Computer Vision

Educational Goals:: The aim of vision systems is to build a model of the environment based on the analysis of one or more images. The course provides an introduction to principles and fundamental algorithms used in order to create artificial vision systems.

News:: *** Thu 14/4/2016 class is suspended ***; *** Thu 4/2/2016 class will be held at 12:15 in Delta2B ***

Suggested books:: R.C. Gonzalez and R.E. Woods, "Digital Image Processing (3rd Edition)", Prentice Hall, 2007. ISBN 013168728X; E. Trucco and A. Verri. Introductory Techniques for 3D Computer Vision. Prentice-Hall, 1998; D. Forsyth, J. Ponce. Computer Vision. A Modern Approach. Prentice-Hall, 2002; R. Szeliski. Computer Vision. Algorithms and Applications. Springer, 2011.

Image Formation (slides);

Transformations in color-space (slides);

Interpolation (slides);

Filters (slides);

Frequency-Domain Filters (slides);

Edge detection (slides);

Point features (slides);

Color-Based Segmentation (slides); Mean Shift paper

Background Subtraction (slides)

Motion and Tracking (slides)

Old Results:

Course 2012

Assignment #1

Name	Matricola	Grade	Notes
Francesco Cagnin	840157	9/10	Good background. Analysis could be more thorough
Gianluca Caiazza	840009	10/10	Good background and analysis
Andrea Filippi	828746	9/10	Good background, limited analysis
Alessandro Gagliardi	833635	10/10	Good background and analysis
Marco Gasparini	840156	10/10	Good background and analysis
Murat Karaman	839585	9/10	Good background, limited analysis
Bandi Vinay Kumar	850634	7/10	Acceptable background. Analysis almost absent
Gaia Orsini	832985	10/10	Good background and analysis
Mara Pistellato	839976	10/10	Good background and analysis
Roberta Prendin	819575	10/10	Good background and analysis. Little known fact: conciseness is actually a virtue
Rocco Salvia	838737	9/10	Good background. Analysis could be more thorough
Dalila Ressi	839745	10/10	Good background and analysis

Assignment #2

Name	Matricola	Grade	Notes
Gianluca Caiazza	840009	10/10	Good background and analysis
Andrea Filippi	828746	9/10	Good background. Analysis could be more thorough
Murat Karaman	839585	8/10	Good background, limited analysis
Bandi Vinay Kumar	850634	8/10	Good background, limited analysis
Gaia Orsini	832985	10/10	Good background and analysis
Mara Pistellato	839976	10/10	Good background and analysis
Roberta Prendin	819575	10/10	Good background and analysis
Rocco Salvia	838737	9/10	Good background. Analysis could be more thorough
Dalila Ressi	839745	9/10	Good background. Analysis could be more thorough

Assignment #3

Name	Matricola	Grade	Notes
Gianluca Caiazza	840009	10/10	Good background and analysis
Andrea Filippi	828746	9.5/10	Good background and analysis (although better on snakes than on Ncut)
Alessandro Gagliardi	833635	/10
Gaia Orsini	832985	10/10	Good background and analysis
Mara Pistellato	839976	10/10	Good background and analysis
Roberta Prendin	819575	10/10	Good background and analysis
Rocco Salvia	838737	10/10	Good background and analysis
Dalila Ressi	839745	10/10	Good background and analysis

Assignment #4

Name	Matricola	Grade	Notes
Mara Pistellato	839976	10/10	Good work! (It is a very difficult dataset)
Gaia Orsini	832985	9.5/10	Good background and analysis. Lacks conclusions
Rocco Salvia	838737	10/10	Good background and analysis
Roberta Prendin	819575	10/10	Good background and analysis
Gianluca Caiazza	840009	10/10	Good background and analysis
Andrea Filippi	828746	7/10	Limited background and analysis
Dalila Ressi	839745	10/10	Good background and analysis

Final Mark

Name	Matricola	Grade
Mara Pistellato	839976	30/30^*
Gaia Orsini	832985	30/30^*
Rocco Salvia	838737	30/30^*
Roberta Prendin	819575	30/30^*
Gianluca Caiazza	840009	30/30^*
Andrea Filippi	828746	27/30
Dalila Ressi	839745	30/30^*
Alessandro Gagliardi	833635	30/30^*

* can take oral for "lode".