Introduction to Computer Vision, Fall 2021

Course number: CSE 527

Meets: Tuesday/Thursday 6:30-7:50pm

Location: Light Engineering Lab 102 (in-person) + Zoom (online)

Website: http://michaelryoo.com/course/cse527/ 

Instructor: Michael S. Ryoo

Email: mryoo "at" cs.stonybrook.edu

Office: NCS 231

Office hours: Thursdays 10-11am, virtually

Course description:

Computer Vision is the study of enabling machines to "see" the visual world (i.e., understand images and videos). In this course, the students will learn fundamental computer vision algorithms and have opportunities to implement them. Further, we will be discussing more recent state-of-the-art visual representation learning approaches.

The topics to cover include:

• Basics

• Features and filters
• Edges, Texture, Color
• Grouping and fitting
• Object recognition
• Motion and tracking
• Action recognition

• Geometry

• Perspective Projection
• Multiple View Geometry

• Visual Representation Learning

• Convolutional neural networks
• Generative models
• Visual attention mechanisms
• Transformers
• Indirect representations

Textbooks:

Computer Vision: Algorithms and Applications by Richard Szeliski

Computer Vision: A Modern Approach by David Forsyth and Jean Ponce

Prerequisites:

Prerequisites include a foundation in Linear Algebra and Calculus, and the ability to program. We will be programming in Python (OpenCV, NumPy, SciKit).

Schedule:

Course requirements and grading:

Programming assignments (45%): 3 homeworks

Final project (25%): team project with presentations and reports (could be replaced with +2 programming assignments)

Midterm exam (10%)

Final exam (20%)

Acknowledgement:

This course has been inspired by the Computer Vision course by Kristen Grauman (UT), Devi Parikh (Gatech), Yong Jae Lee (UC Davis), and Dimitris Samaras (Stony Brook)