3D Computer Vision Winter Term 2006/07

Administrative Info Lecture by Prof. Nassir Navab, Dr. Selim Benhimane Exercises by Dr. Selim Benhimane, Martin Groher 3+2 SWS, 6 ECTS, Theoretische Informatik, Wahlpflichtfach

Time & Location Tuesday 10:30 - 12:00 MI 00.13.009A Thursday 11:15 - 12:00 MI 00.13.009A Exercises: Thursday 13:00 - 14:30 MI 00.13.009A First Lecture: 17th Oct 2006

Site Content Overview Content Course Schedule Exercises Readings Programming Assignment

Announcements * The lecture of the 23.11.06 will take place in the room 01.07.014 instead of 00.13.009A * The first intermediate Exam is *CLOSED BOOK and WITHOUT SLIDES, NO DOCUMENTS ALLOWED! * The second intermediate Exam is *CLOSED BOOK and WITHOUT SLIDES, NO DOCUMENTS ALLOWED! * Thursday 25/01 no exercises. Individual/groups questions and answers concerning the programming assignment in the room 03.13.043 ! * *Please for the Field Trip to BrainLAB.* * On Tuesday 30/01/2007, we will have a 30 min Lecture since a talk is scheduled in the room at 11:00. * On Thursday 01/02/2007, we will have a 1:30 Lecture (10:30-12:00) for the invited talk of Dr. Vincent Lepetit.

Overview

Making a computer see was something that leading experts in the field of Artificial Intelligence thought to be at the level of difficulty of a summer student's project back in the sixties. Forty years later the task is still unsolved and seems formidable. A whole field, called Computer Vision, has emerged as a discipline in itself with strong connections to mathematics and computer science and looser connections to physics, the psychology of perception and the neuro sciences.

Over the past decade there has been a rapid development in the understanding and modelling of the geometry of multiple views in computer vision. The theory and practice have now reached a level of maturity where excellent results can be achieved for problems that were unsolved a decade ago, and often thought unsolvable. These tasks and algorithms include problems like:
Given two/three/multiple images, and no further information, compute/estimate:

• matches between the images
• the 3D position of the points that generate these matches
• the cameras that generate the images

adapted form Hartley & Zisserman's "Multiple View Geometry in Computer Vision"

This tasks and algorithms as well as the methods which allow us to reason about the quality of our results are the core of the lecture 3D Computer Vision.

Content

1. Intro, motivation & Overview
2. 2D Transformations
3. Projective 2D Geometry
4. 3D Transformations
5. Projective 3D Geometry
6. Parameter Estimation
7. Camera Models
8. Camera Calibration
9. Feature-based matching
10. Feature-based tracking
11. Programming assignment
12. Conclusion & Discussions

