Ondokuz Mayıs Üniversitesi Bilgi Paketi - Ders Kataloğu

Description of Individual Course Units

Course Unit CodeCourse Unit TitleType of CourseYearSemesterECTS
HRT328 Computer Vision (EC 4) 927006 3 6 5
Level of Course Unit
First Cycle
Objectives of the Course
Instruction of computer vision techniques to develop automatic vision systems.
Name of Lecturer(s)
Yrd. Doç. Dr. Sedat Doğan
Learning Outcomes
  1. The student learns the computer vision and artificial intelligence concepts and their natures.
  2. Learns how to develop an automatic vision system.
  3. Understands the existence and the importance of the relations between geometry and the corresponding conceptual meaning.
  4. Uses the open source libraries of artificial intelligence, computer vision and artificial neural networks and also learns how to integrate these libraries to own programs.
Mode of Delivery
Formal Education
Prerequisites and co-requisities
Recommended Optional Programme Components
Recommended or Required Reading
Steger C et al. ,2007. Machine Vision Algorithms and Applications.Wiley-VCH, Weinheim.
Planned Learning Activities and Teaching Methods
Language of Instruction
Work Placement(s)
Course Contents
Computer vision, visual target tracking, target pointing, feature extraction, image matching and image matching methods.
Weekly Detailed Course Contents
Week Theoretical Practice Laboratory
1.The concepts of artificial intelligence and computer vision and their relations.
2.Epipolar geometry in computer vision: fundamental and essential matrices as well as homography.
3.Computer vision in real time applications.
4.3D vision, disparity and disparity maps in stereo images.
5.Image matching techniques and computer vision.
6.Optical flow: sparse and dense optical flow.
7.Dense point matching algorithms.
8.The philosophy of artificial intelligince, causalitiy and reasoning.
9.The concept of ontology, the ontological methods used for knowledge extraction from images.
10.Mid-term exam.
11.Perceptron models and learning algorithms.
12.The use of computer vision and artificial intelligence together to solve vision problems.
13.Computer vision, artificial intelligence and intelligent sensor networks.
14.The use of sensor networks for spatial data production and for emergency management.
Assessment Methods and Criteria
Term (or Year) Learning ActivitiesQuantityWeight (%)
Midterm Examination170
Project Preparation130
End Of Term (or Year) Learning ActivitiesQuantityWeight (%)
Final Examination1100
Term (or Year) Learning Activities40
End Of Term (or Year) Learning Activities60
Workload Calculation
ActivitiesQuantityTime(hours)Total Workload(hours)
Midterm Examination111
Final Examination111
Project Preparation12525
Self Study12020
Individual Study for Mid term Examination11515
Individual Study for Final Examination11515