E27: Computer Vision

Spring 2013

Tue, Thu 11:20-12:35, Hicks 211
Instructor: Matt Zucker

Course Description

Computer vision studies how computers can analyze and perceive the world using input from imaging devices. This course introduces topics in computer vision of particular relevance to engineers, with an emphasis on hands-on applications. We will also learn about state of the art techniques and sensors, including the Microsoft XBOX Kinect sensor.

Look over the course syllabus for more information.

The topics below are subject to change. As we move through the course, I will update the list to reflect the new schedule, readings, and assignments.

Textbook

Richard Szeliski, Computer Vision: Algorithms and Applications, Springer 2010-11.

The book is available in its entirety online at http://szeliski.org/Book/. I have not ordered copies at the bookstore, but if you want a hard copy you should be able to find it for purchase online.

Useful Links

Note

Some of the slides below come from Martial Hebert's excellent Computer Vision course at Carnegie Mellon University.

Class Schedule

Part I: Image formation and appearance-based methods
Week Dates Topics Readings Labs & HW
1 Jan 22, Jan 24
  • Introduction
  • Math review
  • Image formation
  • Homogeneous coordinates
Syllabus; Chapter 1; Sections 2.1, 2.3 OpenCV setup Sample code Homework 1
2 Jan 29, Jan 31
  • Image representations
  • OpenCV introduction
  • Thresholding & color segmentation
  • Morphological operators
Sections 3.1-3.4, 3.5.1, 3.5.2, 3.6.1
HW 2 images
Fruit flies movie 1
Fruit flies movie 2
Homework 2
Project 1
3 Feb 5, Feb 7
  • Filters
  • Convolutions
  • Frequency domain analysis
Filtering slides
Fourier slides
Fourier applet
Homework 3
4 Feb 12, Feb 14
  • Edge detection
  • Hough transform
  • Template tracking
Sections 4.2, 4.3
Section 8.1
Hough applet
Sudoku solver Tracker code
Part II: Geometric and 3D methods
5 Feb 19, Feb 21
  • Exam 1: date and time TBA
  • Camera calibration
  • Intrinsic & extrinsic parameters
findx code Chapter 6
Camera slides
Projection slides
Homework 4
6 Feb 26, Feb 28
  • Multiple view geometry
  • Algebraic vs. geometric error
Diebel - attitude paper
Cereal box camera calibration code
Homework 5
Project 2
Sample images
7 Mar 5, Mar 7
  • Stereo
  • Structured light
Sections 7-7.1
Sections 11-11.3
Homework 6
SPRING BREAK
8 Mar 19, Mar 21
  • Singular value decomposition
  • Structure from motion
Chapter 7
9 Mar 26, Mar 28
  • Radiometry & color
  • BRDF's & shading
Radiometry slides
Section 2.2
10 Apr 2, Apr 4
  • Shape from shading
  • Photometric shape from example
Section 12.7
Kinect specs
Shape from example; Paper
Sample code
Project 3
Starter code
Homework 7
Part III: Recognition and classification
11 Apr 9, Apr 11
  • Exam 2: date and time TBA
  • Principal component analysis
  • Eigenfaces
  • Linear classifiers
Section 14.2
Eigenfaces applet
Final project
12 Apr 16, Apr 18
  • Neural networks
  • AdaBoost
Section 14.1
13 Apr 23, Apr 25
  • Cascade classification
  • Viola-Jones object recognition
Viola-Jones paper
14 Apr 30, May 2
  • Clustering & k-means
  • Histogram analysis
  • Texture classification with textons
Varma & Zisserman textons paper
FINAL EXAM - date and time TBA