Course Schedule

Date	Type	Topic	Conducted by	Material
Tue, Oct 17, 2006	C	Introduction & Motivations	N. Navab
Thu, Oct 19, 2006	C	Basic Transformations, Duality (points, lines)	N. Navab	3D_CV_WT_2006_Lecture_01.pdf
Tue, Oct 24, 2006	C	2D Projective Geometry	S. Benhimane	3D_CV_WT_2006_Lecture_02Part1.pdf
Thu, Oct 26, 2006	C	2D and 3D Projective Transformations	N. Navab	3D_CV_WT_2006_Lecture_02Part2.pdf
Tue, Oct 31, 2006	E	2D Projective Transformations	S. Benhimane
Thu, Nov 2, 2006	F	Field Trip to Siemens Medical
Tue, Nov 7, 2006	C	3D Projective Transformations	N. Navab
Thu, Nov 9, 2006	C	Introduction to conics and quadrics	N. Navab	3D_CV_WT_2006_Lecture_03.pdf
Tue, Nov 14, 2006	C	Parameter Estimation: Linear estimation, DLT, Cost Functions	N. Navab
Thu, Nov 16, 2006	C	Parameter Estimation: Sampson Error, Statistical Cost Function	N. Navab	3D_CV_WT_2006_Lecture_04.pdf
Tue, Nov 21, 2006	C	Non-linear Parameter Estimation I	N. Navab
Thu, Nov 23, 2006	C	Non-linear Parameter Estimation II ( in room 01.07.014 )	N. Navab
Tue, Nov 28, 2006	T	1st intermediate test	M. Groher	Results
Thu, Nov 30, 2006	C	Algorithm Evaluation & Error Analysis I	N. Navab	Algorithm Evaluation & Error Analysis.pdf
Tue, Dec 5, 2006	C	Algorithm Evaluation & Error Analysis II	N. Navab
Thu, Dec 7, 2006		no class due to Dies Academicus
Tue, Dec 12, 2006	C	Camera Model	N. Navab	3D_CV_WT_2006_CameraModel.pdf
Thu, Dec 14, 2006	C	Computation of the Projection Matrix I	N. Navab
Tue, Dec 19, 2006	C	Camera Calibration	N. Navab	3D_CV_WT_2006_CameraCalib.pdf
Thu, Dec 21, 2006	C	Computation of the Projection Matrix II	N. Navab
Tue, Dec 26, 2006		no class due to Christmas holidays
Thu, Dec 28, 2006		no class due to Christmas holidays
Tue, Jan 2, 2007		no class due to Christmas holidays
Thu, Jan 4, 2007		no class due to Christmas holidays
Tue, Jan 9, 2007	C	Camera Distortion Calibration	N. Navab
Thu, Jan 11, 2007	C	Feature-based Matching	A. Ladikos	3D_CV_WT_2006_FeatureMatching.pdf
Tue, Jan 16, 2007	T	2nd intermediate test	M. Groher	Results
Thu, Jan 18, 2007	E	Feature-based matching	A. Ladikos	exercise08.pdf solution08.pdf
Tue, Jan 23, 2007	C	Template-based tracking	S. Benhimane	TemplateTracking.pdf
Thu, Jan 25, 2007	I	Invited Talk	Marco Feuerstein
Tue, Jan 30, 2007	I	Research events of the CAMP&AR Chair ( 30 min Lecture)	CAMP Chair
Thu, Feb 1, 2007	I	Invited Talk ( Lecture from 10:30 to 12:00)	Dr. Vincent Lepetit	Real-Time 3D Tracking in Monocular Sequences
Tue, Feb 6, 2007	I	Invited Talk ( Lecture from 10:30 to 12:00)	Dr. Adrien Bartoli
Thu, Feb 8, 2007	T	Final Exam 13:00-14:30 in 00.13.009A	M. Groher	Results

Exercises

Date	Type	Topic	Conducted by	Material
Thu, Oct 19, 2006	C	Basic Transformations, Duality (points, lines)	N. Navab
Thu, Oct 26, 2006	E	2D Projective Geometry	S. Benhimane
Thu, Nov 2, 2006	F	Field Trip to Siemens Medical
Thu, Nov 9, 2006	E	2D Projective Transformations & Conics	S. Benhimane
Thu, Nov 16, 2006	E	Homography estimation, Cross Ratio Computation and Applications	S. Benhimane
Thu, Nov 23, 2006	E	Non-linear Parameter Estimation	S. Benhimane
Thu, Nov 30, 2006	E	1st Intermediate test correction	M. Groher
Thu, Dec 7, 2006		no class due to Dies Academicus
Thu, Dec 14, 2006	E	Mosaicing, Parameter Estimation, Error Propagation	S. Benhimane
Thu, Dec 21, 2006	E	Self-calibration of the distortion of a zooming camera	S. Benhimane
Thu, Dec 28, 2006	E	no class due to Christmas holidays
Thu, Jan 4, 2007	E	no class due to Christmas holidays
Thu, Jan 11, 2007	E	Projection matrices	S. Benhimane
Thu, Jan 18, 2007	E	2nd Intermediate test correction	S. Benhimane
Thu, Jan 25, 2007	I	Programming assignement (questions/answers) room 03.13.043	S. Benhimane
Thu, Feb 1, 2007	F	Field Trip to BrainLAB
Thu, Feb 8, 2007	T	Final Exam 13:00-14:30 in 00.13.009A	M. Groher

Readings

• Primary Reading
  • Multiple View Geometry in Computer Vision by Richard Hartley & Andrew Zisserman

• General Introduction to 3D Computer Vision
  • Three-Dimensional Computer Vision by Olivier Faugeras
  • Computer Vision: A Modern Approach by David A. Forsyth & Jean Ponce
  • Introductory Techniques for 3-D Computer Vision by Emanuele Trucco & Alessandro Verri

• More Specific Readings
  • The Geometry of Multiple Images: The Laws That Govern the Formation of Multiple Images of a Scene and Some of Their Applications by Olivier Faugeras, Quang-Tuan Luong, Theodore H. Papadopoullos; MIT Press; 2001

Programming Assignment

• Text
  • Overview slide
  • General remarks
  • Detailed description
• Pix
  • here is a sequence of test images. There is no pure rotational movement between consecutive images, so feel encouraged to make your own images. the cooler the better...
    
    mosaic.zip