Course Details

COMPUTER VISION

COMP431

Return to Classes
Course Information
SemesterCourse Unit CodeCourse Unit TitleT+P+LCreditNumber of ECTS Credits
7COMP431COMPUTER VISION0+3+055

Course Details
Language of Instruction English
Level of Course Unit Bachelor's Degree
Department / Program COMPUTER ENGINEERING
Type of Program Formal Education
Type of Course Unit Elective
Course Delivery Method Face To Face
Objectives of the Course Introducing basic basic image processing and computer vision techniques.
Discussing the foundations of image formation, measurement, analysis, object representations.
Explaining the theoretical knowledge and practical applications of common and the state of the art CV and approaches.
Course Content This course introduces students to foundational methods, algorithms commonly used in computer vision field and discusses their applications. In relevant subjects, most popular deep learning based methods takes place. The topics include digital image processing basics such as histogram equalization, neighborhood operations and filtering; feature detection, extraction and matching, SIFT, Hough transform, stereo and epipolar geometry, image to image projections, Homographies and mosaics, projective geometry, essential and fundamental matrix, camera calibration, object detection, recognition and segmentation using classical methods as well as more modern deep learning based approaches. The students will have hands on experience and ability to discuss of theoretical aspects of the methods.
Course Methods and Techniques This course starts with basic digital image processing steps such as histogram equalization and neighborhood-based filtering; continues with feature detection-extraction-matching algorithms such as SIFT, Hough transform and similar. Then, projective relationships of multiple images are examined through stereo-epipolar geometry, homography and mosaicking techniques; three-dimensional reconstruction is performed with camera calibration, fundamental and eigen matrix concepts. In the last part, modern deep learning solutions for object detection, recognition and segmentation are discussed with classical approaches as well as convolutional neural networks and Transformer-based models.
Prerequisites and co-requisities None
Course Coordinator Associate Prof.Dr. Rifat Kurban - rifat.kurban@agu.edu.tr
Name of Lecturers Associate Prof.Dr. Rifat Kurban - rifat.kurban@agu.edu.tr
Assistants None
Work Placement(s) No

Recommended or Required Reading
Resources Computer Vision: Algorithms and Applications, 2nd ed.
Computer Vision: Algorithms and Applications, 2nd ed.
2022 Richard Szeliski, The University of Washington
Computer Vision: Algorithms and Applications, 2nd ed.
-
-

Course Category
Mathematics and Basic Sciences %30
Engineering %40
Engineering Design %20
Social Sciences %0
Education %0
Science %0
Health %0
Field %10

Planned Learning Activities and Teaching Methods
Activities are given in detail in the section of "Assessment Methods and Criteria" and "Workload Calculation"

Assessment Methods and Criteria
In-Term Studies Quantity Percentage
Ödev 5 % 50
Sunum/Seminer 1 % 50
Total
6
% 100

 
ECTS Allocated Based on Student Workload
Activities Quantity Duration Total Work Load
Araştırma Ödevi 1 133 133
Ev Ödevi 5 10 50
Senkron Ders 14 3 42
Total Work Load   Number of ECTS Credits 7,5 225

Course Learning Outcomes: Upon the successful completion of this course, students will be able to:
NoLearning Outcomes
1 Gaining knowledge about current computer vision research problems
2 Gaining the ability to implement and apply the basic image processing techniques
3 Gaining the ability to calculate the 2D projection of 3D objects in camera scenes
4 Gaining the ability to calibrate an image and extract the camera calibration matrix
5 Gaining the skill of object matching including feature extraction, matching using SIFT
6 Gaining the skill of object tracking using optical flow and others
7 Gaining the ability of segmenting an image
8 Gaining the ability of using deep learning in CV problems such as object recognition
9 Gaining the ability to initiate a research in computer vision related field


Weekly Detailed Course Contents
WeekTopicsStudy MaterialsMaterials
1 Introduction, Image Processing, Histogram Equalization - -
2 Image Proccessing Cont'd: Neighbourhood Operations, Filtering Spatial and Frequency domains, - -
3 Harris Corner Detection, SIFT ( Feature detection, extraction) - -
4 SIFT matching ( Feature matching, application) - -
5 Dense Motion Analysis: Optical Flow - -
6 Image Segmentation - -
7 Fall Break - -
8 Midterm - -
9 Active learning week - -
10 Homography, Image plane to image plane projections, Essential and Fundamental Matrices - -
11 Stereo matching, 3D mapping SLAM - -
12 Object Recognition (Face recognition) - -
13 Deep learninig in CV: Major structures and applications - -
14 Review and emerging technologies, Edge CV, embedded CV etc. - -
15 Final - -


Contribution of Learning Outcomes to Programme Outcomes
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12 P13 P14 P15
All 3 4 4 3 3 3 4 1 2 1 1
C1 5 5 4 5 4 3 4 2 3 2 2
C2 2 4 3 2 2 3 4 2 1 1 1
C3 2 4 3 2 2 4 4 1 1 1 1
C4 2 4 4 2 2 4 4 1 1 1 1
C5 2 4 3 2 2 3 4 1 1 1 1
C6 2 4 3 2 2 3 4 1 1 1 1
C7 2 4 3 2 2 3 4 1 1 1 1
C8 4 5 4 4 3 4 4 1 2 2 2
C9 5 4 5 5 5 4 5 3 4 2 3

Contribution: 1: Very Slight 2:Slight 3:Moderate 4:Significant 5:Very Significant


https://sis.agu.edu.tr/oibs/bologna/progCourseDetails.aspx?curCourse=74881&lang=en
Return to Classes