CS6320 3D Computer Vision, Spring 2015

Computing properties of our 3-D world from passive and active sensors

Syllabus, Guido Gerig (home)

Goal and Objectives:

To introduce the fundamental problems of 3D computer vision.
To introduce the main concepts and techniques used to solve those.
To enable participants to implement solutions for reasonably complex problems.
To enable participants to understand basic methodology that is discussed in the computer vision literature.

General Information:

Lecture:        M,W 1.25 - 2.45 WEB 2250
Instructor:    Guido Gerig (gerig at sci.utah.edu)
                   Office WEB 4893, office hours M,W 3 - 5pm
TA:            Padmashree Teeka, (u0880562 at utah.edu)
                   Office MEB 3115 desk 11, office hours: Tuesdays - 3pm to 5pm, Thursdays - 11am to 1pm

Material:
Primary Textbook, to be purchased by students: Computer vision: a modern approach, by Forsyth and Ponce. Prentice Hall, 2011 (or original 2002 version).
(Secondary Textbook: not to be purchased by students Book by Rick Szeliski).
The class will make use of MATLAB for projects. Students can also use of C++.

Prerequisites:
It is a prerequisite that students have knowledge in fundamental image processing procedures and techniques. The graduate course CS6640 Image Processing or an equivalent graduate level image analysis or graphics/imaging course are highly recommended. Students with dierent background and curriculum related to image processing and/or pattern recognition background need to discuss suitability and options with the teacher.

Syllabus (pdf document)

College of Engineering CADE lab infrastructure and hand-in system for assignments

Schedule (DATES AND TOPICS SUBJECT TO CHANGE):

