EECS 274 Computer Vision

Introduction

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

Optical illusions

Copyright A.Kitaoka 2003

Why is computer vision difficult?• Inverse problem• Ill-posed• High-dimensional data• Noise• Variation

Earth viewers (3D modeling)

Image from Microsoft’s Virtual Earth(see also: Google Earth)

Google streetview

Photosynth

http://labs.live.com/photosynth/http://www.youtube.com/watch?v=p16frKJLVi0

by Noah Snavely, Steve Seitz, and Rick Szeliski

Optical character recognition

Digit recognition, AT&T labshttp://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 readershttp://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…

Fingerprint scanners on many new laptops,

other devices

Face recognition systems now beginning to appear more widely

http://www.sensiblevision.com/

Object recognition (in mobile phones)

• This is becoming real:– Microsoft Research– Point & Find, Nokia, NTT Docomo

The Matrix movies, ESC Entertainment, XYZRGB, NRC

Special effects: shape capture

Bullet time:http://www.youtube.com/watch?v=J5ryLMZTO5M

Pirates of the Carribean, Industrial Light and MagicClick here for interactive demo

Special effects: motion capture

Sports

Sportvision first down lineNice explanation on www.howstuffworks.com

http://www.youtube.com/watch?v=UyPU2l9rdvo

Smart cars

• Mobileye– Vision systems currently in high-end BMW, GM, Volvo models – By 2010: 70% of car manufacturers.– Video demo

Vision-based interaction (and games)

Nintendo Wii has camera-based IRtracking built in. See Lee’s work atCMU on clever tricks on using it tocreate a multi-touch display!

Digimask: put your face on a 3D avatar.

“Game turns moviegoers into Human Joysticks”, CNETCamera tracking a crowd, based on this work.

Vision-based HCI

• Reatrix: http://www.youtube.com/watch?v=QzsQKULMbiU

Gaming

• Sony Eyetoy • Microsoft Natal

http://www.youtube.com/watch?v=AOXohr4XE-4&feature=related

http://www.youtube.com/watch?v=1BRSfCuLYHc

Motion capture

• Marker-based motion capture– http://www.youtube.com/watch?v=V0yT8mwg9nc

• Organic motion• http://www.organicmotion.com/

Looking at people• Hand gesture• Head pose• Expression • Identity

http://www.youtube.com/watch?v=NwVBzx0LMNQ

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.

Gigapan

• http://www.gigapan.org/index.php• HP TouchSmart with Gigapn demo at

Chicago O’Hare airport

Robotics

http://www.robocup.org/NASA’s Mars Spirit Roverhttp://en.wikipedia.org/wiki/Spirit_rover

Medical imaging

Image guided surgeryGrimson et al., MIT

3D imagingMRI, CT

Digital comestics

Inpainting

Bertalmio et al. SIGGRAPH 00

Debluring

Fergus et al. SIGGRAPH 06

Digital photo albums

• Picasa, Flickr, Photobucket, etc.• Categorization• Tagging• Search

Computational photography

• Image acquisition• Hardware/software• Optics• Shuttle speed• Novel sensors• Multiple camera• Multiple shots• Multi flash• Applications: high dynamic range imaging, super

resolution, photomontage, panorama moasicing, debluring, light field, camera projector system…

Image and video search

• Google• YouTubes• Microsoft• Yahoo

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 applications 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

• Confluence of vision, graphics, learning, sensing and signal processing

Software and hardware

• Algorithms: processing images and videos

• Camera: acquiring images/videos • Embedded system

Topics

• Image formation: camera model, camera calibration, radiometry, color, shading

• Early vision: stereopsis, structure from motion, illumination, reflectance, shape from X, texture

• Mid-level vision: segmentation, grouping, Kalman filter, particle filter, shape representation

• High-level vision: correspondence, matching, object detection, object recognition, visual tracking

• Recent topics: image and video retrieval, internet vision

Related topics

Textbooks and references• Textbook

– Computer Vision: A Modern Approach, David Forsyth and Jean Ponce– Computer Vision: Algorithms and Applications (draft), Richard Szeliski

• Reference for background study:  – Introductory Techniques for 3-D Computer Vision, Emanuele Trucco and

Alessandro Verri– Multiple View Geometry in Computer Vision, Richard Hartley and Andrew

Zisserman– An Invitation to 3-D Vision by Yi Ma, Stefano Soatto, and Jana Kosecka– Robot Vision, Berthold Horn– Learning OpenCV: Computer Vision with OpenCV Library, Gary Bradski and

Adrian Kaehler

• Reading assignments will be from the text and additional material that will be handed out or made available on the web page

• All lecture slides will be available on the course website http://faculty.ucmerced.edu/mhyang/course/cse274/index.htm

Grading

• Based on projects• No midterm or final• 20% Homework• 40% Programming assignments• 40% Term project

Project 1: features

Project 2: Lucas-Kande Tracker

http://www.youtube.com/watch?v=yoQ8pSXrl4g

Project 3: object detection

Term Project

• Open-ended project of your choosing• Oral presentation

– Midterm presentation– Final presentation and demo

• Publish your results

General Comments

• Prerequisites—these are essential!

– Data structures– A good working knowledge of MATLAB, C,

and C++ programming– Linear algebra – Vector calculus

• Course does not assume prior imaging experience

– computer vision, image processing, graphics, etc.

Acknowledgements

• Slides– David Forsyth and Jean Ponce– Richard Szleski and Steve Seitz