Revision 5e052f0d7bda1ac0cc56b7284b108ab759234c18 (click the page title to view the current version)

Lecture Notes - AIS2204 Maskinsyn

Note The lecture plan as posted at the start of semester is last year’s schedule. There will not be any revolutionary changes, but it will be reviewed and amended as we go along.

Chapter 1-3. Introduction; 3D geometry and projections

Dates 21, 24, 28, and 31 August, and 4 and 7 September

# Session Notes Reading Keywords Status
1 Introduction Ma 2004:Ch 1 (Ch 2.1 and 2.3) Practical matters. Software installation. Recap of linear algebra. OK
2 3D Modelling Ma 2004:Ch 2, App A (SZ 2) 3D modelling, motion OK
3 3D Objects in Python Tutorials Homogeneous co-ordinates. General Rotations. 3D Transformations in Python OK
4 Image Formation Ma 2004:Ch 3-3.3.1 (SZ 6) (self-study) projection, lens/camera
5 Camera Calibration Ma 2004:Ch 3.3-3.3.3 (self-study) Calibration, Radial Distortion etc.
6 Three-week Recap Ma 2004:Ch 1-3 3D Motion and 2D Projections To be adapted to class need
7 Recap: Camera Calibration Ma 2004:Ch 3 Many students needed more time to get the calibration to work.

Note It could have been useful to do a session on Theorem 2.8, training proof reading skills.

Chapter 4. Feature Tracking

We need to interleave this with material from later blocks to have project tracker run over midterm. Study Technique may be a good candidate.

# Topic Reading Keywords Status
8 (14 Sep) Image Filters Convolution. Filters. Blurring.
9 Corner Detection Ma 2004:Ch 4.3, 4.A (SZ 4) Calculate Gradient. Harris Feature Detector.
10 (21 Sep) Tracking Features Ma 2004:Ch 4-4.2 Tracking of Features. Tracking of Edges.
11 SIFT Feature Matching. Feature Descriptor.
12 (28 Sep) Edges Ma 2004:Ch 4.4 Canny, connected components, line fitting
13 Colour Models
14 (5 Oct)
15 Project Tracker Multiscale Detection
16 (12 Oct) Self-Study Continue with Tracking Features - -
17 Recap Status, review, repetition

Chapter 5. Projective Reconstruction

# Topic Reading Keywords
7/2022 Pre- and co-image Ma 2004:Ch 3.3-3.4 Radial Distortion, Tangential Distortion
17 Relative Pose Ma 2004:Ch 5.1 Triangulation. Relative Pose. Essential Matrix.
18 Eight-point algorithm Ma 2004:Ch 5.2 Calculate Essential Matrix
19 Study Technique Ma 2004:Ch 5.1 Proof reading.
20 3D Reconstruction Ma 2004:Ch 5.1-2
21 Planar Scenes Ma 2004:Ch 5.3
22 Epipolar Geometry Ma 2004:Ch 5.1-3
  1. Study Technique should may be needed earlier. We introduced some fragments of this in 2022, but should possibly do more of it.
  2. Relative Pose is a little messy. It covers two things.
    • triangulation is poorly covered in the textbook and the notes, but the students need a recap from basic calculus
    • the essential matrix is preparation for the next session.
  3. Generally, the preliminary steps of the exploratory exercises should have been premade, to save time for the students. We have made some improvements in 2022, but we should do more.
  4. Algorithm implementation is difficult and require sample solutions. Some have been added in 2022, but may have to be incorporated earlier in the course.
  5. We need more examples with complete calculations

Chapter X. Machine Learning

# Topic Reading Keywords
23-24 Neural Networks Szeliski 2022 Chapter 5 Training. Testing
25 Statistics Evaluation, Standard Deviation
26 Regression

Last Week. Summary and Miscellanea

# Topic Reading Keywords
27 (23) Distorted Space Ma 2004:Ch 6.1-2
28 Recap The Entire Syllabus Questions & Answers

Other Material.

Old Material.

# Topic Reading Keywords
24/2021 Stratified Reconstruction Ma 2005:Ch 6.3-4
25/2021 Partial Scene Information Ma 2005:Ch 6.5
26/2021 Real World Reconstruction Ma 2004:Ch 11
27/2021 Continuous Motion Ma 2004:Ch 5.4
  1. Ma 2004 Chapter 10. Partial Scene Knowledge
    • This is referenced as a building block in Chapter 11.
  2. Ma 2004 Chapter 11.4.
  3. Ma 2004 Chapter 11.5. Keywords texture, visualisation