CS 6476 — Computer Vision

General resources

Here is the official course page.
An old version of the syllabus is here. A much older version of the syllabus is here, which contains links to old problem sets that you might want to give a stab at.

A good grasp of Numpy and OpenCV would go a long way. And as the official course page hinted, brush up on your linear algebra.

Please click on 'Files' below for the course slides.

List of Math and Stats concepts.

This is not a list of hard prerequisites, you could learn some of them while taking the class. But if you find that your are not familiar with most of these concepts, it might be a good idea to take a refresher/review class (Calc, Linear Algebra, Probability). Notice that most of these concepts are needed for many other classes like Machine Learning, Artificial Intelligence, Artificial Intelligence for Robotics, etc.

  • Equation of a line, slope of a line, y intercept
  • 3D coordinate system
  • Equation of a line in 3D
  • Equation of a plane
  • Similar triangles and their properties
  • Basic trigonometry - sin, cos, tangent, arctangent
  • Equation of a circle
  • Polar coordinates, Polar Coordinates representation of a line
  • Homogeneous Coordinates
  • Series
  • Real Numbers, Imaginary Numbers, Complex Numbers
  • Even function, Odd function
  • mean, median, mode
  • variance, standard deviation, standard error
  • normal distribution, Gaussian, circularly semetric Gaussian
  • vector, matrix, matrix addition, scalar matrix multiplication
  • vector cross product
  • vector dot product
  • matrix vector mutliplication
  • Transpose of matrix
  • Inverse of matrix
  • Diagonal Matrix
  • Identity Matrix
  • Determinant of a Matrix
  • Singular Matrix
  • Linear Subspaces https://www.khanacademy.org/math/linear-algebra/vectors-and-spaces/subspace-basis/v/linear-subspaces
  • Null Space
  • Rank of matrix
  • Basic Derivatives - instantaneous rate of change.
  • logarithm
  • First Derivative, Second Derivative
  • Integrals, Definite Integrals - area under a curve.
  • Partial Derivatives
  • Gradient, Laplacian(Laplace Operator)
  • Linear Independence
  • Basis of a vector space (Linear Algebra)
  • Orhtogonal Vectors
  • Sine Wave
  • Complex Numbers
  • Sinc function
  • Rotation Matrix around the Z Axis
  • Linear projections
  • Linear operator
  • Orthogonal Vectors, Orthogonal Spaces, Orthogonal Bases
  • Least squares approximation, Least Squares line fitting
  • Eigen Values, Eigen Vectors
  • Singular Value Decomposition
  • Taylor Expansion, Second Order Taylor Expansion
  • K-D trees
  • Combinatorics (what's the probabilty of having at least one girl if you have three children)
  • Homogenous Differential Equations
  • Solid angle
  • Delta Function
  • Law of Total Probability and Marginalization
  • Bayes Probability
  • Markov Models, Hidden Markov Models