Kristen Grauman - Computer Vision Spring 2011

http://www.cs.utexas.edu/~grauman/courses/spring2011/index.htmlCS 376: Computer Vision
Spring 2011

Mon/Wed 11:00 am - 12:15 pm
UTC 3.124

---

Instructor: Kristen Grauman Office location: ACE 3.446 Office hours: Wed 5-6 pm, and by appointment.

TA: Shalini Sahoo shalini@cs.utexas.edu Office location: PAI 5.33 TA station, desk 3 Office hours: Tues/Thurs 5-6 pm

TA (office hours only): Yong Jae Lee Office location: PAI 5.33 TA station, desk 3 Office hours: Mon 5-6 pm

Please come to any of our office hours for questions about assignments or lectures.

Questions via email about an assignment should be sent to:
cv-spring2011@cs.utexas.edu, with "CS376" in the beginning of the subject line.
This will ensure the most timely response from the instructor or TA.

---

Announcements

The final exam slot has been confirmed by the registrar: Monday May 16, 2-5 pm, in JGB 2.102.  You may bring two sheets of notes on 8.5 x 11" paper.  The exam is comprehensive.

View all current grades and late days used on Blackboard.

Overview

Course description: Billions of images are hosted publicly on the web---how can you find one that “looks like” some image you are interested in?  Could we interact with a computer in richer ways than a keyboard and mouse, perhaps with natural gestures or simply facial expressions?  How can a robot identify objects in complex environments, or navigate uncharted territory?  How can a video camera in the operating room help a surgeon plan a procedure more safely, or assist a radiologist in more efficiently detecting a tumor?  Given some video sequence of a scene, can we synthesize new virtual views from arbitrary viewpoints that make a viewer feel as if they are in the movie?

In computer vision, the goal is to develop methods that enable a machine to “understand” or analyze images and videos.   In this introductory computer vision course, we will explore various fundamental topics in the area, including image formation, feature detection, segmentation, multiple view geometry, recognition and learning, and video processing.  This course is intended for upper-level undergraduate students. 

Textbook: The textbook is Computer Vision: Algorithms and Applications, by Rick Szeliski.  It is currently available for purchase e.g. at Amazon for ~$65.  An electronic copy is also available free online here.  I will also select some background reading on object recognition from this short book on Visual Object Recognition that I prepared together with Bastian Leibe.

Syllabus: Details on prerequisites, course requirements, textbooks, and grading policy are posted here.    A high-level summary of the syllabus is here.

Problem set deadlines: Assignments are due about every two weeks.  The dates below are tentative and are provided to help your planning.  They are subject to minor shifts if the lecture plan needs to be adjusted slightly according to our pace in class. 

• Pset 0 due Jan 28
  
• Pset 1 due Feb 14 (tentative)
  
• Pset 2 due Mar 2 (tentative)
  
• Pset 3 due Mar 28 (tentative)
  
• Pset 4 due April 18 (tentative)
  
• Pset 5 due May 4 (tentative)
  

