COMPUTER VISION (2/2 Credits)

Learning Outcomes:

On successful completion of this course, students will be able to: LO1 – describe Various computational principles and standard image processing operators in computer vision; LO2 – apply Techniques of image filtering, feature detection, and geometric transformation for visual analysis; LO3 – integrate Components of a computer vision pipeline (feature ? geometry ? motion) into an end-to-end working system; LO4 – evaluate Classical computer vision algorithms (e.g., Harris, SIFT, Epipolar Geometry, Optical Flow) using Python and OpenCV.

Topics:

1. Introduction to Computer Vision;
2. Image Filtering & Enhancement;
3. Feature Detection I – Interest Points;
4. Feature Detection II – Descriptors & Matching;
5. Image Alignment & Homography;
6. Camera Models & Calibration;
7. Epipolar Geometry;
8. Stereo Vision;
9. 3D Reconstruction;
10. Motion Analysis – Optical Flow;
11. Feature-Based Tracking;
12. Motion Applications;
13. Final Project Presentation;
14. Image I/O & Color Manipulation;
15. Filtering & Edge Detection;
16. Corner Detection;
17. Feature Extraction & Matching;
18. Image Alignment;
19. Camera Calibration;
20. Epipolar Geometry Visualization;
21. Depth Estimation;
22. 3D Triangulation;
23. Optical Flow Implementation;
24. Feature Tracking;
25. Motion Segmentation & Stabilization.