CAP5415 – Fall 2019
Computer Vision (3 Credit Hours)
This introductory course will focus on traditional methods as well as modern approaches for computer vision. Approximately one-third of the lectures will deal the fundamentals of imaging geometry, camera models, feature detection and matching. Following this, two-thirds of the course will cover object detection and tracking, image classification, scene understanding, and deep learning with neural networks. At the end of this course, the student will have an indepth understanding of how computer vision works, design and implement computer vision algorithms, and pursue advanced topics in computer vision research.
There is no text book for this class.
Suggested reference books are
- Computer Vision by Richard Szeliski
- Pattern Classification by R. O. Duda, P. E. Hart, D. G. Stork
Pre-requisites: Basic Probability/Statistics, a good working knowledge of any programming language (python, matlab, C/C++, or Java), Linear algebra, Vector calculus.
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.
- Homework and programming assignments 35%
- Term project 35%
- Mid-Term Exam- 30% (tentative date: October 8, and November 26, 2019, in-class, written)
Students can use any programming language and platform of choice.
Students are free to discuss ideas and technical concepts. However, students must submit original work for all assignments, projects and exams, and abide by UCF Golden Rule.
- Lecture 1 – Introduction to Computer Vision (pdf)
- Lecture 2 – Basics of Matrix Vector Algebra (pdf)
- Lecture 3 – Camera Model (pdf)
- Lecture 4 – Edges (pdf)
- Lecture 5 – Features (pdf)
- Lecture 6 – Review with Examples (pdf)
- Lecture 7 – KLT Tracking (pdf)
- Lecture 8 – Feature Classification (pdf)
- Lecture 9 – Linear Machines (pdf)
- Lecture 10 – Support Vector Machines (pdf)
- Lecture 11 – Simple Neural Networks (pdf)
- Lecture 12 – Basic CNNs (pdf)
- Lecture 13 – CNN in Matrix Vector Notation (pdf)
- Lecture 14 – Auto Encoders (pdf)
- Lecture 15 – Generative Adversarial Networks (pdf)
- Lecture 16 – LSTMs (pdf)
- Lecture 17 – Structure From Motion (pdf)
CAP 5415 Term Project – Fall 2019
Final Project Project Report
Instructions for Final Project Report