant chapters are 2-8.

• Week 1 : Intro, MATLAB tutorial
• Week 2 : Cameras, images, 3D transformations, review of linear algebra
• Week 3 : Triangulation, Calibration
• Week 4 : Correspondence
• Week 5 : Dense Stereo
• Week 6 : Structured Light Scanning
• Week 7 : Mesh Generation and Alignment
• Week 8 : Other cues to depth
• Week 9 : Applications
• Week 10 : Final Project Presentations

The grading for this class will be based on homeworks (50%) and final project proposal, presentation and writeup (50%)

There will be approximately 6 assignments during the quarter. Each is due by 11:59pm on the specified due date. Work turned in late will not be graded so please just hand in whatever you have completed. Assignments should be uploaded to the appropriate EEE Dropbox. 

Extra credit: if you submit an assignment 24 hours early, you will automatically get 10% extra credit on the assignment (e.g. if the assignment is worth 100 points you will get 10 pts extra credit).  

You will be required to use MATLAB for some of your homework problems. MATLAB is available on about 34 machines in the CS 364 lab - the machines are in 3 rows front of the lab assistant's desk and to the left of this desk as you face away from it.

You are asked to be respectful of your student colleagues and instructor in class, not being disruptive or otherwise distracting others in the classroom. This includes turning off cell-phones and not using your laptops during class.

Academic honesty is taken seriously. For homework problems or programming assignments you are allowed to discuss the problems or assignments verbally with other class members, but under no circumstances can you look at or copy anyone else's written solutions or code relating to homework problems or programming assignments. All problem solutions submitted must be material you have personally written during this quarter. Failure to adhere to this policy can result in a student receiving a failing grade in the class. It is the responsibility of each student to be familiar with UCI's current academic honesty policies. Please take the time to read the current UCI Senate Academic Honesty Policies (in Spring Schedule of Classes, a few pages from the end). Also you may want to look at the ICS Department's policies on academic honesty .