6th  Inverted  CERN School of Computing 2013
25-26 February, CERN
 

Introduction to Computer Vision

Lecturers:

Samuele Carli
Martin Hellmich

A few questions

  • How do we see the world?
  • What's a 3D camera? How does it work?
  • Will your car see better than you?
  • Does an optical illusion trick a computer?
  • Isn't computer vision just image processing?

All the answers at iCSC

This lecture gives an introduction to the problem of computer vision starting with a comparison of the human visual system to its artificial approximations.

It will give an overview of different example applications.

Later on it focuses on image acquisition processing techniques which are needed for higher level processing: basic entities representations, filters, transformations, image equalization and camera models.

Targeted audience :

This series of three lectures targets any computer scientists or physicists interested in better understanding the principles of computer vision.



Lecture 3

Theme: Introduction to Computer Vision


Lecture: Introduction to the human visual system and image pre-processing

A few questions addressed in the lecture

Monday  25 February

 

14:00 14:55

Lecture
3

Introduction to the human visual system and image pre-processing

Samuele Carli
Martin Hellmich

Description

This lecture gives an introduction to the problem of computer vision starting with a comparison of the human visual system to its artificial approximations.

It will give an overview of different example applications.

Later on it focuses on image acquisition processing techniques which are needed for higher level processing: basic entities representations, filters, transformations, image equalization and camera models.

Audience and benefits
This lecture targets everyone interested in the basic concepts behind vision, both human and artificial, as well as in basic image manipulation, filtering, enhancement and representation.

After this lecture the attendees are expected to have acquired a basic knowledge of the important concepts, properties and limitations of image acquisition systems and basic image manipulation techniques, and will be able to evaluate and compare different aspects of human and artificial vision systems.

Pre-requisite
This lecture can be followed by anyone having interest in the subject and basic knowledge in linear algebra and mathematics.
Nevertheless the main concepts explained in this lecture will be understandable by everyone.




Lecture 4

Theme: Introduction to Computer Vision


Lecture: Introduction to image feature detection and 3D reconstruction

A few questions addressed in the lecture

Monday  25 February

 

14:00 14:55

Lecture
4

Introduction to image feature detection and 3D reconstruction

Samuele Carli
Martin Hellmich

Description

This lecture introduces the concepts needed to obtain depth information from two or more images taken from slightly different angles.
It will cover the various steps necessary, from features detection and matching to triangulation techniques.

Audience and benefits
This lecture targets everyone interested in the basic concepts behind computer vision, how 3D cameras work and what are the necessary steps in order to reconstruction depth information.

After this lecture the attendees are able to understand the concepts behind 3D cameras (and movies) and are able to use this knowledge to mechanically reconstruct a scene as a cloud of 3D points.
They will be able as well to understand how stereo vision helps self-driving cars to estimate distances and avoid collisions.

Pre-requisite
This lecture can be followed by anyone having interest in the subject and with basic knowledge of linear algebra.

Lecture 1 of this lectures series is recommended if you are not familiar with the concepts of image manipulation and vision systems.
Nevertheless the main concepts explained in this lecture will be understandable
by everyone.





Lecture 5

Theme: Introduction to Computer Vision


Lecture: Introduction to object recognition and scene understanding

A few questions addressed in the lecture

Monday  25 February

 

16:30
17:25

Lecture
5

Introduction to object recognition and scene understanding

Samuele Carli
Martin Hellmich

Description

This lecture gives an introduction to object recognition. It expands the topic of stereo vision and describes different object recognition techniques, involving object discrimination through texture and geometric properties (like shape, occlusion and overlapping of objects) to perform both instance recognition and classification.
It gives a soft comparison between artificial recognition and how the human brain recognizes items in its environment.

Audience and benefits
This lecture targets everyone interested in the topic of artificial object recognitors and classifiers, as well as techniques for texture and geometric properties discrimination.

After this lecture the attendees are able to understand the main challenges which computer vision is facing as well as some of the basic ideas and musings behind existing and future solutions.

Pre-requisite
This lecture can be followed by anyone having interest in the subject and with basic knowledge of linear algebra. The preceding lectures of this series are recommended if you are not familiar with the concepts of image manipulation and vision systems or image's features detection and 3D reconstruction.
Nevertheless the main concepts explained in this lecture will be understandable by everyone..

 





     
  GPU computing and HEP  
Lecture 1
Lecture 2
  All lectures  
     
  Computer vision  
  Lecture 3  
  Lecture 4  
  Lecture 5  
  All lectures  
     
  Testing methods and tools  
Lecture 6
     
  Grid interpretation  
  Lecture 7  
     
  Programme overview  
  All lectures at iCSC2013  
  All questions addressed  
     
  Handouts  
     

 

Copyright CERN

Print version