1-introduction to computer vision compatibility mode

8/12/2019 1-Introduction to Computer Vision Compatibility Mode

1/58

Introduction to Computer Vision

Professor Fei-Fei Li (Stanford Vision Lab)

James Hays (http://www.cs.brown.edu)

Image bykirkh.deviantart.com


2/58

Todays Class

Introductions

What is Computer Vision?

Why study computer vision? Why computer vision matters

How vision is used now

Specifics of this course


3/58

Computer Vision

Make computers understand images and

video.

What kind of scene?

Where are the cars?

How far is the

building?


4/58


5/58

Computer Vision and Nearby Fields

Computer Graphics: Models to Images

Comp. Photography: Images to Images

Computer Vision: Images to Models


6/58


7/58


8/58


9/58


10/58


11/58


12/58


13/58


14/58


15/58


16/58


17/58


18/58


19/58


20/58


21/58

In the field of artificial intelligence, the most difficult problems are informally known asAI-compl ete orAI-hard, implying that the difficulty of these

computational problems is equivalent to solving the central artificial intelligence problemmaking computers as intelligent as people, or strong AI

AI-complete problems are hypothesised to include computer vision, natural language understanding, and dealing with unexpected circumstances

while solving any real world problem.


22/58

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 aqueen or a

bishop?


23/58


24/58

Illumination (image), the use of light and shadow in art


25/58


26/58


27/58

If you are developing a system which tracks

objects (people, cars, ...) then occlusion occurs if

an object you are tracking is hidden (occluded) by

another object


28/58


29/58


30/58


31/58


32/58


33/58


34/58


35/58


36/58


37/58


38/58


39/58


40/58


41/58


42/58

Why computer vision matters

Safety Health Security

Comfort AccessFun


43/58

How vision is used now

Examples of state-of-the-art

Some of the following slides by Steve Seitz


44/58

Optical character recognition (OCR)

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 readershttp://en.wikipedia.org/wiki/Automatic_number_plate_recognition


45/58

Face detection

Many new digital cameras now detect faces

Canon, Sony, Fuji,


46/58

Smile detection

Sony Cyber-shot T70 Digital Still Camera


47/58

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


48/58

Vision-based biometrics

How the Afghan Girl was Identified by Her Iris Patterns Read the story

wikipedia


49/58

Login without a password

Fingerprint scanners on

many new laptops,

other devices

Face recognition systems now

beginning to appear more widelyhttp://www.sensiblevision.com/


50/58


51/58


52/58

Object recognition (in mobile phones)

Point & Find, Nokia

Google Goggles


53/58


54/58


55/58

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.


56/58

Industrial robots

Vision-guided robots position nut runners on wheels


57/58

Mobile robots

http://www.robocup.org/NASAs Mars Spirit Rover

http://en.wikipedia.org/wiki/Spirit_rover

Saxena et al. 2008

STAIR at Stanford


58/58

Medical imaging

Image guided surgery

Grimson et al., MIT3D imaging

MRI, CT

1-introduction to computer vision compatibility mode

Documents