Introduction
to Computer Vision Spring 2020 |
Basic Information: · Lecture time: Mon/Wed 5:30pm – 6:50pm, Engineering 143, West Campus · Instructor: Prof. Haibin Ling, hling AT cs.stonybrook.edu · Office hour: by appointment · Syllabus: PDF · TA: Tao Sun, Tao.Sun.1 AT stonybrook.edu, Office hour: Thur 3-5pm, by appointment. · TA: Kunal Kolhe, kkolhe AT cs.stonybrook.edu Office hour: Tues 10-11am, by appointment. |
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 |
General introduction · Background · Topics and
applications · Related fields · Milestones |
|
1/29 |
Image formation · Basic facts
about light · Anatomy of
cameras ·
Matting |
Szeliski 2.1, esp. 2.1.5 |
Week 2 |
Filters and
Noises · Modeling image
noise · Convolution |
Szeliski 3.1, 3.2, 3.3.1, 3.4 (Fourier Transforms) |
2/5 |
· Smoothing
images ·
Image pyramids |
|
Week 3 |
Image Features · Point features · Corners and
Edges · Scale · Orientation |
Szeliski 4.1.1, 4.1.2, 4.2 |
2/12 |
Guest lecture by Prof.
Xianfeng David Gu |
|
Week 4 |
Model Fitting · Lines, curves · Hough Transform |
Szeliski 4.1.3, 4.3.2 Szeliski 6.1, 2.1 |
2/19 |
· Deformation ·
RANSAC |
|
Week 5 |
Perspective
Projection · Homogeneous
coordinates · Image warping,
mosaics |
Szeliski 2.1 |
2/26 |
·
Midterm review |
|
Week 6 |
Multiple View
Geometry · Stereo viewing
and reconstruction · 3D range
scanning |
Szeliski 6.3.1, 7, 11 |
3 /4 |
·
Midterm
1 |
|
Week 7 |
Object
Recognition · Overview of
machine learning in computer vision · PCA for image
patches |
|
3/11 |
· Object
representation · Classifiers · Object
categories |
|
|
Spring Break |
|
Week 8 |
Deep Learning · Convolutional
neural networks · Architectures |
· Deep Learning,
Goodfellow et al., 2016, MIT press. http://www.deeplearningbook.org/ |
4/1 |
·
Applications |
· Deep Learning
Tutorial, http://ufldl.stanford.edu/tutorial/. |
Week 9 |
Deep Learning
Practice · Pre-training |
|
4/8 |
·
Data-augmentation |
|
Week 10 |
Illumination · Shading,
shadows · Reflectance
properties |
|
4/15 |
·
Midterm
2 |
|
Week 11 |
Deep Generative
Models · Autoencoders,
VAEs · Generative
adversarial networks (GAN) |
|
4/22 |
·
Application in computer vision |
|
Week 12 |
Detection · Traditional
solutions · Deep learning
solutions |
|
4/29 |
·
Semantic segmentation |
|
Week 13 |
Motion &
Tracking · Low level motion
· Flow |
Szeliski 8.4 |
5/6 |
· Recurrent
neural networks Tracking in 2D and 3D |
|
|
|
|
Final exam |
|
|
|