Instructor
Lihi Zelnik-Manor
lihi -at- ee.technion.ac.il
Personal website
phone: 04-8295736
Office: Meyer 959
Office hours: Upon request by email
Short description
This course will deal with methods for analyzing and interpreting the contents of images and video, by reviewing existing state-of-the-art approaches and algorithms. The methods will be explored through their usage in real-world applications such as visual summarization of video clips, special effects in movies or search in visual data bases such as YouTube.
Topics that will be explored: feature detection in video, motion estimation, video mosaics, video synthesis, recognizing objects, detecting people and action recognition.
In this course you will
-
Learn basic concepts in image and video analysis
-
Read state-of-the art academic papers
-
Implement published work and test it
-
Learn how to build an “executive summary” presentation of a scientific idea
-
Evaluate prior art
-
Propose your own solutions
Prerequisites
A bunch of things you want to know.
-
A good working knowledge of Matlab
-
Linear Algebra
-
Any previous exposure to computer vision, machine learning, applied probability, and/or image processing will be an asset.
Please feel free to contact me if you have any concerns about whether or not you should take this course.
Textbooks
None required.
Optional: Forsyth & Ponce, Computer Vision: A Modern Approach, Pearson, 2002, ISBN 0130851981
Administrative
Email List: Please send me an email asking to be added to the distribution list.
I will use emails to for updates/corrections/information.
Grading
The grade is based on a programming project and its presentation.