Introduction to Computer Vision, Spring 2016

Course number: Info I400 / CS B490

Meets: Tuesday/Thursday 8:00-9:15pm

Location: Info W 107 / Info W 109 (lab)

Website: http://homes.soic.indiana.edu/classes/spring2016/csci/b490-mryoo/ 

Instructor: Prof. Michael S. Ryoo

Email: mryoo "at" indiana.edu

Office: Informatics E259

Office hours: Friday 1-2pm

Associate Instructor (i.e., teaching assistant): Alex Seewald

Email: aseewald "at" umail.iu.edu

Office: Informatics W018

Office hours: Tuesday 7-8pm, Wednesday 2-3pm

*Announcement* Final exam at 8:00pm on 5/3 Tuesday.

Course description:

Computer Vision is the study of enabling machines to "see" the visual world (i.e., understand images and videos). In this course, the students will learn fundamental computer vision algorithms and have opportunities to implement them. The course will have a format of half-lecture-half-lab, meaning that there will be one lecture (1.5 hours) per week to study the theory and one lab experience (1.5 hours) to implement the learned techniques. The basic machine learning frameworks necessary for automated understanding of images and videos will also be discussed, while particularly focusing on object recognition from images and activity recognition from videos.

The topics to be covered include:

Textbooks:

Computer Vision: Algorithms and Applications by Richard Szeliski

Programming Computer Vision with Python by Jan Erik Solem

(Optional) Visual Object Recognition, by Grauman and Liebe

Prerequisites:

Interest in computer vision; basic programming skills; basic knowledge of probability, linear algebra, data structures, and algorithms

Schedule:

Week

Topic

Reading

Slides

Programming

Week1

Introduction

Szeliski 1.1~1.3

Introduction [ppt]

Recognition_intro [ppt]

Week2

Features and filters

Szeliski 3.1.1, 3.1.2, 3.2

Szeliski 3.2.3, 4.2

Filters [ppt]

Gradients [ppt]

Week3-4

Edges, Texture, Color

Szeliski 3.3.2, 3.3.3, 3.3.4, 2.3.2, 10.5

Edges [ppt]

Texture [ppt]

assignment0

Week5-7

Grouping and fitting

Szeliski 5.2-5.4

Szeliski 4.3.2

Segmentation [ppt]

Fitting/Voting [ppt]

assignment1

assignment2

assignment3

Week8-12

Object recognition

Szeliski 4.1

Szeliski 14.1

Grauman&Liebe 7, 8, 9.1, 11.1

Solem 8.1~8.3

Local features [ppt]

Indexing [ppt]

Category recognition [ppt]

assignment4

assignment5

assignment6

assignment7

Week13-14

Videos - motion and tracking

Szeliski 8.4, Solem 10.4

Optical flows [ppt]

assignment8

Week14-15

Activity/event recognition

Szeliski 8.4, 12.6.4

Human activity analysis: A review, ACM Computing Surveys, 43(3), 2011

Activity recognition [ppt1]

[ppt2]

assignment9

Week16

Deep learning

Deep learning [ppt]

Course requirements and grading:

Programming assignments (50%): the students will work on implementations of the learned computer vision techniques. This will be done during the lab and through the homeworks.

Midterm exam (25%): the midterm exam.

FInal exam (25%): the final exam.

Acknowledgement:

This course has been inspired by the Computer Vision course by Kristen Grauman (UT), Devi Parikh (Virginia Tech), and Yong Jae Lee (UC Davis).