Advanced Vision - Syllabus / Lecture Plan
All textbook readings are inclusive! (i.e. from Section X-Y means include Y in your reading).
All movie examples should work under DICE using mplayer <filename>
command.
- Imaging Overview / 2D Geometry review / 2D geometric modeling
Lecture Note 0: [PDF]
Time lapse video example: [WMV]
Lecture Problem Solution: [PDF]
Reading:
- Ensure familarity with the IVR course vision techniques
- Course textbooks (one of):
- Davies: 1.1-1.3 / 2.1 / 21.2
- Morris: 1.1-1.3 / 2.1-2.3 / 2.5 / 3.6.1
- Forsyth/Ponce: 1.3-1.4 / 2.1
- Szeliski: 2
Examples (in matlab): RGB Image display;
RGB to Grayscale conversion
Online:
Color images;
Greyscale images;
Pixels;
Images;
Informatics New Building Timelapse Videos (updated daily)
- System 1 - Geometric Recognition of Flat Parts (2D):
Lecture Note 1: [PDF]
Model-based object recognition: Boundary Extraction, Boundary Segmentation,
Model Matching, Pose Estimation, Verification
Reading:
- Course textbooks (one of):
- Davies: 4.3-4.4 / 6.11 / 7.2 / 22.1-22.4 / 22.7-22.8 / 22.12 (Chapter 5 - edge detection)
- Morris: 4.1-4.2 / 5.2 / 5.4 / 6.3-6.3.2
- Forsyth/Ponce: Chapter 8 - edge detection
- Szeliski: 4.2, 6.1, 6.2, 14.3
Examples (in matlab):
mybwperim.m;
Example code for lecture content;
Online:
Thresholding;
Edge Grouping Introduction;
Boundary Connectivity;
Edge Tracking;
Boundary representation introduction;
Parametric boundary representations;
Tree Search Methods for Model Matching;
Interpretation Tree Algorithm (N.B. example is best first search, in lectures we did depth first search);
Online java applet example of Interpretation Tree based edge matching (explanation of task);
- System 2 - Tracking a falling 2D object : Condensation Tracking
Lecture Note 2: [PDF] Ball Condensation Tracking [MPG] Adaptive Change Detection [MPG]
Reading:
- Course textbooks (one of):
- Davies: 18.13 (18.8-18.9 for background)
- Morris: 9.3.1 / 9.3.2 / 9.4.3 / 9.4.4
- Forsyth/Ponce: 14.3 / 17.3 / 17.5 (Chapter 17 intro, 17.1-17.2 for background) / Section 2.2 of this extra chapter (not in book)
- Szeliski: -
Examples (in matlab): Example code for ball tracking Online Demos
Online:
Kalman Filtering - concept detail
Traffic and Pedestrian Tracking; People Tracking [MPG] [MPG]
Online:
The Condensation Algorithm;
- System 3 - Persistent Tracking and Behaviour Recognition
Lecture Note 3: [PDF]
Reading:
-
A. A. Efros, A. C. Berg, G. Mori, J. Malik,
"Recognizing Action at a Distance",
Proc. IEEE Int. Conf. on Computer Vision, Nice, Vol 2, pp 726-733, Oct 2003.
-
Pedro M. Jorge, Arnaldo J. Abrantes, Jorge S. Marques.
"On-line Object Tracking with Bayesian Networks".
International Workshop on Image Analysis for Multimedia Interactive Systems,
Lisbon, April 2004.
- System 4 - Modeling and Recognizing Classes of Shapes : PCA and PDM
Lecture Note 4: [PDF]
Reading:
- Course textbooks (one of):
- Davies: 24.10 (PCA) 24.12 (Face Recongition)
- Morris: 3.4.4 (PCA) 7.3.1-7.3.2 (PCA images)
- Forsyth/Ponce: 22.3.1-22.3.3
- Szeliski: 14.2
Examples (in matlab):
Example code for "T" recognition via PCA/PDM;
Example code for Eigen faces (external)
Online:
PCA;
Point Distribution Models (PDM);
PCA Representations;
SVD (general);
Gaussian Noise
Eigen faces : 1
2
3
Eigen faces : original Turk/Pentland paper (1991)
Online: Mahalanobis Distance;
- System 5 - 3D Object Recognition from Stereo Image Data : Feature Detection
Lecture Note 5: [PDF]
Reading:
- Course textbooks (one of):
- Davies: 3.2 / Chapter 5 / 7.1.1 / 16.3.1 / 16.3.2 / 21.3-21.4 / 21.7 / 21.12-21.13 / Appendix A.6
- Morris: 3.3.3 / 3.5.2 / 5.5.3 / 6.5.2
- Forsyth/Ponce: 3.2 / 7.1.1/ 8.2.3 / 10.1.1 / 11.1-11.4 / 15.5.2
- Szeliski: 4,6.1,6.2,11
Examples (in matlab): edge function;
smoothing (via fspecial function);
Example code for stereo wedge recognition
Online: Edge Detectors; Canny Edge Detector;
Gaussian smoothing;
RANSAC; Stereo Vision Overview;
Convolution - IVR lecture 1
Stereo Vision Overview; Stereo Imaging Intro.;
Another view on Stereo; Ballard & Brown - Section 3.4.1 ;
Dense Stereo Matching; Online Comparison of Dense Stereo Approaches;
Dimensional Imaging Website,
SIFT
- System 6 - 3D Object Recognition from Range Data : Range Sensors & Differiential Geometry
Lecture Note 6: [PDF] 3D cola bottle [MPG] Laser Scanner [WMV]
Reading:
- Course textbooks (one of):
- Davies: 16.1-16.2 16.8, 16.9 (16.10-16.12 - background only) 16.13 16.14
- Morris: nothing appropriate
- Forsyth/Ponce: 21.1 / 21.2 / 21.4.1
- Szeliski: 12.2
Examples (in matlab):
Example code for wedge recognition;
Movie of matlab code execution and segmentation by region growing [MPG
Online:
Range Images (depth maps) 1;
Range Images 2;
Time of Flight Scanners;
Triangulation based scanners;
Section 8.7 of Machine Vision - David Vernon;
Curvature Classification;
Planar Fitting
interpetation tree + lecture 3 links; Scalar Triple Product
[Breckon/Fisher '04] - Detecting changes in 3D scenes using simple methods
There are also some review materials based on the IVR course, useful
for reviewing some MATLAB and elementary image analysis:
- Image capture and flat part recognition
[PDF]
- Thresholding and background removal
[PDF]
- Invariant Shape Descriptors
[PDF]
- Basic Object Recognition
[PDF]
- Active Vision Techniques
[PDF]
- Visual Servoing
[PDF]
[AV home page]
This page is maintained by the course lecturer, Bob Fisher,
rbf@inf.ed.ac.uk
,
room IF 1.26, ext 513441