CAP5415 - Computer Vision
Fall 2005
Monday Wednesday 3pm-4pm
Instructor: Dr. Alper Yilmaz (yilmaz at cs.ucf.edu)
Room: CSB 250
Office Hours: 2pm-3pm Monday Wednesday
1. Introduction and course objectives
2. Lecture 2 (August 24, 2005)
• Imaging geometry, perspective projection etc.
• Reading from Course text book pp. 26-40
• Homework assignment (due date: September 7, 2005)
3. Lecture 3 (August 31, 2005)
• Imaging geometry, affine camera models, radial distorsion
• Estimating camera parameters
• Rotation around arbitrary axis
• Homework assignment (due date: September 14, 2005)
• CORRECTION:  2nd slide rotation matrices are corrected!
• In last class and today's slides the rotations were defines as follows:
• Rotation around z-axis is in the counter-clock wise direction
• Rotation around x-axis is in the clock wise direction
• Rotation around y-axis is in the clock wise direction
• Now it is updated to be counter clock wise in all 3 axis. In your assignments you can do it either way.
• Another correction is in the matrix notation of the intrinsic camera parameters. ox and oy should be on the last column of the matrix. (new)
4. Lecture 4 (September 7, 2005)
• Binary, gray level and color images.
• Image noise.
• Derivatives, filtering.
5. Lecture 5 (September 12, 2005)
• Blurring, noise removal.
• Image derivatives and edge detection.
• Programming assignment (due date: September 19, 2005)
• Image Viewer for windows
• Sample image
• Implementation of sobel and prewitt edge detector.
• Deliverables:
• Report: For both sobel and prewitt the report should include blurred images in x and y directions, derivative images in x and y directions, the gradient magnitude as image, and the edge maps for various thresholds.
• Source code.
6. Lecture 6 (September 14, 2005)
• Marr Hildrett edge detector.
• Canny edge detector.
• Homework assignment (due date: September 28, 2005).
• 1st Programming Project (due date: October 17, 2005)
• Implementation of Canny Edge Detector.
7. Lecture 7 (September 19, 2005)
• Region segmentation
• Connected component analysis
• Reading: Chapter 3 from Dr. Shah's lecture notes
• Programming assignment (due date: September 28, 2005)
• Sample image
• Implementation of histogram based segmentation.
• Deliverables:
• Report: Show the histograms after smoothing 5 times with a gaussian filter (.05 .25 .40 .25 .05), and show the resulting binary region images.
• Hardcopy of the source code.
8. Lecture 8 (September 21, 2005)
• Image segmentation: seed segmentation, region growing, region split and merge.
• Likelihood ration test and phagocyte algorithm.
• CORRECTION:  Likelihood ratio test is corrected!
• The ratio is P(H2)/P(H1)
9. Lecture 9 (September 26, 2005)
• Region properties (segments in an image or objects).
• Area, centroid, perimeter, moments, compactness, orientation.
• Homework assignment (due date: October 10, 2005)
• Look at lecture 10 slides
10. Lecture 10 (September 28, 2005)
• Derivation of  orientation (elongation) of a region
• Gaussian Pyramid
• Laplacian Pyramid
• Programming assignment (due date: October 12, 2005)
• Lenna image
• Implementation of Gaussian Pyramid.
• Deliverables:
• Report: Write a report showing all the resolutions of Gaussian pyramid at least on two different examples.
• Hardcopy of the source code.
11. Lecture 11 (October 3, 2005)
• Review
12. Mid-Term Exam 1 (October 5, 2005)
13. Lecture 12 (October 10, 2005)
• Hough Transform
• Line fitting
• Reading: Section 5.2 from text book
• Programming assignment (due date: October 26, 2005)
• Sample image
• Implementation of Hough transform. Your program should use the one of the  edge detectors you have written to find the edges first, than apply Hough transform on the edgemap
• Deliverables:
• Report: Write a report which shows the detected edges, and the (theta,rho) voting matrix.
• Hardcopy of the source code.
14. Lecture 13 (October 12, 2005)
• Hough Transform (continued).
• Circle fitting
• Generalized hough transform.
• Medial axis transform
• Interest point detectors
15. Lecture 14 (October 17, 2005)
• Optical flow
• Horn and Schunk.
• Schunk
16. Lecture 15 (October 19, 2005)
• Global Motion
• Anandan's approach
• Programming assignment (due date: November 16, 2005)
• Sample images flower garden sequence <mpeg>
• Implementation of Lucas Kanade. Create 2 levels of pyramid and for each level compute optical flow independently.
• Deliverables:
• Report: Write a report which shows the input images, and computed flow fields for each pyramid level independently. You can use matlab "quiver" function to show the flow field.
• Hardcopy of the source code.
17. Lecture 16 (October 26, 2005)
• Block based optical flow
• Token based optical flow
18. Lecture 17 (November 1, 2005)
• Structure from motion
• Orthographic displacement model
• Perspective displacement model
• Hager, Jepson's approach
• Homework assignment (due date: November 9, 2005)
• 2nd Programming Project (due date: December 5, 2005)
• Implementation of Anandan's approach for global motion compensation.
• Sample test images head sequence, claire sequence.
• See slides for deliverables.
19. Lecture 18 (November 3, 2005)
• Stereopsis
• Simple stereo system
• Token based stereo
• Marr-Pogio approach
• Correlation based stereo
• Barnard's approach
20. Lecture 19 (November 7, 2005)
• Revisit Programming project #2
21. Lecture 20 (November 9, 2005)
• Revisit Generalized Hough Transform
• Revisit Motion
22. Lecture 21 (November 14, 2005)
• Epipolar Geometry
• Essential Matirx
• Fundamental Matrix and their derivation
23. Lecture 22 (October 16, 2005)
• Review
24. Midterm Exam 2 (21 November 2005)
25. Lecture 23 (November 28, 2005)
• Image segmentaion using graph cuts
26. Last day for bonus assignment is Friday 4pm.
27. FINAL December 7, 2005, Time 1.00pm-3.50pm., Place: Regular classroom

Course Goal
This course is introductory level. It will cover the basic topics of computer vision, and introduce some fundamental approaches for computer vision research.

• Imaging Geometry
• Camera Modeling and Calibration
• Filtering and Enhancing Images
• Region Segmentation
• Color and Texture
• Line and Curve Detection
• Shape Analysis
• Stereopsis
• Motion and Optical Flow
• Structure from X
• Grading Policy (Updated 11 September 2005)
Biweeky Assignments: 20%
Programming Assignments: 20%
Programming Projects: 20%
Mid-Term Exam: 20%
Final Exam: 20%