CSE 327: Fundamentals of Computer Vision

(Undergraduate Course)

Fall 2024

Basic Information:

·       Lecture info: Mon/Wed 3:30pm – 4:50pm, Frey Hall 205

·       Instructor: Haibin Ling (haibin.ling AT stonybrook.edu), NCS 147

·       Office hour: Wed 9:30am-11:30am or by appointment

·       TAs:

o   Ming Lin, ming.lin@stonybrook.edu, office hour: Mon 9:30-11:30am 

o   Shivasankaran Vanaja Pandi, shivasankaran.vanajapandi@stonybrook.edu, office hour: Tue 9-11am

o   Naman Joshi, namjoshi@cs.stonybrook.edu, office hour: Thu 12-2pm

o   Rushil Nilesh Shah, rushshah@cs.stonybrook.edu, office hour: Mon 3-5pm

·       Syllabus: PDF

Useful Links:

·       Main textbook: Computer Vision: Algorithms and Applications, Richard Szeliski, 2nd ed., 2022.

·       Computer Vision: A Modern Approach, David Forsyth and Jean Ponce, 2nd ed., 2012.

·       Multiple View Geometry in Computer Vision, Richard Hartley and Andrew Zisserman, 2nd ed., 2004.

·       Pattern Recognition and Machine Learning, Christopher M. Bishop, 2006.

·       Monocular Model-Based 3D Tracking of Rigid Objects: A Survey, Vincent Lepetit, Pascal Fua, 2005.

 

Course Schedule (tentative, will be actively updated during semester)

Date

Topics

Materials

Week 1

8/26

8/28

·       Introduction

o   Topics, history, applications, related fields

o   Course logistics

·       Image Formation

o   Camera anatomy

o   Anatomy of cameras

·       Szeliski 1.1, 1.2

·       Szeliski 2.1, 2.2, 2.2, 2.3

Week 2

9/4

·       Review of math and coding (by Kalyan Garigapati)

o   Basic math concept review

o   Tutorial to Google Colab  

Week 3

9/9

9/11

·       Image Formation

o   Photometric image formation

·       Image Processing

o   Point operations

o   Filters, convolution

o   Fourier transformation

·       Quiz 1 (9/11)

·       Szeliski 2.1, 2.2, 2.2, 2.3

·       Szeliski 3.1-3.4

 

Week 4

9/16

9/18

·       Image Processing

o   Image smoothing

o   Histogram equalization

o   Image pyramid

o   Geometric transform

o   Image gradient

o   Points, corners, edges

o   Scale and orientation

·       Szeliski 3.4, 3.5, 3.6

·       Szeliski 7.1, 7.2, 7.4, 7.4

 

 

Week 5

9/23

9/25

·       Model Fitting and Optimization

o   Line fitting, robust fitting

o   Hough transform

o   RANSAC

·       Szeliski 4.1, 4.2

·       Szeliski 7.4, 8.1

9/29

·       Homework 1 Due (11:59pm EST)

 

Week 6

9/30

10/2

·       Machine Learning Concepts

o   Supervised learning

o   Unsupervised learning

·       Quiz 2 (10/2)

Week 7

10/7

10/9

·       Elements of perspective geometry

o   Homogeneous coordinates

o   Camera geometry transformations

o   Epipolar geometry

·       Szeliski 5.5, 6.3

Week 8

10/16

·       Stereo

o   Stereo viewing

 

10/20

Homework 2 Due (11:59pm EST)

 

Week 9

10/21

10/23

·       Midterm (10/21)

·       Stereo

o   Stereo reconstruction

·       Szeliski 12.1, 12.2, 12.3, 12.4, 12.5, 12.6

·        

Week 10

10/28

11/30

·       Motion estimation and tracking

o   Translational alignment

o   Optical flow

·       Szeliski 9.1, 9.3

 

Week 11

11/4

11/6

·       Recognition

o   Instance recognition

o   Image classification (traditional methods)

·       Deep Learning

o   Deep neural networks

·       Szeliski 5.3, 5.4, 5.5, 6.2

·       Deep Learning, Goodfellow et al., 2016.

·       Deep Learning Tutorial, Stanford

 

11/10

Homework 3 Due (11:59pm EST)

 

Week 12

11/11

11/13

 

·       Deep Learning

o   Convolutional neural networks

o   Architecture

·       Deep Learning Practice

o   Training

o   Data augmentation

·       Szeliski 8.1, 8.2, 8.3

 

Week 13

11/18

11/20

·       Detection and segmentation

o   Traditional solution

o   Deep learning solutions

o   Semantic segmentation

 

·       Quiz 3 (11/18)

·       Szeliski 6.3, 6.4

·       End-to-End Object Detection with Transformers, Carion, et al., 2020

·       Segment Anything, Kirillov et al., 2023

11/24

Homework 4 Due (11:59pm EST)

 

Week 14

11/25

·       Vision Transformer

o   Transformer

o   Transformer in computer vision

 

·       Szeliski 5.5

 

Week 15

12/2

12/4

·       Video analytics

o   Video object tracking

o   Activity understanding

·       Guest lecture by Peiyao Wang (12/4)

o   Temporal Action Segmentation

·       Quiz 4 (12/4)

·       Szeliski 9.4

 

Week 16

12/9

·       Advanced topic

o   Generative models

·       Final review

 

12/10

Homework 5 Due (11:59pm EST)

 

12/16

Final Exam, 5:30-8:00pm, Frey Hall 205