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) | Relative Pose | Ma 2004:Ch 5.1 | Triangulation. Relative Pose. Essential Matrix. | |
| 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 | Status |
|---|---|---|---|---|
| 18 (19 Oct) | Eight-point algorithm | Ma 2004:Ch 5.2 | Calculate Essential Matrix | OK |
| 19 | Study Technique | Ma 2004:Ch 5.1 | Proof reading. | OK |
| 20 (26 Oct) | Planar Scenes | Ma 2004:Ch 5.3 | ||
| 21 (30 Oct) | Epipolar Geometry | Ma 2004:Ch 5.1-3 | ||
| 22 | self study 3D Reconstruction | Ma 2004:Ch 5.1-2 | Continuous on 18 Eight-point algorithm using real image data | OK |
Chapter X. Machine Learning
| # | Topic | Reading | Keywords |
|---|---|---|---|
| 23-24 | Neural Networks | Szeliski 2022 Chapter 5 | Training. Testing |
| 25 | Statistics | Evaluation, Standard Deviation | |
| 26 | Object Detection | Szeliski 2022 Chapter 6 (6.3 in particular) | Object Detection |
| 27 | Regression | ||
| 28 | Distorted Space + Recap | Ma 2004:Ch 6.1-2 | Questions; Answers; module evalutaiton |
Other Material.
- Overview of Python Demoes
- The material is under constant review.
- Any feedback is welcome.
- Existing notes for Review
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 |
- Ma 2004 Chapter 10. Partial Scene Knowledge
- This is referenced as a building block in Chapter 11.
- Ma 2004 Chapter 11.4.
- Ma 2004 Chapter 11.5. Keywords texture, visualisation