Schedule

	Dates	Topic	Readings and links	Lectures	Assignments, exams
	Wed Jan 19	Course intro	Sec 1.1-1.3	Intro [pdf]	Pset 0 out Friday Jan 21
	Mon Jan 24	Features and filters	Sec 3.1.1-2, 3.2	Linear filters [ppt] [pdf] [outline]
	Wed Jan 26		Sec 3.2.3, 4.2 Seam carving paper Seam carving video	Gradients and edges [ppt] [pdf] [outline]	Pset 0 due Friday Jan 28
	Mon Jan 31		Sec 3.3.2-4	Binary image analysis [ppt] [pdf] [outline]	Pset 1 out [class results]
	Wed Feb 2		Sec 10.5 Texture Synthesis	Texture [ppt] [pdf] [outline]
	Mon Feb 7		Sec 2.3.2 Foundations of Color, B. Wandell Lotto Lab illusions	Color [ppt] [pdf] [outline]	Pset 0 grades and solutions returned in class
	Wed Feb 9	Grouping and fitting	Sec 5.2-5.4 k-means demo	Segmentation and clustering [ppt] [pdf] [outline]
	Mon Feb 14		Sec 4.3.2 Hough Transform demo Excerpt from Ballard & Brown	Hough transform [ppt] [pdf] [outline]	Pset 1 due Monday Feb 14   Pset 2 out
	Wed Feb 16
	Mon Feb 21		Sec 5.1.1	Deformable contours [ppt] [pdf] [outline]
	Wed Feb 23		Sec 2.1.1, 2.1.2, 6.1.1	Alignment and 2d image transformations [ppt] [pdf] [outline]	Pset 1 grades and solutions returned in class
	Mon Feb 28	Multiple views and motion	Sec 3.6.1, 6.1.4	Homography and image warping [ppt] [pdf] [outline]
	Wed Mar 2		Sec 4.1	Local invariant features 1 [ppt] [pdf] [outline]	Pset 2 due Wednesday Mar 2
	Mon Mar 7		(Sec 4.1)	Local invariant features 2 [ppt] [pdf] [outline]
	Wed Mar 9				Midterm exam Pset 2 grades and solutions returned in class
	Spring break				Pset 3 out  [class results]
	Mon Mar 21		Sec 11.1.1, 11.2-11.5	Image formation (and local feature matching wrap-up) [ppt] [pdf] [outline]
	Wed Mar 23		Sec 11.1.1, 11.2-11.5 Epipolar geometry demo Audio camera, O'Donovan et al.	Stereo 1: Epipolar geometry [ppt] [pdf] [outline]
	Mon Mar 28		Virtual viewpoint video, Zitnick et al.	Stereo 2: Correspondence and calibration [ppt] [pdf] [outline]
	Wed Mar 30	Recognition	Grauman & Leibe Ch 1-4 (3 is review)	Indexing local features [ppt] [pdf] [outline]	Pset 3 due Wed March 30
	Mon April 4		Grauman & Leibe Ch 5, 6 Szeliski 14.3 Video Google demo by Sivic et al., paper	Instance recognition [ppt] [pdf] [outline]
	Wed April 6		Grauman & Leibe Ch 7, 8.1, 9.1, 11.1 Szeliski 14.1	Intro to category recognition [ppt] [pdf] [outline]	Pset 3 grades and solutions returned in class Pset 4 out
	Mon April 11		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] [outline]
	Wed April 13		Grauman & Leibe 11.3, 11.4 Szeliski 14.4	Discriminative classifiers for image recognition [ppt] [pdf] [outline]
	Mon April 18		Grauman & Leibe 11.3, 11.4 Szeliski 14.4	Part-based models [ppt] [pdf] [outline]
	Wed April 20	Video processing	8.4, 12.6.4	Motion [ppt] [pdf] [outline]	Pset 4 due Wed April 20
	Mon April 25		8.4, 12.6.4 Davis & Bobick paper: The Representation and Recognition of Action Using Temporal Templates Stauffer & Grimson paper: Adaptive Background Mixture Models for Real-Time Tracking.	Background subtraction, Action recognition [ppt] [pdf] [outline]	Pset 5 out
	Wed April 27		5.1.2, 4.1.4	Tracking [ppt] [pdf]	Pset 4 grades and solutions returned
	Mon May 2			Course wrap-up and review
	Wed May 4
					Pset 5 due Sun May 8
	Mon May 16 2-5 pm				Final exam in JGB 2.102

Links

• Accessing Matlab at UT
  If you're using gnome on the new package machines and are trying to use Matlab you'll notice that you get a blank Matlab window. To fix the problem click on System Menu - Preferences - Appearance, then pick 'Visual Effects' tabs. Set the effect to None and close the window.  Matlab will start up normally after that.
• Having Matlab license issues?  See tips here (thanks Yong Jae)
• Getting started with Matlab: basic tutorial
• Blackboard
  
• UTCS Computing / Facilities web page
• CV Online
• OpenCV (open source computer vision library)
• Weka (Java data mining software)
• Compiled list of image datasets
• Netlab (matlab toolbox for data analysis techniques, written by Ian Nabney and Christopher Bishop)
• Computer vision conferences
• Annotated computer vision bibliography
• Face recognition homepage
• Computer vision research groups
• Vision related links on AAAI.org page
• Grauman & Leibe - Visual Object Recognition  - short book in Synthesis lecture series
  
• Also see above in our syllabus for links relevant per lecture.