digital holography - khu.ac.kr
TRANSCRIPT
Digital Holography
(Computational Photography)
About Instructor
Seungkyu Lee, Assistant Prof., Dept. of CE
Ph.D at Penn State Univ. US, MS & BS at KAIST
Researcher, KBS TRI - 6 Years
Senior Researcher, Samsung (SAIT) – 3.5 Years
Research Field
: Computer Vision
- 3D Reconstruction & Interaction using depth cameras
- Object/Gesture/Pattern Recognition
- Computational Photography
Office: Room 310-2 (Find my name!!!)
Email: [email protected]
Lab: Room 436
Members: 1 Professor, 6 Grad. Stud.
Webpage: http://cvlab.khu.ac.kr/
What is Computer vision?
(Some slides are from Prof. James Hays, Brown Univ.)
Computer Vision
Make computers understand images and video.
What kind of scene?
Where are the cars?
How far is the
building?
…
Vision is really hard
• Vision is an amazing feat of natural intelligence – Visual cortex occupies about 50% of Macaque brain
– More human brain devoted to vision than anything else
Is that a queen or a bishop?
Why computer vision matters
Safety Health Security
Comfort Access Fun
Ridiculously brief history of computer vision
• 1966: Minsky assigns computer vision as an undergrad summer project
• 1960’s: interpretation of synthetic worlds
• 1970’s: some progress on interpreting selected images
• 1980’s: ANNs come and go; shift toward geometry and increased mathematical rigor
• 1990’s: face recognition; statistical analysis in vogue
• 2000’s: broader recognition; large annotated datasets available; video processing starts
• 2030’s: robot uprising?
Guzman ‘68
Ohta Kanade ‘78
Turk and Pentland ‘91
Optical character recognition
Digit recognition, AT&T labs
http://www.research.att.com/~yann/
Technology to convert scanned docs to text • If you have a scanner, it probably came with OCR
software
License plate readers http://en.wikipedia.org/wiki/Automatic_number_plate_recognition
Face detection
• Many new digital cameras now detect faces
Smile detection
Sony Cyber-shot® T70 Digital Still Camera
3D from thousands of images
Building Rome in a Day: Agarwal et al. 2009
Object recognition
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… “
Vision-based biometrics
“How the Afghan Girl was Identified by Her Iris Patterns” Read the
story
wikipedia
Login without a password…
Fingerprint scanners on
many new laptops,
other devices
Face recognition systems now
beginning to appear more widely http://www.sensiblevision.com/
Object recognition
Point & Find, Nokia
Google Goggles
The Matrix movies, ESC Entertainment, XYZRGB, NRC
Special effects:shape capture
Pirates of the Carribean, Industrial Light and Magic
Special effects:motion capture
Smart cars
• Mobileye
– Vision systems currently in high-end BMW, GM, Volvo models
– By 2010: 70% of car manufacturers.
Slide content courtesy of Amnon Shashua
Google cars
Oct 9, 2010. "Google Cars Drive Themselves, in Traffic". The New York Times.
John Markoff
June 24, 2011. "Nevada state law paves the way for driverless cars". Financial
Post. Christine Dobby
Aug 9, 2011, "Human error blamed after Google's driverless car sparks five-
vehicle crash". The Star (Toronto)
Interactive Games: Kinect • Object Recognition:
http://www.youtube.com/watch?feature=iv&v=fQ59dXOo63o
• Mario: http://www.youtube.com/watch?v=8CTJL5lUjHg
• 3D: http://www.youtube.com/watch?v=7QrnwoO1-8A
• Robot: http://www.youtube.com/watch?v=w8BmgtMKFbY
Vision in space
Vision systems (JPL) used for several tasks • Panorama stitching
• 3D terrain modeling
• Obstacle detection, position tracking
• For more, read “Computer Vision on Mars” by Matthies et
al.
NASA'S Mars Exploration Rover Spirit captured this westward view from atop
a low plateau where Spirit spent the closing months of 2007.
