School/Faculty/Institute |
Graduate School |
Course Code |
CSE 601 |
Course Title in English |
Advanced Computer Vision |
Course Title in Turkish |
İleri Bilgisayarla Görü |
Language of Instruction |
EN |
Type of Course |
Flipped Classroom |
Level of Course |
Advanced |
Semester |
Fall |
Contact Hours per Week |
Lecture: 3 |
Recitation: 0 |
Lab: 0 |
Other: 0 |
|
Estimated Student Workload |
190 hours per semester |
Number of Credits |
7.5 ECTS |
Grading Mode |
Standard Letter Grade
|
Pre-requisites |
None |
Expected Prior Knowledge |
Computer Vision |
Co-requisites |
None |
Registration Restrictions |
Only Doctorate Students |
Overall Educational Objective |
To become familiar with the fundamental concepts of Computer Vision, such as image formation, camera parameters, preprocessing, convolution, segmentation, edge and corner detection, line and ellipse fitting, image understanding and object recognition. |
Course Description |
This course covers advanced topics in computer vision. Major topics include Image formation, Camera models, image filtering and feature extraction, Two-view geometry, Shape from Stereo, Photometric stereo and shape from shading, optical flow, structure from motion and, alignment, tracking, segmentation, classification and recognition by deep learning. Students will learn basic concepts of computer vision as well as hands on experience to solve real-life vision problems. |
Course Description in Turkish |
Bu ders bilgisayarla görü konusunda ileri konuları içermektedir. Dersin temel konuları arasında görüntü oluşturma, kamera modelleri, filtreleme, öznitelik çıkarımı, iki bakışlı geometri, stereodan şekil bulma, fotometrik stereo, tonlamadan şekil bulma, optik akış, hareketten şekil bulma, hizalama, derin öğrenme kullanarak izleme, bölütleme, sınıflandırma ve tanıma yer almaktadır. Öğrenciler derste bir yandan bilgisayarla görünün temel kavramlarını öğrenirken diğer yandan gerçek dünya problemlerini çözebilecek düzeyde deneyim kazanacaklardır. |
Course Learning Outcomes and Competences
Upon successful completion of the course, the learner is expected to be able to:
1) Understand image processing methods in image formation, feature extraction, shape from X problems
2) Apply probability and statistics to solve problems in computer vision
3) Develop solutions for image classification, understanding and objects recognition problems
4) Develop solutions for computer vision problems by using deep learning methods
5) Communicate effectively by means of reports and presentations
6) Analyze and interpret data, and use analytic thinking to draw conclusions
7) Acquire and apply new knowledge as needed
|
Program Learning Outcomes/Course Learning Outcomes |
1 |
2 |
3 |
4 |
5 |
6 |
7 |
Relation to Program Outcomes and Competences
N None |
S Supportive |
H Highly Related |
|
|
|
|
Program Outcomes and Competences |
Level |
Assessed by |
Prepared by and Date |
, |
Course Coordinator |
TUNA ÇAKAR |
Semester |
Fall |
Name of Instructor |
Asst. Prof. Dr. TUNA ÇAKAR |
Course Contents
Week |
Subject |
1) |
Introduction |
2) |
Image formation |
3) |
Camera parameters |
4) |
Feature extraction – edges, lines, corners, blobs |
5) |
Model fitting and parameter estimation |
6) |
Shape from Stereo |
7) |
Shape from Shading |
8) |
Optical flow and structure from motion |
9) |
Deep learning – image enhancement and feature extraction |
10) |
Deep learning – semantic segmentation |
11) |
Deep learning – classification |
12) |
Deep learning – object recognition |
13) |
Deep learning – object recognition |
14) |
Term Project presentations |
15) |
Final Examination Period |
16) |
Final Examination Period |
Required/Recommended Readings | Computer Vision: Algorithms and Applications, Richard Szeliski, Springer Science & Business Media, 2010
Introductory Techniques for 3-D Computer Vision, by Emanuele Trucco, Alessandro Verri, Prentice-Hall, 1998
|
Teaching Methods | Lecturing and exercises in the classroom with computers. In-class exercises and 3 Projects will be carried out by students |
Homework and Projects | In-class exercises, 2 Projects, 2 Midterm exams, Term project |
Laboratory Work | Programming exercises |
Computer Use | For programming |
Other Activities | None |
Assessment Methods |
Assessment Tools |
Count |
Weight |
Quiz(zes) |
3 |
% 10 |
Project |
2 |
% 20 |
Midterm(s) |
2 |
% 40 |
Paper Submission |
1 |
% 30 |
TOTAL |
% 100 |
|
Course Administration |
gokmenm@mef.edu.tr
02123953600
Academic dishonesty and plagiarism will be subject to Law on Higher Education Article 54. |