Introduction to Computer Vision   

 

Spring 2021


Basic Information:

·  Lecture time: Mon/Wed 7:50pm – 9:10pm, online or NCS 120

·  Instructor: Prof. Haibin Ling, hling AT cs.stonybrook.edu

·  Office hour: Tue 3pm-5pm

·  Syllabus: PDF

· TAs:

Heng Fan (hefan AT cs.stonybrook.edu): 3:30-5:30pm Monday

Zuhui Wang (zuhui.wang AT stonybrook.edu), office hour: 9-11am Wednesday

Pavani Tripathi (pavani.tripathi AT stonybrook.edu), by appointment

 

 

Special Note Spring 2021: Students are expected to attend every class, report for examinations and submit major graded coursework as scheduled. If a student is unable to attend lecture(s), report for any exams or complete major graded coursework as scheduled due to extenuating circumstances, the student must contact the instructor as soon as possible.  Students may be requested to provide documentation to support their absence and/or may be referred to the Student Support Team for assistance. Students will be provided reasonable accommodations for missed exams, assignments or projects due to significant illness, tragedy or other personal emergencies. In the instance of missed lectures or labs, the student is responsible for review posted slides, review recorded lectures, seek notes from a classmate or identified class note taker, write lab report based on sample data.  Please note, all students must follow Stony Brook, local, state and Centers for Disease Control and Prevention (CDC) guidelines to reduce the risk of transmission of COVID. For questions or more information click here.

 

Useful Links:

·  Computer Vision: Algorithms and Applications, Richard Szeliski, 2010.

·  Computer Vision:  Models, Learning, and Inference, Simon J.D. Prince, 2012.


Date

Topics and Schedule (up to change)

Material

Week 1
2/1

SNOW, no class

 

2/3

General introduction

·         Background

·         Topics and applications

·         Related fields

·         Milestones

Week 2
2/8

Image formation

·         Basic facts about light

·         Anatomy of cameras

·         Matting

Szeliski 2.1, esp. 2.1.5

 

2/10

Filters and Noises

·         Modeling image noise

·         Convolution

Brief tutorial to Google Colab (Pavani Tripathi)

Szeliski 3.1, 3.2, 3.3.1, 3.4 (Fourier Transforms)

Week 3
2/15

Filters and Noises

·         Smoothing images

·         Image pyramids  

Szeliski 3.1, 3.2, 3.3.1, 3.4 (Fourier Transforms)

2/17

Image Features

·         Point features

·         Corners and Edges

·         Scale

·         Orientation  

Szeliski 4.1.1, 4.1.2, 4.2

Week 4
2/22

Model Fitting

·         Lines, curves

·         Hough Transform

Szeliski 4.1.3, 4.3.2

Szeliski 6.1, 2.1

2/24

·         Deformation

·         RANSAC

 

2/27

  Homework 1 due (11 :59pm EST)

     

 

Week 5
3/1

Perspective Projection

·         Homogeneous coordinates

Szeliski 2.1

3/3

·         Image warping

 

Week 6
3/8

Multiple View Geometry

·         Stereo viewing

Szeliski 6.3.1, 7, 11

 

3/10

·         Stereo reconstruction

 

 

Week 7
3/15

Object Recognition

·         Overview of machine learning in computer vision

·         PCA for image patches

 

3/17

·         Object representation

·         Classifiers

·         Object categories

 

3/20

  Homework 2 due (11 :59pm EST)

     

 

Week 8
3/22

·         Midterm review

3/24

·         Midterm

Week 9
3/29

Deep Learning

·         Deep neural networks

·         Convolutional neural networks

· Deep Learning, Goodfellow et al., 2016, MIT press. http://www.deeplearningbook.org/

3/31

·         Architectures

·         Applications

· Deep Learning Tutorial, http://ufldl.stanford.edu/tutorial/.

Week 10
4/5

Deep Learning Practice

·         Pre-training

·         Data-augmentation 

 

4/7

Illumination

·         Shading, shadows

·         Reflectance properties

 

4/10

  Homework 3 due (11 :59pm EST)

     

 

Week 11
4/12

Deep Generative Models

·         Autoencoders, VAEs

·         Generative adversarial networks (GAN)

 

4/14

Geometric Understanding in Deep Learning, Guest lecture by Prof. David Gu

 

Week 12
4/19

Detection

·         Traditional solutions

·         Deep learning solutions

 

4/21

·         Semantic segmentation  

 

4/24

  Homework 4 due (11 :59pm EST)

     

 

Week 13
4/26

Motion & Tracking

·         Low level motion

·         Flow

Szeliski 8.4

4/28

·         Recurrent neural networks

Tracking in 2D and 3D

 

Week 14
5/3

Advanced Topics (up to change)

·         SLAM

5/5

Spatial Augmented Reality – guest lecture by Bingyao Huang

 

5/8

  Homework 5 due (11 :59pm EST)

     

 

 

 

 

5/18

Final exam