Computer Vision (SE 461)
Fall 2014
Dr. Nazar
Khan
Lectures:
|
Morning Session (Room 15) |
Afternoon Session (Room 15) |
Monday |
09:45 am - 11:10 am |
01:00 pm - 02:30 pm |
Wednesday |
09:45 am - 11:10 am |
01:00 pm - 02:30 pm |
Office Hours:
Thursday |
2:00 pm - 06:00 pm |
Programming Environment:
Matlab
Grading Scheme/Criteria:
Assignments and Quizes |
10% |
Project |
15% |
Mid-Term |
35% |
Final |
40% |
Assignments
- Assignment
1 (Due: Monday, 17th November, 2014 before class)
- Assignment
2 (Due: Monday, 1st December, 2014 before class) First
group/person to email me the identity of the person in
"mystery.png" alongwith the cleaned up image will win
this semester's "Fourier Challenge"!
Winner of Fall2014
semester: Fazeela Tariq (BSEF10M046)
- Assignment
3 (Due: Monday, 12th January, 2015 before class)
- Assignment 4 (Due: Monday, 26th January, 2015 before class)
- Assignment 5 (Due: Monday, 2nd February, 2015 before class)
- Assignment 6 (Due: Sunday, 8th February, 2015 11:59 pm)
Content
- Introduction
- Computer Vision vs. Image Processing vs. Computer
Graphics
- Computer Vision vs. Biological Vision -- The Grand
Deception!
- Successful Computer Vision solutions.
- Image Processing
- 2D Computer Vision
- Edge
Detection
- Corner
Detection
- Moravec Corner Detector
- Harris Corner Detector
- Structure Tensor -- Geometry and Algebra
- Hough
Transform
- 2D
Spatial Transformations
- Matrix ≡ Linear Transformation
- Scaling, Shear, Rotation
- Translation is not linear in ℝ^2
- Homogenous Coordinates make translation linear in ℙ^2
- 2D Affine Transformation (Scaling, Shear, Rotation, Translation)
- Recovering best affine transformation from correspondences
- Affine Image Warping
- 2D Projective Transformation (Homography)
- Recovering best projective transformation from correspondences -- Direct Linear Transform (DLT)
- Projective Image Warping
- Optic Flow
- Greyvalue/Brightness Constancy Assumption
- Linearised Optic Flow Constraint via Taylor's Approximation
- Aperture Problem and Normal Flow
- Local Methods
- Spatial approach of Lucas and Kanade
Spatio-temporal approach of Biguen et al.
- Global Methods
- Variational method of Horn and Shunck
Global
Flow
SIFT and its applications
- 3D Computer Vision
- Projective
Geometry and Camera Models
- Pinhole Camera Geometry
- Camera Matrix = Intrinsic x Projection x
Extrinsic
- Camera Models
- Camera Matrix Anatomy
- Camera Calibration
- Stereo
Reconstruction
- Orthoparallel Cameras
- Converging Cameras
- Epipolar Constraint and Fundamental Matrix
- Estimation of Fundamental Matrix
- Disparity Estimation
Shape
from Shading
Structure from Motion
- Machine Learning for Computer Vision
|