CAP5415-Computer Vision (FALL 2017)
Class time: Tuesday/Thursday 3-4.15 pm
Class location: HEC 117
Office hours: Tuesday/Thursday 4.30-5.30 pm
The course is introductory level computer vision course, suitable for graduate students. It will cover the basic topics of computer vision, and introduce some fundamental approaches for computer vision research:
Basic Probability/Statistics, a good working knowledge of any programming language (python, matlab, C/C++, or Java), Linear algebra, Vector calculus.
- Image Filtering, Edge Detection, Interest Point Detectors
- Motion and Optical Flow
- Object Detection and Tracking
- Region/Boundary Segmentation
- Shape Analysis and Statistical Shape Models
- Deep Learning for Computer Vision
- Imaging Geometry, Camera Modeling and Calibration
GRADING:Assignments and the term project should include explanatory/clear comments as well as a short report describing the approach, detailed analysis, and discussion/conclusion.
RECOMMENDED BOOKS (optional)
- 3 Programming assignments 30% (10% each)
- Term project 40%
- Mid-Term Exam 30% (tentative date: Second week of November 2017, in-class, written)
- Simon Prince, Computer Vision: Models, Learning, and Interface, Cambridge University Press,
- Mubarak Shah, Fundamentals of Computer Vision,
- Richard Szeliski, Computer Vision: Algorithms and Applications, Springer, 2010 (online draft),
- Forsyth and Ponce, Computer Vision: A Modern Approach, Prentice Hall, 2002,
- Palmer, Vision Science, MIT Press, 1999,
- Duda, Hart and Stork, Pattern Classification (2nd Edition), Wiley, 2000,
- Koller and Friedman, Probabilistic Graphical Models: Principles and Techniques, MIT Press, 2009,
- Strang, Gilbert. Linear Algebra and Its Applications 2/e, Academic Press, 1980.
Python will be main programming environment for the assignments. Following book (Python programming samples for computer viion tasks) is freely available.
Python for Computer Vision
For mini-projects, Processing programming language can be used too (strongly encoured for android application development)
Collaboration on assignments is encouraged at the level of sharing ideas and technical conversation only. Please write your own code. Students are expected to abide by UCF Golden Rule.
- KLT Object Tracking with Python
- Interactive Segmentation of Images (Thresholding) as Smart Phone Application (with Processing language)
- Canny Edge Detection as Smart Phone Application (with Processing language)
- Locally Affine Motion Model for Image Registration Application in 3D (C/C++ or Python Implementation only)
- 3D Graph-Cut Segmentation
- 2D Conditional Random Field based image segmentation
- Action Recognition (sports) with Fisher Vectors
- Image Stiching for Smart Phone Applications
- Real Time Face Detection for Android Applications
- 3D Edge Detection for Surface Reconstruction
- Anisotropic Diffusion Filtering (Perona/Malik)
- SIFT-Flow for image registration (See: SIFT-flow paper)
- Deep Learning Based Object Recognition
- Deep Learning Based Object Tracking in Videos
- Deep Learning Based Activity Recognition
- Deep Learning for Image/Video Segmentation
| Mailing address:
Dr. Ulas Bagci
Center for Research in Computer Vision (CRCV)
4328 Scorpius Street, HEC 221, UCF
Orlando, Florida 32816, USA.
Last updated November, 2017 by Ulas Bagci.