Revision 8ea97d2677e61f5062f45eebec15248b0b04e630 (click the page title to view the current version)

Lecture Notes - AIS2204 Maskinsyn

Chapter 1-2. Introduction and 3D Modelling (two weeks)

Dates 25-26 August + 1-2 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 3D Modelling Part II Velocity transformations. Recap. Questions. To be adapted to class

Chapter 3. Image Formation (two weeks)

# Topic Reading Keywords
5 Image Formation Ma 2004:Ch 3-3.3.1 (SZ 6) projection, lens/camera
6 Camera Calibration Ma 2004:Ch 3.3-3.3.3 Calibration, Radial Distortion etc.
7 More Camera Mathematics Ma 2004:Ch 3.3-3.4 Radial Distortion, Tangential Distortion

Dates 8-9 and 15 September

Chapter 4. Feature Tracking (three weeks)

The material will be as given for this chapter, but it will be rearranged.

# Topic Reading Keywords
8 (new) Image Filters Convolution. Filters. Blurring.
9 (8) Corner Detection Ma 2004:Ch 4.3, 4.A (SZ 4) Calculate Gradient. Harris Feature Detector.
10 (9) Corner Detection continued new Multi-Scale Detection
11 (10) Tracking Features Ma 2004:Ch 4-4.2 Tracking of Features. Tracking of Edges.
12 (11) Edges Ma 2004:Ch 4.4
13-14 Self-Study Continue with Tracking Features
15 Tracking Features 2 Recap. Long project?
16 SIFT NB Feature Matching. Feature Descriptor.
  • 8 - 16 September
  • 9-12 - 22-23 and 29-30 September
  • 13-14 - 6-7 October - staff seminar - possibly self-managed work only
  • 20-21 - 13-14 October - midterm - regular teaching

Note Last year, session 12 was planned Self-Study due to staff seminar. Session 13-14 became self-study because of sick leave, and negligible progress was made this week.

Note from last year We should have had one session on blurring filters and similar techniques from image processing before starting on Corner Detection (Session 8). This would have made the introduction of signal differentiation smoother.

Chapter 5. Projective Reconstruction (two weeks ?)

This plan is tentative and may be shortened as well as rearranged.

# Topic Reading Keywords
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 Synthetic Experiment Ma 2004:Ch 5.1-2
21 Planar Scenes Ma 2004:Ch 5.3
22 Epipolar Geometry Ma 2004:Ch 5.1-3

Notes from last year

  1. Synthetic Experiment should be merged into Eight-point algorithm
  2. Study Technique should probably be done earlier in the semester
  3. 3D modelling took a lot of time. Many did not realise that they needed to find triangles. Rectangles mixed with triangles caused problems.
  4. Generally, the preliminary steps of the exploratory exercises should have been premade, to save time for the students.
  5. Algorithm implementation is difficult and require sample solutions

New. Machine Learning

TBC

Chapter 6 and 11. Projective Reconstruction (many weeks)

This will be shortened and probably based on different sources.

# Topic Reading Keywords
23 Distorted Space Ma 2004:Ch 6.1-2
24 Stratified Reconstruction Ma 2005:Ch 6.3-4
25 Partial Scene Information Ma 2005:Ch 6.5
26 Real World Reconstruction Ma 2004:Ch 11

Notes from last year

  1. We can skip Stratified Reconstruction and Partial Scene Information
  2. Distorted Space may be interesting as an introduction to inner product spaces.
  3. What can we make out of Real World Reconstruction?

Closure/Tentative

# Topic Reading Keywords
27 Continuous Motion Ma 2004:Ch 5.4
28 Tentative Seminar: Applications TBA TBC - we may decide to move on to feature tracking
  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