CSE 327: Fundamentals of Computer Vision

Fall 2022

Basic Information:

Lecture info: Mon/Wed 6:05pm - 7:25pm, EARTH & SPACE 079
Instructor: Prof. Haibin Ling, haibin.ling AT stonybrook.edu
Office hour: Tue 2:30pm-4:30pm or by appointment
TAs:
- Zhilin Zou, zhilin.zou AT stonybrook.edu, office hour: Thu 4-5pm
- Ajithkumar Shanmugam, ajshanmugam AT cs.stonybrook.edu, office hour: Tue 4-5pm
- TA office hour will be hold at Old Computer Science 2126.
Syllabus: PDF

Useful Links:

Computer Vision: Algorithms and Applications, Richard Szeliski, 2nd ed., 2021.
Computer Vision: Models, Learning, and Inference, Simon J.D. Prince, 2012.
Pattern Recognition and Machine Learning, Christopher M. Bishop.

Date	Lecture Topics (NOTE: the schedule is Tentative and upto frequent change)	Materials (for references)
Week 1 8/22 8/24	General introuction Background, topics, applications, related fields Course logistics Image formation basics Camera anatomy Baisc facts about light	Szeliski 1.1, 1.2 Szeliski 2.1, 2.2, 2.3
Week 2 8/29 8/31	Filtering and edges Point operations Filters, convolution, Fourier transforms	Szeliski 3.1 (point operator), 3.2 (linear filter), 3.3 (neighbor operators), 3.4 (Fourier) Correlation and convoluation (David Jacobs)
9/5	Labor Day, no class
Week 3 9/7	Review of math/coding background Introduction to Google Collab Basic math concept review Quiz 1	Szeliski Appendix A: Linear algebra and numerical techniques
Week 4 9/12 9/14	Image features Smoothing images Image pyramid Image gradient Points, corners, edges Scale and orientation	Szeliski 3.3 (neighbor operators), 3.4 (Fourier), 3.5 (pyramids) Szeliski 7.1 (points & patches), 7.2 (edges & contours)
9/18	Homework 1 due (11:59pm EST)
Week 5 9/19 9/21	Model Fitting Lines and curves Hough transform Alignment	Szeliski 4.1 (data interpolation), 7.4 (lines), 8.1 (pairwise alignment)
Week 6 9/26 9/28	Machine learning concepts Dimensionality reduction Clutering and segmentation Regression and classification	Wikipedia: Dimensionality reduction Szeliski 7.5 (segmentation), 6.1 & 6.2.1 (recognition)
Week 7 10/3 10/5	Elements of perspective geometry Homogeneous coordinates Camera geometry transformations Epipolar geometry Quiz 2 (10/3) Miterm review	Szeliski 2.1 (geometric primitives), 8.1 (alignment), 8.2 (stitching)
10/9	Homework 2 due (11:59pm EST)
10/10	Fall Break, no class
Week 8 10/12	Midterm
Week 9 10/17 10/19	Stereo Stereo viewing Stereo reconstruction	Szeliski 12.1 (epipolar), 12.2 & 12.3 (correspondence), 12.4 & 12.5 (optimization)
Week 10 10/24 10/26	Motion Low level motion Optical flow	Szeliski 9.3 (optical flow), 9.4 (layered motion)
Week 11 10/31 11/2	Recognition basics / Bag of features Object representation Classifiers and category recognition Deep Learning Introduction Deep neural networks Convolutional neural networks Architecture Applications	Szeliski 5.3 (DNN), 5.4 (CNN), 5.5 (more complex models) Deep Learning, Goodfellow et al., 2016. Deep Learning Tutorial, Stanford.
11/6	Homework 3 due (11:59pm EST)
Week 12 11/7 11/9	Convolutional Neural Networks Training Data augmentation Deep Learning Practice Pretraining Data augmentation Quiz 3, 11/9 in class
Week 13 11/14 11/16	Detection and segmentation Traditional solutions Deep learning solutions Semantic segmentation Recurrent neural networks	Szeliski 6.3 (detection), 6.4 (semnatic segmentation)
11/20	Homework 4 due (11:59pm EST)
Week 14 11/21	Vision Transformer Transformer Transformer in computer vision	An online tutorial of vision transformer
11/23	Thanksgiving Break, no class on 11/23
Week 15 11/28 11/30	Video Analytics Video object tracking Activity understanding Advanced Topics Spatial augmented reality
12/4	Homework 5 due (11:59pm EST)
Week 16 12/5	Final Review Quiz 4
12/14	Final Exam, Wed. 12/14, 5:30pm-8:00pm EST