Date	Topic	Slides	Readings (files)	Additional Materials	Assignments
12-Jan-15	Introduction	Introduction slides (pdf)	Textbook Forsyth&Ponce: Book Contents (pdf)
14-Jan-15	Image Formation	Image Formation I: Cameras, Lenses, Sensors (slidesI, slidesII, slides-lenses III)	Old book: 1.1 New book: 1.1 Textbook Forsyth&Ponce: Image Formation: Ch1 Cameras (pdf) Geometric Camera Models CH 2 (pdf)
16-Jan-15 1 to 3pm	Matlab Introduction	Lecturer: Padmashree Teeka Time: 1pm to 3pm Location: WEB 2nd Floor Meldrum Conference Room (opposite 2nd floor WEB elevator SCI Inst.)	Slides pdf, Matlab code and images archive), (2014 materials by Avantika Vardhan and Bo Wang)	Matlab tutorial streaming video: vimeo page http://vimeo.com/sciinstitute and directly at http://vimeo.com/105393037
19-Jan-15	MLK Day Holiday
21-Jan-15	Image Formation ctd.	Image Formation II (pdf)	Old book: 2.1, 2.2 New book: 1.2 (Geometic Camera Models) Part I: Image Formation
26-Jan-15	Image Formation ctd.	Image Formation II (pdf): Camera Calibration (pdf) Radial Distortion Corr: (pdf)	Geometric Camera Models: Old Book: Read 2.1, 2.2, 3.1-3.3 New Book: 1.2, 1.3 Part I: Image Formation -Intrinsic/Extrinsic Parameters -Cameras with Lenses
28-Jan-15	Image Formation ctd.: Image Transformations, Lenses, Camera Calibration	Lenses: slides-lenses III Lenses, depth of field (ppt) Depth of field animated slides (pdf) Slides intro Stereo (pdf)	Ch2 Image Transformations, Camera Calibration Camera Calibration slides (intrinsic, extrinsic parameters) S.M. Abdullah		Assignment 1 is out: Deadline Monday February 11: (pdf) calibration pattern: (pdf) see also slides S.M. Abdullah (pdf)
02-Feb-15	Cameras with Lenses Introduction Stereo		New book: 1.13 Old book: 1.2
04-Feb-15	Stereo, Epipolar Geometry,Stereo Essential and Fundamental Matrices.	Slides intro Stereo (pdf) Slides Multiple View Geometry I (pdf)	New book: Ch7 Stereopsis Old Book: Ch10 and 11
09-Feb-15	Repetition: Geometry of multiple Views, Correspondence: Multiview stereo, Triangulation.	Slides MVG II (pdf) Slides Image Rectification (pdf)	New book: Ch7 Stereopsis Old Book: Ch10 and 11	Image Rectification (Trucco & Verri Textbook) (pdf)
11-Feb-15	Multiview stereo, Rectification, Triangulation.	Slides Image Rectification (pdf) Epiipolar Geometry and Small motions (pdf)	New book: Ch7 Stereopsis Old Book: Ch10 and 11		Assignment 1 due midnight (canvas handin)
16-Feb-15	President's Day Holiday
18-Feb-15	Stereo, Triangulation, Correspondences	Slides Correpondences/Correlation (pdf)	New book: Ch 7.4/7.5/7.6 Old book: Ch 11.2/11.3/11.4
23-Feb-15	Correspondences ctd..	Slides Correspondence and Dense Depth Estimation (see above)			Assignment 2 out (pdf)
25-Feb-15	Stereo: Triangulation / 3D Reconstruction	Stereo: Triangulation (pdf)	Old book: 11.1 and 10.1.4 (motions) New book: Ch7.2 and Problem 7.2
02-Mar-15	Introduction: Reflectance Maps, Shape from Shading	Photometric Stereo and Shape from Shading SfS: Slides G. Gerig Slides introduction (pdf) , SfS (pdf)	New Book: Chapter 2 Old Book:: Chapters 4 and 5
04-Mar-15	Photometric Stereo (ctd) Lecture given by Shireen Elhabian (Postdoc SCI Institute)	Slides SFS: (pdf)		Additional materials/slides Photometric Stereo and Shape fronm Shading (Ohad Ben-Shahar BGU) Slides Wolff JHU (pdf) Link to materials Wolff JHU (link)
09-Mar-15	Shape from Shading: Surface Reconstruction	Sllides SFS (see above)	Hands on Shape from Shading, Technical Report, May 2008 by Shireen Y. Elhabian (pdf)	SfS via curve evolution (Kimmel, Siddiqi, Bruckstein): (pdf)	Assignment 2 due midnight (canvas handin)
11-Mar-15	Optical Flow I	Optical Flow (OF) I: Slides G. Gerig (pdf)	Optical Flow: Computer Vision Book (pdf) Original Paper Horn & Schunck 1981 (pdf)		Assignment 3 out (pdf) synthetic images sphere images dog-images-png dog-images-tif Final Project Ideas: (pdf)
16-Mar-15	Spring Break
18-Mar-15	Spring Break
23-Mar-15	Optical Flow II, Structure from Motion	Optical Flow I: Slides G. Gerig, modified by Shireen Elhabian (pdf)	Optical Flow: Computer Vision Book T&V (pdf) Original Paper Horn & Schunck 1981 (pdf) Optical Flow Computer Vision Book T&V Ch8 (pdf)	CAP5415 - Computer Vision , Slides: Motion&Optical Flow
25-Mar-15	Optical Flow III	Optical Flow II: Slides G. Gerig (pdf)
30-Mar-15		Optical Flow II: Slides G. Gerig (pdf)
01-Apr-15	Structured Lighting I and II	Optical Flow: Structure from motion (see previous slides), additional handwritten notes. Structured Lighting I: Slides G. Gerig (pdf) Powerpoint slides with animations (ppt)	Structured Lighting: Some pages from Computer Vision Book R. Klette (pdf)	Build your own 3D scanner: SIGGRAPH 2009 course: D. Lanman/ G. Taubin Brown University: Notes pdf, Slides Stanford, Levoy et al: Real-time 3D Model Acquisition (link) 3D photography on your desk: Bouget &Perona ICCV 1998: (pdf) *	Assignment 3 due Friday 03-April midnight
06-Apr-15	Structured Lighting II ctd.	Structured Lighting II cts. (pdf)			Assignment 4 out (pdf) video-sequence-images b/w video-sequence-images color
08-Apr-15	Shape from Silhouettes I	Shape from Silhouettes I: Slides G. Gerig (pdf)	Marching Intersections (M. Tarini (pdf)) Exact Polyhedral Methods (W. Matusik pdf ) Image-based Visual Hulls IBVH (W. Matusik, pdf)
13-Apr-15	Shape from Silhouettes II	Shape from Silhouettes II (Visual Hulls): Slides G. Gerig (pdf) Shape from Silhouettes III (Forbes): Slides G. Gerig (pdf)	K. Forbes: Consistency Constraints (pdf) K. Forbes: Uncalibrated, two planar mirrors (pdf)
15-Apr-15	Shape from Silhouettes III
20-Apr-15	Range/Depth Image Processing	Range/Depth Data Processing: Slides G. Gerig (pdf)	Textbook F&P: New book: Ch 14, pp 422ff Old book: Ch 21, pp. 467ff		Assignment 4 due midnight (canvas handin)
22-Apr-15	Final Project Presentations: 1:25-2:45	Schedule: pdf	Attendence of ALL is mandatory. Talks need to be uploaded to canvas and will be made available to the class.
27-Apr-15	Final Project Presentations: 1:25-2:45	Schedule: pdf	Attendence of ALL is mandatory.
04-May-15	Final Project Report due				Final Project Report/code/materials due Wed 05/04/15 midnight

