Ders bilgi formları arşivlenmiştir ve bilgi amaçlıdır. Güncel ders bilgi formlarına ulaşmak için Akademik Bilgi Sistemi'ni (https://obs.gtu.edu.tr/) ziyaret ediniz.

Course information packages are for archival purposes only. For up-to-date course information packages, please visit Academic Information System (https://obs.gtu.edu.tr/).

• Basic information
• Learning outcomes
• Contents
• Assessment
• Workload

Basic information
Course title:	Multiview Geometry For Computer Vision
Course code:	CSE 666
Lecturer:	Prof. Dr. Yusuf Sinan AKGÜL
ECTS credits:	7.5
GTU credits:	3 (3+0+0)
Year, Semester:	2, Fall and Spring
Level of course:	Second Cycle (Master's)
Type of course:	Area Elective
Language of instruction:	English
Mode of delivery:	Face to face , Group study , Lab work
Pre- and co-requisites:	CSE 665
Professional practice:	No
Purpose of the course:	To teach the geometric relations between multiple views of scenes and the general principles of parameter estimation.

Learning outcomes

Upon successful completion of this course, students will be able to:

1. Solve the the geometric relations between multiple views of scenes

   Contribution to Program Outcomes

   1. Define and manipulate advanced concepts of Computer Engineering
   2. Formulate and solve advanced engineering problems
   3. Use advanced knowledge of mathematics, science, and engineering
   4. Review the literature critically pertaining to his/her research projects, and connect the earlier literature to his/her own results
   5. Work effectively in multi-disciplinary research teams
   6. Acquire scientific knowledge
   7. Design and conduct research projects independently
   8. Continuously develop their knowledge and skills in order to adapt to a rapidly developing technological environment,
   9. Find out new methods to improve his/her knowledge.

   Method of assessment

   1. Written exam
   2. Homework assignment
2. List the techniques for parameter estimation

   Contribution to Program Outcomes

   1. Define and manipulate advanced concepts of Computer Engineering
   2. Formulate and solve advanced engineering problems
   3. Review the literature critically pertaining to his/her research projects, and connect the earlier literature to his/her own results
   4. Work effectively in multi-disciplinary research teams
   5. Acquire scientific knowledge
   6. Design and conduct research projects independently
   7. Continuously develop their knowledge and skills in order to adapt to a rapidly developing technological environment,
   8. Find out new methods to improve his/her knowledge.

   Method of assessment

   1. Written exam
3. Solve the camera scene relation problems from images

   Contribution to Program Outcomes

   1. Define and manipulate advanced concepts of Computer Engineering
   2. Formulate and solve advanced engineering problems
   3. Use advanced knowledge of mathematics, science, and engineering
   4. Review the literature critically pertaining to his/her research projects, and connect the earlier literature to his/her own results
   5. Work effectively in multi-disciplinary research teams
   6. Acquire scientific knowledge
   7. Design and conduct research projects independently

   Method of assessment

   1. Homework assignment

Contents
Week 1:	Intro and Motivation
Week 2:	2D Projective Geometry
Week 3:	3D Projective Geometry
Week 4:	Estimation (2D homography)
Week 5:	Camera models
Week 6:	Camera calibration
Week 7:	The epipolar geometry Midterm exam
Week 8:	3D reconstruction
Week 9:	Computing the F matrix
Week 10:	Computing the F matrix
Week 11:	Rectification and structure reconstruction
Week 12:	Rectification and structure reconstruction
Week 13:	Planes and homographies
Week 14:	Self-Calibration
Week 15*:	Self-Calibration and Multi-View Reconstruction
Week 16*:	Final exam
Textbooks and materials:	"Multiple View Geometry in Computer Vision" by Richard Hartley and Andrew Zisserman
Recommended readings:	“Computer vision: A Modern Approach,” David A. Forsyth, Jean Ponce
	* Between 15th and 16th weeks is there a free week for students to prepare for final exam.

Assessment
Method of assessment	Week number	Weight (%)
Mid-terms:	7	30
Other in-term studies:		0
Project:		0
Homework:	1-12	30
Quiz:		0
Final exam:	16	40
	Total weight:	(%)

Workload
Activity	Duration (Hours per week)	Total number of weeks	Total hours in term
Courses (Face-to-face teaching):	3	14
Own studies outside class:	3	14
Practice, Recitation:	0	0
Homework:	7	10
Term project:	0	0
Term project presentation:	0	0
Quiz:	0	0
Own study for mid-term exam:	10	1
Mid-term:	1	1
Personal studies for final exam:	15	1
Final exam:	2	1
		Total workload:
		Total ECTS credits:	*
	* ECTS credit is calculated by dividing total workload by 25. (1 ECTS = 25 work hours)