1
Computer Vision
CS 682
Jana Kosecka
http://cs.gmu.edu/~kosecka/cs682.html
2-9827
Logistics
•Grading: Homeworks (about every 2 weeks) 30% Midterm: 30% Fin al
project: 40%
•Prerequisites: linear algebra, calculus
•Required Text:
• From Ima ges to Geometr ic Models: Y. Ma, S. Soatto, J.Kosecka an d S.
Sastry, Springer Verlag 2003
• Introductory Techniques for 3D Computer Vis ion
(E. Trucco, A. Verri, Prentice Hall, 1998)
• Computer Vision a Modern Approach
(D. Forsyth, J. Ponce, Prentice Hall 2002)
• Required Software MATLAB (with Image Processing toolbox)
Biological motivations
Understanding visual sensing modality and its role
- We have no difficulties to navigate, manipulate objects
recognize familiar places and faces
- How can we successfully carry out all these everyday tasks ?
- How does the visual perception mediates these activities ?
- Overall system
Sensation and perception – int egrate and interpret sensory readings
Behavior – control musc les and glands to mediate some behavior
Memory – long term me mory (declarative – faces, places, events)
short term memory (procedural – associations, skills)
Higher level functions – internal models and r epresentations of the
environments
Goal of Computer Vision
• Build machines and develop algorithms which can
automatically replicate some funcionalities of
biological visual system
- Systems which navigate in cluterred environments
- Systems which can recognize objects, activities
- Systems which can interact with humans/world
Synergies with other disciplines and various applications
Artificial Intelligence ( Robotics, Natural Language
Understanding)
Vision as a sensor – medical imaging, Geospatial Imaging,
robotics
visual surveilance, inspection
