Spring 2017

Lecture: Tues & Thurs 4:40pm-6:00pm, Giedt Hall 1003
Discussion: Mon 4:10-5pm, Giedt Hall 1003 
Units: 4


Instructor: Yong Jae Lee
Email: yongjaelee@ucdavis  (email subject should begin with "[ECS 174]")
Office: Academic Surge 1044
Office hours: Fri 3-5 PM

TA: Chongruo Wu
Email: crwu@ucdavis 
Office: Academic Surge 1116
Office hours: Mon & Tues 10 AM - noon

TA: Zhongzheng (Jason) Ren 
Email: zzren@ucdavis 
Office: Academic Surge 1116
Office hours: Wed 10 AM - noon

TA: Leonardo Javier Ferrer Garcia De Alba 
Email: ferrer@ucdavis 
Office: Academic Surge 1044
Office hours: Thurs noon - 2 PM



A
nnouncements
  • Matlab is available for free this quarter from the campus software site here.
  • Info on IET Virtual Labs for MATLAB remote access
  • Instructions on obtaining a Graphical Interface (e.g., for MATLAB) via SSH to CSIF machines
  • Sign-up for our class piazza here (access code sent via email).



Course Overview

Computer vision is the study of enabling machines to "see" the visual world (i.e., understand images and videos).   In this upper-division undergraduate course, we will explore several fundamental topics in the area, including features and filters, grouping and fitting, and recognition.


Prerequisites

Basic knowledge of probability and linear algebra; data structures, algorithms; and programming experience.  Experience with image processing or Matlab will help but is not necessary.  Please talk to me if you are unsure if the course is a good match for your background.


Textbook

Computer Labs (w/ Matlab)
  • Matlab is available for free this quarter from the campus software site here.
  • CSIF labs 67, 71, 75.  Lab info and account info here and here.  Remote access info here.  pc1-pc60 have Matlab.  
  • Academic Surge 1044 and 1116.  Lab schedule can be found here.  ECS 174 is reserved for our class; other empty slots are available as well.  Remote access info here.
  • IET Virtual labs here.  Please read the FAQ.

Piazza

Rather than emailing questions to the teaching staff, please post your questions on Piazza.  Our class page: piazza.com/uc_davis/spring2017/ecs174/home
While we encourage you to help your fellow students, please do not post assignment solutions.


Canvas

We will use Canvas for problem set submissions and grading.  Our class page: https://canvas.ucdavis.edu/courses/113670


Requirements

Students will be responsible for participating in class and on piazza, completing 4 problem sets, and completing a final exam.


Grading

The final grade will be determined by:
  • Class and piazza participation (5%)
  • Problem sets (70%)
  • Final exam (25%)

Important Dates
  • 4/14: PS0 due 
  • 5/3: PS1 due (tentative) 
  • 5/22: PS2 due (tentative) 
  • 6/9: PS3 due (tentative) 
  • 6/15: Final exam

Detailed course requirements and grading are here.




Schedule (tentative)


 Date  Topic  Reading and links  Lectures  Assignments, deadlines
 4/4  Course intro  Szeliski 1.1-1.3  Intro [ppt] [pdf]

 4/6  Features and filters  Szeliski 3.1.1-2, 3.2  Linear filters [ppt] [pdf]  PS0 out
 4/11
 Szeliski 3.2.3, 4.2
 Seam carving paper
 Seam carving video
 Gradients [ppt] [pdf]
 4/13
 Szeliski 3.3.2-4  Edges and binary image analysis [ppt] [pdf]  PS0 due Fri 4/14, 11:59 pm
 4/18
 Szeliski 10.5 
 Texture Synthesis
 Texture [ppt] [pdf]  PS1 out

 4/20  Grouping and fitting  Szeliski 5.2-5.4 
 k-means demo
 Segmentation and clustering [ppt] [pdf]   
 4/25
 Szeliski 4.3.2
 Hough Transform demo
 Excerpt from Ballard & Brown
 Hough transform [ppt] [pdf]  
 4/27
 Szeliski 5.1.1  Deformable contours [ppt] [pdf]  
 5/2
 Szeliski 2.1.1, 2.1.2, 6.1.1  Alignment and 2D image transformations [ppt] [pdf]  PS1 due Wed 5/3, 11:59 pm
 5/4
 Szeliski 3.6.1, 6.1.4  Homography and image warping [ppt] [pdf]  PS2 out
 5/9
 Szeliski 4.1  Local invariant features 1 [ppt] [pdf]
 5/11
 Szeliski 4.1  Local invariant features 2 [ppt] [pdf]   

 5/16  Recognition  Grauman & Leibe Ch 1-4 (3 is review)
 Grauman & Leibe Ch 5,6 
 Szeliski 14.3
 Video Google demo by Sivic et al., paper
 Indexing local features and instance recognition [ppt] [pdf]    
 5/18
 Grauman & Leibe Ch 7,8.1,9.1,11.1
 Szeliski 14.1
 Intro to category recognition [ppt] [pdf]    PS2 due Mon 5/22, 11:59 am
 5/23
 Grauman & Leibe Ch 7,8.1,9.1,11.1
 Szeliski 14.1
 Viola-Jones face detection paper (for additional reference)
 Face detection [ppt] [pdf]    
 5/25
 Grauman & Leibe Ch 11.3 11.4 
 Szeliski 14.4
 Discriminative classifiers for image recognition [ppt] [pdf]    PS3 out
 5/30
 Grauman & Leibe Ch 11.3 11.4 
 Szeliski 14.4 
 Parts-based models 
 6/1

 Deep learning 1  
 6/6   Deep learning 2 
 6/8

 Course wrap-up and review  PS3 due Fri 6/9, 11:59 pm

 6/15    Final exam    Final exam 3:30-5:30 pm  




Acknowledgements

Thanks to Rick Szeliski for making his textbook available online for free.  I am also grateful to many instructors including Kristen Grauman, Devi Parikh, Alyosha Efros, Steve Seitz, Derek Hoiem, and Svetlana Lazebnik for making their course slides publicly available.

Links
Subpages (1): Requirements