Instructor:
Prof. Dimitris Samaras
Fall 2018: Tue-Thu 5:30 – 6:50 in Javits 103 Computer Science
|
The
aims of this course are to provide an understanding of the fundamentals of
Computer Vision and to give a glimpse in the state-of-the-art, at a moment
when the field is achieving "critical mass" and has significant
commercial applications. Apart from basic theory we will look at applications
of Computer Vision in Robotics, Graphics and Medicine. Topics in this course:
|
|
|
|
1.
Image
Formation
Basic facts about light Anatomy of a camera Matting 2.
Image Noise Convolution Image Pyramids 3.
Image
Features
Scale Orientation 4.
Model Fitting
Deformation RANSAC 5.
Perspective
Projection Homogeneous Coordinates Image Warping, Mosaics 6.
Object
Recognition Object
representation PCA for Image Patches Classifiers Object
Categories 7.
Deep Learning
Convolutional Neural Networks Architectures Applications |
8.
Deep Learning
Practice Pre-Training Data Augmentation 9.
Multiple View
Geometry 3D Range Scanning 10.
Illumination Shading, Shadows, Reflectance properties
11.
Deep
Generative Models Autoencoders, VAEs, Generative Adversarial Networks 12.
Motion Motion Capture Tracking in 2D and 3D Recurrent
Neural Networks Action Recognition 13. Segmentation Grouping, SuperPixels Nearest
Neighbors UNET, Semantic
Segmentation 14.
Big Data Annotated
Data Sets Crowdsourcing Weakly
Supervised and Unsupervised
Learning |
|
This
course is intended for graduate students with interests in all areas of Visual Computing
and Machine Learning, such as Computer Vision, Computer Graphics,
Visualization, Biomedical Imaging, Robotics, Virtual Reality, Computational
Geometry, Optimization, Deep Learning, HCI. Prerequisites include a foundation
in Linear Algebra and Calculus, and the ability to program. We will be
programming in Python (OpenCV, NumPy,
SciKit).
There will be homeworks,
a midterm and a final. Homeworks will be 45%, the midterm
20%, and the final 35%. Weights are approximate and subject to change. You are
expected to do homeworks (4 or 5) by yourselves.
Even if you discuss them with your classmates, you should turn in your own code
and write-up. Do not share your code! There will be 3 free late dates for
the semester. After that there will be 10% penalty per day.
· You can do a
project instead of the final. Projects will be done in up-to 2 people teams,
and will require a significant programming and documentation effort. This
will probably be much more work than studying for the final. Two people
projects will be scaled accordingly.
Midterm
1 date: Oct 18th 2018
Final date: Dec 13th 2018. Projects due Dec 18th 2018.
You can have one sheet of
paper with notes in the exams.
Computer
Vision: Algorithms and Applications by Richard Szeliski
(2010) Main text, available online.
Computer
Vision: A Modern Approach by David Forsyth and Jean Ponce (2012)
Computer Vision: Models, Learning, and Inference by
S. Prince, Cambridge Univ. Press, 2012
Introductory
Techniques for 3-D Computer Vision by E. Trucco and
A. Verri, (1998)
Readings
from these books and notes for all topics will be posted on blackboard
Don't
cheat. Cheating on anything will be dealt with as academic misconduct and
handled accordingly. I will not spend a lot of time trying to decide if you
actually cheated. If I think cheating might have occurred, then evidence will
be forwarded to the University's Academic Judiciary and they will decide. If
cheating has occurred, an F grade will be awarded. Discussion of assignments is
acceptable, but you must do your own work. Near duplicate assignments will be
considered cheating unless the assignment was restrictive enough to justify
such similarities in independent work. Just think of it that way: Cheating
impedes learning and having fun. The labs are meant to give you an opportunity
to really understand the class material. If you don't do the lab yourself, you
are likely to fail the exams. Please also note that opportunity makes thieves:
It is your responsibility to protect your work and to ensure that it is not
turned in by anyone else. No excuses! The University has a relevant policy:
“Each
student must pursue his or her academic goals honestly and be personally
accountable for all submitted work. Representing another person's work as your
own is always wrong. Any suspected instance academic dishonesty will be
reported to the Academic Judiciary. For more comprehensive information on
academic integrity, including categories of academic dishonesty, refer to the
academic judiciary website at http://www.stonybrook.edu/uaa/academicjudiciary/
If
you have a physical, psychological, medical or learning disability that may
impact on your ability to carry out assigned course work, I would urge that you
contact the staff in the Disabled Student Services office (DSS), Room 133
Humanities, 632-6748/TDD. DSS will review your concerns and determine, with
you, what accommodations are necessary and appropriate. All information and
documentation of disability is confidential.
· D. Samaras, Email:
samaras@cs.sunysb.edu
Office Hours:
Tue., Thu 4 - 5pm to 3.30, or by appointment, in room NCS 263
· TA: Fan Wang, Email:
fanwang1@cs.stonybrook.edu
Office Hours: Mon.
11:00 - 12:00pm, Wed. 3:00 - 4:00pm in room NCS 140