16-385 Computer Vision, Spring 2017
Instructor: Kris Kitani
Time: Monday, Wednesday 1:30PM - 2:50PM
Location: DOHERTY HALL 1212
Course Description

This course provides a comprehensive introduction to computer vision. Major topics include image processing, detection and recognition, geometry-based and physics-based vision and video analysis. Students will learn basic concepts of computer vision as well as hands on experience to solve reallife vision problems.

This course requires familarity with linear algebra and basic probability. MATLAB will be used for project assignments and will be covered as part of the introduction to the course.

Prerequisites
Teaching Assistants
Discussion

We use Piazza for class discussion and announcements.

Special Thanks

These lecture notes have been pieced together from many different people and places. Special thanks to colleagues for sharing their PPTs directly with me: Bob Collins, Srinivasa Narashiman, Martial Hebert, Alyosha Efros, Ali Faharadi. I would also like to thank the following people for making their lecture notes and materials available online: Steve Seitz, Richard Selinsky, Larry Zitnick, Noah Snavely, Lana Lazebnik, Kristen Grauman, Yung-Yu Chuang, T. Tuytelaars, Fei-Fei Li, Antonio Torralba, Rob Fergus, David Claus and Dan Jurafsky.

Schedule

Slides would be updated on this website 3 days after each lecture. Please see Piazza for latest schedule.

1. Introduction - Why you can succeed in this class?
Jan 18
1.1 Staff Introduction
1.2 What is Computer Vison?
1.3 Applications of Computer Vision
1.4 Class Overview
2. Image Processing
Jan 30
2.1 Image Filtering
2.2 Point Processing
2.3 Box Filter
2.4 Gaussian Filter
2.5 Subsampling
2.6 Image Pyramid
Feb 1
2.7 Image Gradients and Gradient Filtering
2.8 Filtering vs Convolution
3. Hough Transform
Feb 6
3.1 Defining Boundaries
3.2 Extracting Edges
3.3 Line Parameterizations
3.4 Hough Transform
3.5 Generalized Hough Transform
4. Corner Detection
Feb 8
4.1 Finding Corners
4.2 Visualizing Quadratics
4.3 Harris Corner Detector
4.4 Multiscale Detection
5. Visual Recognition
Feb 13
5.1 Designing Descriptors
5.2 Feature Descriptors
5.3 More Feature Descriptors
5.4 SIFT Detector and Descriptor
Feb 15
5.5 Object Recognition
5.6 Probability Basics
5.7 Bag of Visual Words
5.8 Classification
6. Convolutional Neural Networks
Feb 22
6.1 Perceptron
6.2 Neural Network
6.3 Perceptron Training
6.4 Visualizing Gradient Descent
6.5 Backpropagation
Feb 27
6.6 Convolutional Neural Networks and Deep Learning
6.7 Deep Learning Architectures
7. 2D Transforms
Mar 1
7.1 2D Transforms
7.2 2D Alignment - Linear Least Squares
Mar 6
7.3 2D Alignment - Direct Linear Transform
7.4 2D Alignment - RANSAC
8. Multi-View Geometry
Mar 8
8.1 Two-View Geometry
8.2 Camera Matrix
8.3 Camera Models
Mar 20
8.4 Pose Estimation
8.5 Triangulation
8.5 SVD for Total Least Squares
9. Structure From Motion
Mar 22
9.1 Epipolar Geometry
9.2 Essential Matrix
Apr 3
9.3 Fundamental Matrix
9.4 8-Point Algorithm
9.5 Reconstruction
10. Stereo
Apr 5
10.1 Stereo Rectification
13.2 Stereo Matching
11. Optical Flow
Apr 10
11.1 Brightness Constancy
11.2 Optical Flow : Constant Flow
11.3 Optical Flow: Horn-Schunck
Apr 12
11.4 Alignment : LucasKanade
11.5 Alignment : BakerMatthews
12. Tracking
Apr 17
12.1 KLT tracking
12.2 Mean_Shift Tracking
13. Filtering
Apr 24
13.1 Temporal State Models
13.2 Temporal Inference
13.3 Kalman Filtering
Apr 26
13.4 Extended Kalman Filter
13.5 Mono SLAM
Wrap up
Previous Course Websites

16-385 - Computer Vision, Spring 2015

15-385 - Computer Vision, Spring 2014

Last modified: Jan 14 2017 Animesh Ramesh