Public View

You are viewing the public version of the syllabus. If you have a SUNet account, you can view the richer version of the syllabus after logging in.

EE 417
Computer Vision

Faculty Faculty of Engineering and Natural Sciences
Semester Spring 2025-2026
Course EE 417 - Computer Vision
Time/Place
Time
Week Day
Place
Date
08:40-10:30
Tue
FASS-G006
Feb 16-May 22, 2026
10:40-11:30
Wed
FASS-G006
Feb 16-May 22, 2026
Level of course Undergraduate
Course Credits SU Credit:3, ECTS:6, Basic:1, Engineering:5
Prerequisites CS 201 or DSA 201
Corequisites EE 417L
Course Type Lecture

Instructor(s) Information

Erchan Aptoula

By appointment. Contact the TA first, and if the issue is not resolved send me an email to arrange a meeting. For questions about the course, please post them to SUcourse.

Course Information

Catalog Course Description
Image filtering, Image pyramids, Hough transform, Feature and corner detection, Content description, Learning and recognition, Warping, Homographies, Geometric camera models, Two view geometry and stereo, Structure from motion, Depth estimation, Optical flow, Object tracking
Course Learning Outcomes:
1. Upon successful completion of EE 417 Computer Vision, students are expected to be able to: - Discuss the main problems of computer vision, its uses and applications
2. - Design and implement various image transforms: point-wise transforms, neighborhood operation-based spatial filters, and geometric transforms over images
3. - Design and implement several feature extraction algorithms including edges and corners
4. - Design and implement line and circle detection using Hough transform
5. - Calibrate real cameras and determine both intrinsic and extrinsic parameters,
6. - Formulate and solve 2D optic flow problem
7. - Establish correct correspondence for stereo images using a correlation based matching technique
8. - Estimate the essential/fundamental matrix and determine extrinsic parameters (rotation and translation) of a stereo vision system
9. - Reconstruct 3D structure from 2D images using estimated extrinsic parameters
10. - Identify or recognize objects from images
Course Objective
This course provides a broad introduction into computer vision. It is divided into three modules. The first is recognition and localization (2D image processing and analysis), the second is geometry for vision (3D vision) and the third is about temporal vision. The first module covers basic spatial image filtering and convnets followed by their adaptation to object detection and segmentation. The second module is about 3D vision presenting methods that are industry standards. The course ends with a brief module on temporal vision covering optical flow and multi-object tracking.
Sustainable Development Goals (SDGs) Related to This Course:
Industry, Innovation and Infrastructure

Course Materials

Resources:
A. Torralba, P. Isola, W. Freeman, Foundations of Computer Vision, MIT Press, 2024
R. Klette, Concise Computer Vision: An Introduction into Theory and Algorithms, 2014.
V. K. Ayyadevara and Y. Reddy, Modern Computer Vision with PyTorch, 2nd Ed, 2024 (Optional reading)
Gonzales and Woods, Digital Image Processing, 4th Ed, 2017 (Optional reading)
R. Szeliski, Computer Vision and Applications, 2010 (Optional reading)
R. Hartley and A. Zisserman, Multiple view geometry in computer vision, 2nd Ed, 2000 (Optional reading)
Technology Requirements:

Policies