R 558 home page
Fundamentals of Computer Vision     COMP 558
Fall 2018 
  ENGTR 1090, Tues. & Thurs. 8:35-9:55


Instructors

Professor Michael Langer
Office:        McConnell Engineering, rm. 329
Tel:             514-398-3740
Email:          langer@cim.mcgill.ca
Office Hours:           will change from week to week (see mycourses)


Professor Kaleem Siddiqi
Office:        McConnell Engineering, rm. 420
Tel:             514-398-3371
Email:          siddiqi@cim.mcgill.ca
Office Hours:     Thursdays, 11-12, McConnell 420 (updates announced on mycourses)
Announcements Resources and other links

Lecture Schedule

Introduction

  1. Course overview [M & K]

2D Vision: Image processing and representation

  1. RGB [M]
  2. Image filtering [M]
  3. Edge detection [M]
  4. Least Squares Estimation: lines & vanishing points [M]
  5. Robust Estimation: Hough & RANSAC [M]
  6. Scale space (Gaussian) [K]
  7. Features 1: corners, intro to histograms [K]
  8. Features 2: histogram-based (SIFT, HOG) [K]
  9. Features 3: learned features (CNN's) [K]
  10. Image Registration 1: translation (Lucas-Kanade) [K]
  11. Image Registration 2: affine [K]
  12. Tracking: histogram-based [M]

IN CLASS MIDTERM EXAM

3D Vision

  1. Linear perspective, camera translation [K]
  2. Vanishing points, motion field for camera rotation [K]
  3. finite camera rotation, homogeneous coordinates [K]
  4. Camera extrinsics and intrinsics [M]
  5. Least Squares methods (eigenspaces, SVD) [M]
  6. Camera Calibration, Homographies 1: plane in 2 views [K]
  7. Homographies 2: image stitching, rectification [K]
  8. Stereo and Epipolar Geometry [K]
  9. Stereo correspondence [M]
  10. Lighting and material [M]
  11. Photography [M]
  12. RGBD Cameras & Point Clouds [K]