Computational Photography and Vision
(CS116)
Deva Ramanan
dramanan@ics.uci.edu
• http://www.ics.uci.edu/~dramanan/teaching/cs116_fall08/index.html
• Check web page often
• T,R 12:30-1:50pm PSCB (Phy Sci Class Blg) 140
• Course intro handout
Slides adapted from Alyosha Efros, Rick Szeliski and Steve Seitz
Agenda
• Intros
• Computational photography/vision overview
• Course overview
• Image processing – let‟s dive in
Readings (due next class)
• Online Book (link from course website):
Richard Szeliski, Computer Vision: Algorithms and Applications
– Intro: Ch 1.0 & 2.1
Ungraded HW (due next class)
• MATLAB tutorial (link from course website)
About me
Deva Ramanan
Relatively new faculty (2cnd class ever!)
My research focus is on computer vision
Part of new Computational Vision Lab
http://vision.ics.uci.edu/
What is computational photography?
Convergence of image processing, computer
vision, computer graphics and photography
Digital photography:
• Simply replaces traditional sensors and recording by digital
technology
• Involves only simple image processing
Computational photography
• More elaborate image manipulation, more computation
• New types of media (panorama, 3D, etc.)
• Camera design that take computation into account
What is computer graphics? (3D->2D)
3D geometry
projection
Simulation
physics GRAPHICS
What is computer vision? (2D->3D)
3D geometry
Estimation
physics
What is computer vision?
Terminator 2
Every picture tells a story
Goal of computer vision is to write computer programs
that can interpret images
Can computers match (or beat) human vision?
Yes and no (but mostly no!)
• humans are much better at “hard” things
• computers can be better at “easy” things
Human perception has its shortcomings…
Sinha and Poggio, Nature, 1996
Copyright A.Kitaoka 2003
Current state of the art
The next slides show some examples of what
current vision systems can do
Earth viewers (3D modeling)
Image from Microsoft‟s Virtual Earth
(see also: Google Earth)
Photo Tourism
http://phototour.cs.washington.edu/
http://labs.live.com/photosynth/
Optical character recognition (OCR)
Technology to convert scanned docs to text
• If you have a scanner, it probably came with OCR software
Digit recognition, AT&T labs License plate readers
http://www.research.att.com/~yann/ http://en.wikipedia.org/wiki/Automatic_number_plate_recognition
Face detection
Many new digital cameras now detect faces
• Canon, Sony, Fuji, …
Smile detection?
Sony Cyber-shot® T70 Digital Still Camera
Object recognition (in supermarkets)
LaneHawk by EvolutionRobotics
“A smart camera is flush-mounted in the checkout lane, continuously watching
for items. When an item is detected and recognized, the cashier verifies the
quantity of items that were found under the basket, and continues to close the
transaction. The item can remain under the basket, and with LaneHawk,you are
assured to get paid for it… “
Face recognition
Who is she?
Vision-based biometrics
“How the Afghan Girl was Identified by Her Iris Patterns” Read the story
Login without a password…
Face recognition systems now
Fingerprint scanners on
beginning to appear more widely
many new laptops, http://www.sensiblevision.com/
other devices
Object recognition (in mobile phones)
This is becoming real:
• Microsoft Research
• Point & Find, Nokia
Special effects: shape capture
The Matrix movies, ESC Entertainment, XYZRGB, NRC
Special effects: motion capture
Pirates of the Carribean, Industrial Light and Magic
Special effects: image-based rendering
Sports
Sportvision first down line
Nice explanation on www.howstuffworks.com
Smart cars Slide content courtesy of Amnon Shashua
Mobileye
• Vision systems currently in high-end BMW, GM, Volvo models
• By 2010: 70% of car manufacturers.
Vision-based interaction (and games)
Digimask: put your face on a 3D avatar.
Nintendo Wii has camera-based IR
tracking built in. See Lee‟s work at
CMU on clever tricks on using it to
create a multi-touch display!
“Game turns moviegoers into Human Joysticks”, CNET
Camera tracking a crowd, based on this work.
Robotics
NASA‟s Mars Spirit Rover http://www.robocup.org/
http://en.wikipedia.org/wiki/Spirit_rover
Medical imaging
Image guided surgery
3D imaging
Grimson et al., MIT
MRI, CT
Current state of the art
You just saw examples of current systems.
• Many of these are less than 5 years old
This is a very active research area, and rapidly changing
• Many new apps in the next 5 years
To learn more about vision applications and companies
• David Lowe maintains an excellent overview of vision
companies
– http://www.cs.ubc.ca/spider/lowe/vision.html
This course
http://www.ics.uci.edu/~dramanan/teaching/cs116_fall08/index.html
Prerequisites
• Calculus, linear algebra + probability helpful
• Interest in playing with images
Emphasis on programming projects!
• Best way to learn is to build something from scratch
• MATLAB has a low learning curve
• 5 projects (15% of grad) + final exam (25%)
• Project due every 2 weeks
• For larger projects, “part 1” due first week
Project 1: Demosaicing
1) Get feet wet with MATLAB
2) Turn raw output of digital camera into a color image
Project 2: hole-filling and blending
The fun stuff!
Tools: bayesian modelling, differential equations
Project 3: Image re-targeting
Click on video
Tools: combinatorial optimization, dynamic programming
Project 4: Automatic mosaicing
Tools: linear algebra, signal processing
Project 5: Face detection & recognition
Tools: probabilistic modeling
Cameras
Don‟t need for class, but really cool
Digital SLRs are ideal
Point–and-shoots still nice and not too
expensive (<$200)
e.g. Canon A550
References
There is no required text. Various course notes and papers will
be made available. We will often use an online draft of an
upcoming book:
Richard Szeliski, Computer Vision: Algorithms and Applications
There is a number of other fine texts that you can use for general
reference:
Computer Vision: The Modern Approach, Forsyth and Ponce
Vision Science: Photons to Phenomenology, Stephen Palmer
Multiple View Geometry in Computer Vision, Hartley & Zisserman
The Computer Image, Watt and Policarpo
Linear Algebra and its Applications, Gilbert Strang
A little bit of teaching philosophy…
1) Prefer discussion vs lectures – ask questions!
2) Readings before class help „set the stage‟
3) We learn best by doing it ourselves –
progamming projects important!
4) Don‟t like powerpoint (makes students sleep)
-But visual aides are nice
-Slides will be available online *after* class
-I encourage you to take notes during class
Favor to ask…
Need to boost enrollment - spread the gospel
about this cool class!