Introduction to Computer Vision CS 231A - Winter 2013/2014

Instructor: Prof. Silvio Savarese
Office hours: TBD
Webpage: http://cvgl.stanford.edu/silvio/

Classroom: Nvidia Auditorium
Time: T Th 11:00am-12:15pm

TAs :
Kevin Wong
Office Hours: TBD
David Held
Office Hours: TBD
Jiayuan (Mark) Ma
Office Hours: TBD
Chris Lengerich
Office Hours: TBD

 

 

Course schedule :: Announcements & Resources

 

Course Description
The course is an introduction to 2D and 3D computer vision. Topics include: cameras models, geometry of multiple views; shape reconstruction methods from visual cues: stereo, shading, shadows, contours; low-level image processing methodologies (feature detection and description) and mid-level vision techniques (segmentation and clustering); high-level vision problems: object detection, image classification, scene understanding and target tracking.

Textbooks
No required textbooks; Suggested textbooks:
- R. Szeliski. Computer Vision: Algorithms and Applications. Springer, 2011.
- D. A. Forsyth and J. Ponce. Computer Vision: A Modern Approach (2nd Edition). Prentice Hall, 2011.
- R. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Academic Press, 2002.
- D. Hoiem and S. Savarese. Representations and Techniques for 3D Object Recognition and Scene Interpretation, Synthesis lecture on Artificial Intelligence and Machine Learning. Morgan Claypool Publishers, 2011

- Learning OpenCV, by Gary Bradski & Adrian Kaehler, O'Reilly Media, 2008.

Prerequisites
Computer Vision is a field that spans multiple disciplines and draws links to several traditional fields such as image processing, optics, probability, and statistics. Students who have done well in previous years in general have solid knowledge of linear algebra, probability, statistics and machine learning, as well as decent programming skills. Though not an absolute requirement, it is encouraged and preferred that you have at least taken either CS221 or CS229, or have equivalent knowledge.

Course Assignments
4 problem set
1 mid-term exam
1 project
 
Grading Policy:
Problem Sets: 40%
PS1: 10%
PS2: 10%
PS3: 10%
PS4: 10%
Midterm exam: 15%
Final project: 40% (progress mid-term report (%5), final report (25%), presentation (10%))
Class participation: 5%
 
Note: class participation and final project presentation are waived for SCPD students.
 
Project late policy: 25% if one day late; 50% if two days late; zero credit if more than two days

- A "48-hours one-time late submission bonus" is available; that is, you can use this bonus to submit your HW late after at  most 48 hours. This is one time bonus: After you use your bonus, you must adhere to the standard late submission policy. No exceptions will be made.
- No "late submission bonus" is allowed when submitting your mid-term exam and project.
 
 
MIDTERM EXAM & PROJECT Information:
Mid Term Exam
- Take home, 48 hours
- For release and due dates see class schedule
- 0% grade after deadline
- No collaborative solutions are allowed
 
Project Proposal Format
- max 4 pages;
- 3 sections:
  * title and authors
  * sec 1. intro: problem you want to solve and why
  * sec 2. technical part: how do you propose to solve it?
  * sec 3. milestones (dates and sub-goals)
  * references
- final format: pdf, please!
 
Project Progress (mid-term) Report Format
- max 4 pages;
- 3 sections:
  * title and authors
  * sec 1. intro: problem you want to solve and why
  * sec 2. technical part: how do you propose to solve it?
  * sec 3. milestones achieved so far
  * sec 4. remaining milestones (dates and sub-goals)
  * references
- final format: pdf, please!
 
Project Final Report Format
- Max 10 pages;
- Title and authors
- Abstract: short summary of the project with main results
- 6 sections:
  * Sec 1. Introduction: introduce the problem you want to solve, expain why it is important to solve it; and indicate the method
    you used to solve it. add a concept figure showing the overall idea behind the method you are presenting.
  * Sec 2.1. Review of previous work (i.e. previous methods that have explored a similar problem)
  * Sec 2.2. Say why your method is better than previous work; and/or summarize the key main contributions of your work;
  * Sec 3.1: Technical part: Summary of the technical solution
  * Sec 3.2: Technical part: Details of the technical solution; you may want to decompose this section into several subsections;
    add figures to help your explanation.
  * Sec 4: Experiments: present here experimental results of the method you have implemented with plots, graphs, images
    and visualizations.
  * Sec 5: Conclusions: what's the take home message?
  * Sec 6: References
- Final format: pdf, please!

You can look at one of the recent instructor publications (such as this) as an example.

Evaluation:
- Your project report will be evaluated based on the quality of the writing, the clarity of your technical explanation and, overall,  how well you get your message across. If you follow the structure above, you'll have good chances to do a good job. :)
 
Project Source Code
There is no need to attach a print out of the source codes to the manuscript. Final source codes of your working program need to be collected into a unique (zipped) file; this file is due on the project submission deadline date and it is supposed to be sent to the grader as indicated by email.
 
Project Presentation in Class
- The presentation must be N minutes long (N will be decided based on how many projects are to be presented). You will present for N-2 minutes. There will be 2 minutes for questions after the  presentation. If your presentation lasts more than N minutes, it will be stopped. So please make sure the presentation doesn't  go over N minutes.

Presentation format:
- The idea is to turn your project report (as discussed above) into slides; thus, your presentation will need to include slides
  covering:
  * Introduction: introduce the problem you want to solve, explain why it is important to solve it; and indicate the method you
    used to solve it.
  * Review of previous work (i.e. previous methods that have explored a similar problem)
  * Why your method is better than previous work; and/or explain the key main contributions of your work;
  * Technical part: Summary of the technical solution, followed by the details of the technical solution;
  * Experiments: present here experimental results of the method you have implemented with plots, graphs, images and visualizations.
  * Conclusions: what's the take home message?

Evaluation:
- Your team will be evaluated based on the clarity of the presentation, quality of the slides, how well you get your message across, and how well you handle the questions at the end. Note that the presentation can still contain ongoing/preliminary results; final results may be included in the final report.