16-385 Computer Vision, Spring 2015

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: (18202 and 15122) or (21240 and 21241 and 21259 and 15122).

Teaching Assistants

Wei-chiu Ma, weichium at andrew.cmu.edu, EDSH201, Wednesday, 3:00PM - 4:00PM
Minghuang Ma, minghuam at andrew.cmu.edu, EDSH201, Thursday, 3:00PM - 4:00PM

Recommended Textbook

Computer Vision: A Modern Approach , by David A. Forsyth & Jean Ponce, Prentice Hall.
Computer Vision: Algorithms and Applications , by Richard Szeliski, Springer.

Discussion

We use Piazza for class discussion and announments.

Grading

There are five individual projects and one midterm exam. There is no final exam.

Project 1	Hough Transform	15%
Project 2	Bag of Words	15%
Project 3	Homography	20%
Project 4	Structure from Motion	20%
Project 5	Tracking	20%
Midterm Exam		10%

Syllabus

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.

Image Processing
Jan 13	Introduction
Jan 15	Spatial Filtering
Jan 20	Programming Tutorial
Jan 22	Frequency Domain Filter, Image Pyramids, Gradients and Edge Filters
Jan 27	Line Detection
Jan 29	Hough Transform
Feb 03	Generalized Hough Transform	Project 1 Due on Feb 3
Recognition
Feb 05	Corner Detection, Multiscale Detection
Feb 10	Designing Feature Descriptors
Feb 12	Feature Descriptors, GIST, HOG, SURF, SIFT
Feb 17	Object Recognition
Feb 19	Classification
Feb 24	Bag of Words
Image Transformations(2D)
Feb 26	2D Transforms, 2D Alignment LLS
Mar 03	Midterm Review
Mar 05	Midterm Exam	Project 2 Due on March 6
Mar 10	Spring Break; No Class.
Mar 12	Spring Break; No Class.
Mar 17	2D Transforms DLT, RANSAC
Multi-view Geometry(3D)
Mar 19	Two-view Geometry and Camera Matrix
Mar 24	Pose Estimation and Triangulation
Mar 26	Epipolar Geometry, Essential and Fundamental Matrix
Mar 31	Reconstruction, Stereo Vision	Project 3 Due on April 1
Video Analysis
Apr 02	Video and Motion Analysis
Apr 07	Optical Flow
Apr 09	Image Alignment
Apr 14	KLT Tracking	Project 4 Due on April 15
Apr 16	No Class.
Apr 21	Mean-shift Tracking
Apr 23	Temporal Bayesian Inference
Apr 28	Kalman Filter & Extended Kalman Filter
Apr 30	MonoSLAM	Project 5 Due on April 30

Instructor:	Kris Kitani
Time:	Tuesday, Thursday 12:00PM - 1:20PM
Location:	WEAN HALL 5403