computer vision lecture #1

22
Computer Vision Computer Vision Lecture #1 Lecture #1 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical and Computer Engineering Department, University of Louisville, Louisville, KY, USA ECE619/645 – Spring 2011

Upload: red

Post on 25-Feb-2016

42 views

Category:

Documents


0 download

DESCRIPTION

Computer Vision Lecture #1. Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical and Computer Engineering Department, University of Louisville, Louisville, KY, USA ECE619/645 – Spring 2011. Course Outline. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Computer Vision Lecture #1

Computer VisionComputer VisionLecture #1Lecture #1

Hossam Abdelmunim1 & Aly A. Farag2

1Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt

2Electerical and Computer Engineering Department, University of Louisville, Louisville, KY, USA

ECE619/645 – Spring 2011

Page 2: Computer Vision Lecture #1

Course OutlineCourse Outline

• Computer Vision– Focus is on basic computer vision skills– Tools for research

• Mathematical Background– Basic material

– Numerical/computational Skills

• Matlab– Quick prototyping– tool for checking out ideas

Page 3: Computer Vision Lecture #1

Text BooksText Books

1. A Guided Tour of Computer Vision, by V. S. Nalwa,Addison-Wesley, 1993.2. Introductory Techniques for 3-D Computer Vision, by Emanuele Trucco, Alessandro Verri, Prentice-Hall, 1998.3. Multiple View Geometry, by Richard Hartley, Andrew Zisserman, Cambridge University Press, 2000, 2003.4. Numerical Recipes in C, by William Press et al., Cambridge Univ. Press, 1992.5. Pattern Classification and Scene Analysis, by Richard O. Duda, Peter E. Hart, John Wiley & Sons, 1973.

Page 4: Computer Vision Lecture #1

Computer VisionComputer Vision

Computer vision basics– Image creation– Cameras, Eyes, Calibration– Features, correspondence– 3D vision– Optical Flow– Tracking– Compression, vision for content delivery

Page 5: Computer Vision Lecture #1

MathematicsMathematics

Basic Mathematical tools– Linear systems, matrix decompositions– Vector space, Basis, eigenvalues, eigenvectors– Calculus: gradients, Taylor series, maxima

• Projective geometry– Homographies, projectivities, constraints– Fundamental matrix– Trifocal tensor

• Probability, Random Variables, Classification

Page 6: Computer Vision Lecture #1

Numerical MethodsNumerical Methods

• Solving linear systems of equations• Matrix decompositions

– LU, Eigenvalue, SVD,• Optimization• Use Matlab as a tool to quickly try ideas• Familiarity with image types• “Practical computer vision”

Page 7: Computer Vision Lecture #1

Problems we should be able to solveProblems we should be able to solve• Calibrate a camera• Rectify an image• Create a three dimensional reconstruction• Insert model into image• Track objects• Track people• Read papers on these topics and do thesis research

Page 8: Computer Vision Lecture #1

Application Example-1Application Example-1

Detect ground plane in video andintroduce pictures on them

Page 9: Computer Vision Lecture #1

Application Example-2Application Example-2

morphing: blending between two photographs

Page 10: Computer Vision Lecture #1

Application Example-3Application Example-3

morphing: blending between two photographs

Page 11: Computer Vision Lecture #1

Application Example-4Application Example-4

turning a collection of photographs into a 3D model

Page 12: Computer Vision Lecture #1

Application Example-5Application Example-5

Tracking

Page 13: Computer Vision Lecture #1

What is Vision?What is Vision?Recognize objects

– people we know– things we own

• Locate objects in space– to pick them up

• Track objects in motion– catching a baseball– avoiding collisions with cars on the road

• Recognize actions– walking, running, pushing

Page 14: Computer Vision Lecture #1

Vision isVision is

• Deceivingly easy• Deceptive• Computationally demanding• Critical to many applications

Page 15: Computer Vision Lecture #1

Vision is Deceivingly EasyVision is Deceivingly EasyWe see effortlessly

– seeing seems simpler than “thinking”– we can all “see” but only select gifted people can solve“hard” problems like chess– we use nearly 70% of our brains for visual perception!

• All “creatures” see– frogs “see”– birds “see”– snakes “see”

but they do not see alike

Page 16: Computer Vision Lecture #1

Vision is DeceptiveVision is DeceptiveVision is an exceptionally strong sensation

– vision is immediate– we perceive the visual world as external to ourselves,

but it is a reconstruction within our brains– we regard how we see as reflecting the world “as it

is;” but human vision is• subject to illusions• quantitatively imprecise• limited to a narrow range of frequencies of radiation• passive

Page 17: Computer Vision Lecture #1

Some IllusionSome Illusion

Page 18: Computer Vision Lecture #1

Some IllusionSome Illusion

Page 19: Computer Vision Lecture #1

Some IllusionSome Illusion

Page 20: Computer Vision Lecture #1

Some IllusionSome Illusion

Page 21: Computer Vision Lecture #1

Human Vision is PassiveHuman Vision is Passive• It relies on external energy sources(sunlight, light bulbs, fires) providing lightthat reflects off of objects to our eyes

• Vision systems can be “active” - carry theirown energy sources

– Radars– Bat acoustic imaging systems

Page 22: Computer Vision Lecture #1

Spectral Limitation of Human VisionSpectral Limitation of Human Vision

• We “see” only a small part of the energyspectrum of sunlight

– we don’t see ultraviolet or lower frequencies of light– we don’t see infrared or higher frequencies of light– we see less than .1% of the energy that reaches our eyes

• But objects in the world reflect and emit energy in these and other parts of the spectrum