Syllabus

Introduction to computer vision
1. Introduction
2. Research in computer vision
Image formation
1. Pinhole camera
2. Projective geometry
  1. 2D geometry (translation, scaling and rotation)
  2. Homogeneous coordinates
  3. 3D projection
  4. Vanishing points and lines
  5. Camera matrix
    1. intrinsic and extrinsic parameters
Image processing and filtering
1. Image derivatives
2. Derivative approximation
3. Correlation
4. Convolution
5. Filtering and smoothing
  1. Linear filtering
  2. Gaussian filtering
Edge detection
1. Introductions
2. Prewit and Sobel edge detector
3. Laplacian of Gaussian (LoG) (Marr-Hildreth)
4. Gradient of Gaussian (Canny)
Interest points and corners
1. Introduction to interest points
2. Invariant local features
3. Corner detection, the basic idea
4. Harris corner detector
  1. Cross correlation and auto correlation
  2. Correlation and Sum os Square differences (SSD)
  3. Mathematics of Harris corner
  4. OpenCV and interest points
Local Image features
1. Scale invariant feature transform (SIFT)
  1. Scale space peak selection
  2. Key point localization
  3. Orientation Assignment
  4. Key point descriptor
  5. Matching key points
Histogram of Oriented Gradients (HoG)
1. Computing Gradients
  1. Centered difference
  2. Filter masks in x and y direction
  3. Gradient
    1. Magnitude and Orientation
Model filtering and RANSAC
Feature Tracking and Optical Flow
Machine learning in computer vision
1. Machine learning intro and clustering
2. Support Vector Machine

Google Sites

Report abuse