Other Information:

College of Engineering CADE lab infrastructure.

University of Utah and Computer Science Honor Code

Students are expected to work on their own, as instructed by the Professor. Students may discuss projects with other individuals either in the class or outside the class, but they may not receive code or results electronically from any source that is not documented in their report. Students must write their own code, conduct their own experiments, write their own reports, and take their own tests. Any use of sources (for projects or tests) that are not specifically given to the student by the Professor or TA, must be discussed with the Professor or TA or documented in the report. Any student who is found to be violating this policy will be given a failing grade for the course and will be reported to the authorities as described in the University's Student Code.

Accommodations Policy
The University of Utah seeks to provide equal access to its programs, services and activities for people with disabilities. If you will need accommodations in the class, reasonable prior notice needs to be given to the Center for Disability Services, 162 Olpin Union Building, 581-5020 (V/TDD). CDS will work with you and the instructor to make arrangements for accommodations. All written information in this course can be made available in alternative format with prior notification to the Center for Disability Services.

Homework
Homework assignments are due at 11:59pm on the given due date. Written assignments should be in
pdf format, while coding assignments should additionally be source files. Coding can be done in MATLAB (using
only the base package, no toolkits), C++. The report should clearly identify code developed by the student and pieces of code obtained by external sources.

Grading

Weighted contribution of projects and exams to final grade:

Projects (4-5), theoretical and practical parts, coding, tests and project report: 60%.
Final Project (incl. design, coding, project report, presentation, demo): 30%.
Participation: 10%. (Attendance to lectures is required to be eligible for office hours by the instructor and the TA. Attendance and regular active participation is required to get the participation grade).
We will have a few short in-class quizzes to check understanding. Scores will be part of the participation grade.
Late policy on projects: 10 percent deduction per day, projects no more accepted after 3 days.*
Final project is required to get a passing grade.
Please note that for this graduate level class, an A grade means outstanding, whereas A- stands for excellent.

* Exceptions may apply for excused absences documented by officials (e.g. medical problems), requiring additional advanced notice.

Resources:

Matlab Introduction Imaging, special course lecture:

Course Materials Avantika Vardhan and Bo Wang (August 2014) (updated slides pdf, Matlab code and images archive)
Matlab tutorial streaming video: vimeo page http://vimeo.com/sciinstitute and directly at http://vimeo.com/105393037