Industrial robots
Vision-guided robots position nut runners on wheels
Mobile robots
http://www.robocup.org/
NASA’s Mars Spirit Rover
http://en.wikipedia.org/wiki/Spirit_rover
Saxena et al. 2008
STAIR at Stanford
Medical imaging
Image guided surgery
Grimson et al., MIT 3D imaging
MRI, CT
My Research Topics
3D by Color + Depth Fusion
ToF or Kinect Depth Cameras
Depth Image
3D Depth Points
RGB+D Research
3D Modeling 3D Motion
3D Control 3D Recognition
3D Modeling Applications
• 3D Animation
• 3D Printing
3D Animation • Physical to Virtual
3D Printing • Physical to Virtual to Physical
Future 3D Displays
USC, Volumetric Display SeeReal, Hologram Display Holografika
LF Model of Real Scene
Pattern Recognition
Symmetry pattern detection
Rotation symmetry
Reflection symmetry
Curved glide-reflection
symmetry
Translation symmetry
31
Experimental Results
31 Zebra fish
Lizard
Leaves
Spine
Caterpillar
Rotation/Reflection Symmetry Detection
• S. Lee, Y. Liu, "Curved Glide Reflection Symmetry Detection", IEEE TPAMI 2012 • S. Lee, Y. Liu, "Skewed Rotation Symmetry Group Detection", IEEE TPAMI 2010 • S. Lee, Y. Liu, "Curved Glide Reflection Symmetry Detection", IEEE CVPR 2009 (Oral) • S. Lee, R.Collins,Y.Liu,"Rot. Sym. Group Detection Via Freq. Analysis of Frieze-Expansions“, IEEE CVPR 2008 • M. Park & S. Lee et al. "Performance Eval. of State-of-the-Art Disc. Sym. Detection Alg.s“, IEEE CVPR 2008
33
Symmetry in our culture
- Spatiotemporal symmetries from human body motion / cultural activity
- Symmetry in 3D geometry (Niloy Mitra)
Symmetry Gesture/Shape/Object Detection
• S. Lee, “Frequency Guided Bilateral Symmetry Gabor Wavelet Network”, IEEE ICIP 2011 • S. Lee, Y. Liu, "Symmetry-Driven Shape Matching", PSU-CSE-09011, CSE dept. Penn State University 2009 • M. Park, S. Lee, "Face Modeling and Tracking with Gabor Wavelet Network Prior", ICPR 2008 • S. Lee, Y. Liu, R.Collins,"Shape variation-based Frieze Pattern for Robust gait recognition", IEEE CVPR 2007
Motion texture
Activity Recognition (Data: Biomotion)
Confusion matrix
Recognition results (108 subjects)
- 10 activity types
- 50 training, 50 test sets
- Forward selection + nAVR
- Classifier = LDA
100%
0%
In this class?
First Half
Introduction of Computer Vision Topics
Two take home exams
: Two implementation problems for each (Matlab, C++, JAVA, …)
: Discussion is allowed (actually encouraged!!)
: But implement by yourself and submit (working code package)
individually
: No existing library
: Have to include as many annotation lines as possible
(evaluation will be based on your annotations)
(for example, working code without any annotation will get 0 grade)
: Copied submission (from internet or from other students)
will get MINUS grade
Reference Books: "Computer Vision: Algorithms and Applications" by Richard Szeliski
Second Half
Introduction of Computer Vision Topics
Final Project (Competition !!)
: Choose one topic from given list (3 or 4 selected topics)
: Submit project proposal
: Implement your own algorithm and test on given dataset
: Implement by yourself as many parts as possible
: Submit working code package and final report
: Refer if you have adopted any existing algorithm
: Each your algorithm will be evaluated qualitative and quantitatively
: Tips for high grade?
Win the competition~
Propose a new idea and algorithm (extra grade)
Analyze every your algorithm and results in your report