CAP 5416
Computer Vision

 

Final Exam


Online Submission


Homework Assignments

Homework solutions


Programming Assignments


Course Information

Computer Vision is the study of inferring properties of the world using digital images

This course is intended for beginning graduate students. We assume students have a rudimentary understanding of linear algebra, calculus, and are able to program in some type of structured language such as C++ and Java. The primary programming language for this class will be MATLAB, which is a convenient platform for mathematical computing involving matrices. There will be five to six (biweekly) homework assignments and several (three to four) programming assignments. We will have a final (in-class or take-home) exam. Grading will be approximately 50% on the homework assignments, 25% on the midterm exam, and 25% on the programming assignments.

Meetings:Tuesday 8th-9th periods and Thursday 9th period
Instructor:Jeffrey Ho [jho@cise.ufl.edu]
Office:CSE 360
Office hours:Friday 2pm-4pm
Teaching Assistant: S M Shahed Nejhum [smshahed@cise.ufl.edu]
Office hours:Monday 3pm-5pm in CSE 309
Note: when e-mailing the instructor and TA, please include [CAP5416] in the subject.

Policies

Grading will be approximately 50% on the homework assignments, 25% on the exam, and 25% on the programming assignments.

Homeworks are due in class and the programming assignments will be due usually before midnight Late homework is frowned upon. 10% of the possible grade is deducted for each day late. If there is ever a situation which prohibits you from turning in your homework on time, you must alert the instructor or TA promptly.

Honor Code
Above all, you must not misrepresent someone else's work as your own. You can avoid this in two ways:

  1. Do not use work from someone else.
  2. Give proper credit if you do use someone else's work.

Naturally, even if you give appropriate credit, you will only receive credit for your original work, so for this class you should stick with option #1.


Texts

Required Textbook Robot Vision,B. Horn, MIT Press 1986
Recommended Textbook Computer Vision: A Modern Approach, Forsyth and Ponce, Prentice Hall 2002.

(Additional online resources and photocopied readings will be made available.)

Syllabus

The main topics to be covered in this course are listed in the (tentative) schedule below. We will cover most of the chapters in Horn's book and supplemental materials will be made available later in the semester. Some chapters in the textbook will be covered in the form of reading assignments, and we will discuss the following chapters thoroughly in class: 2, 5, 6, 7, 8, 10, 11, 12, 13, 14, 16, 17.

Matlab


Schedule

Week Tuesday Thursday Suggested Readings Notes Comments
One Introduction Linear Algebra Review Horn Ch. 1 Slides
Two Image formation Intrinsic and extrinsic camera parameters Horn Ch. 1-2 Slides (from MD) Notes on projective gometry
Three Camera projection and some projective geometry Image Processing Horn Ch. 6 Slides (from MD) Reading Assignment: Chapters 3-4 in Horn
Four Basic Image Processing Basic Image Processing Horn Ch. 6 Slides 1 and Slides 2 Reading Assignment: Chapters 6-7 in Horn
Five Edges and Edge Detectors Edges and Edge Detectors Horn Ch. 8 Slides
Six More Image Features, Corners, etc. Detecting lines, circles, etc. Slides
Seven Image Segmentation and Active Contours Class Cancelled Slides Papers
Eight Image Segmentation/Clustering More on Spectral Clustering Slides Papers
Nine Camera Calibration Stereo Horn Ch. 13 Slides Slides
Ten Epipolar Geometry, Essential Matrix, Fundamental Matrix Multiview Reconstruction Horn Ch. 13 Slides  
Eleven Stereo Matchings Photometric Stereo Horn Ch. 10-11 Slides  
Twelve Photometry, Shape from Shading 3D reconstruction Horn Ch. 10, 11
Thirteen Motion and Flow I Motion and Flow II Horn Ch. 12, 17 Slides  
Fourteen Optical Flows and Pattern Classification Pattern Classification Horn Ch. 14 Slides
Fifteen Review No Class Slides

Suggested Reading: