Announcements:
• [11.23.12] There will be a PS4 night session November 27, 6-8 pm at the Huang common area, along with a Google Hangouts session (cs231a2012@gmail.com).
• [11.13.12] PS4 posted.
Instructor: Prof. Fei-Fei Li
Office: Room 246, Gates Building
Phone: (650) 725-3860
Office hours: Tues 3:30-4:30
Course Team Email: cs231a-aut1213-staff@lists.stanford.edu
Important: Please use the Piazza for all questions related to lectures, problem sets or projects. *ONLY* email the Course Team Email when absolutely necessary such as for personal questions. Class/homework/project questions will be answered FASTER if asked on the Piazza.
Not registered through Axess? Sign up to the guest course mailing list to receive latest updates about CS231A: cs231a-aut1213-guests
Course Assistants:
Jonathan Krause
Office hours: Mon 4:30-5:30 pm, Wed 2-3 pm
Location: Gates 26
Vignesh Ramanathan
Office hours: Wed 3-4 pm
Location: Gates 26
Zixuan Wang
Office hours: Fri 3:15-5:15 pm
Location: Gates 24
Kevin Wong
Office hours: Wed 5-7 pm
Location: Gates 26
Jinchao Ye
Office hours: Thurs 10:30am-12:30pm
Location: Gates 26
Class Time and Location:
Lectures: Tues/Thur 2:15-3:30 pm, NVIDIA Auditorium
TA Sections: Fri 2:15-3:05 pm, NVIDIA Auditorium
Course Description:
An introduction to the concepts and applications of computer vision. Topics include: cameras and projection models, low-level image processing methods such as filtering and edge detection; mid-level vision topics such as segmentation and clustering; shape reconstruction from stereo, as well as high-level vision tasks such as object recognition, scene recognition, face detection and human motion categorization.
Grading Policy:
Problem Sets: 40%
• PS0: 4%
• PS1: 9%
• PS2: 9%
• PS3: 9%
• PS4: 9%
Midterm exam: 20%
Final project: 40% (please click here for detailed instructions)
Late policy:
• 5 free late days for PS only (not course project)– use them in your ways;
• After you have finished using all of your late days, there is a 25% off per day late penalty;
• No submission is accepted after 3 late days per PS.
• Explicitly mark the number of late days you use on an assignment when you are using them. Failure to do so will result in the maximum number of late days (3) being used;
Assignment Submission:
All assignments are due at the beginning of class. Please submit your assignments as hardcopy. If you cannot submit in class, write down the date and time of submission as well as the number of late days used for that problem set, and leave it in the CS231A submission cabinet near the east entrance of Gates. It is an honor code violation to write down the wrong time.
SCPD Students: Please email your solutions to cs231a-aut1213-staff@lists.stanford.edu and cc scpd-distribution@lists.stanford.edu. Write "Problem Set PID Submission" on the Subject of the email, where PID is the problem set number (1/2/3/4). Each homework should be emailed as a SINGLE pdf file. Additionally, all SCPD students should also include the Homework Routing Form available here. This should appear as the very first page of your Homework solutions.
Late policy: Each student will have a total of five free late (calendar) days to use for the assignments. Once these late days are exhausted, any assignments turned in late will be penalized 25% per late day. However, no assignment will be accepted more than three days after its due date. Each 24 hours or part thereof that an assignment is late uses up one full late day. Late days cannot be used for any part of the final project.
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.
Textbook:
No required textbooks; Suggested textbooks:
Computer Vision: Algorithms and Applications, by Richard Szeliski, Springer, 2010.
Learning OpenCV, by Gary Bradski & Adrian Kaehler, O'Reilly Media, 2008.
Multiple View Geometry in Computer Vision, 2nd Edition, by R. Hartley, and A. Zisserman, Cambridge University Press, 2004.
Computer Vision: A Modern Approach, by D.A. Forsyth and J. Ponce, Prentice Hall, 2002.
Pattern Classification (2nd Edition), by R.O. Duda, P.E. Hart, and D.G. Stork, Wiley-Interscience, 2000.