comp(9517(( computer(vision(
TRANSCRIPT
25/07/2016 1
COMP 9517 Computer Vision
Introduc<on
1 COMP 9517 S2, 2016
25/07/2016 2
What is Computer Vision?
2 COMP 9517 S2, 2016
25/07/2016 3
Every picture tells a story
• Goal of computer vision is to write computer programs that can interpret images
COMP 9517 S2, 2016
25/07/2016 4
Can computers match (or beat) human vision?
• Yes and no (but mostly no!) – humans are much beRer at “hard” things – computers can be beRer at “easy” things
COMP 9517 S2, 2016
25/07/2016 5
Human percep<on has its shortcomings…
Sinha and Poggio, Nature, 1996
COMP 9517 S2, 2016
25/07/2016 6 Copyright A.Kitaoka 2003
COMP 9517 S2, 2016
25/07/2016 7
Current State of the Art
• Here are some examples
COMP 9517 S2, 2016
25/07/2016 8
Earth viewers (3D modeling)
Image from Microsoft’s Virtual Earth (see also: Google Earth)
COMP 9517 S2, 2016
25/07/2016 9
Op<cal character recogni<on (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 so[ware
License plate readers http://en.wikipedia.org/wiki/Automatic_number_plate_recognition
COMP 9517 S2, 2016
25/07/2016 10
Face detec<on
• Many new digital cameras now detect faces – Canon, Sony, Fuji, …
COMP 9517 S2, 2016
25/07/2016 11
Smile detec<on?
Sony Cyber-shot® T70 Digital Still Camera
COMP 9517 S2, 2016
25/07/2016 12
Object recogni<on (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… “
COMP 9517 S2, 2016
25/07/2016 13
Face recogni<on
Who is she? COMP 9517 S2, 2016
25/07/2016 14
Vision-‐based biometrics
“How the Afghan Girl was Identified by Her Iris Patterns” Read the story at http://www.cl.cam.ac.uk/~jgd1000/afghan.html
COMP 9517 S2, 2016
25/07/2016 15
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/
COMP 9517 S2, 2016
25/07/2016 16
Object recogni<on (in mobile phones)
• This is becoming real: – Microso[ Research – Point & Find, Nokia
COMP 9517 S2, 2016
25/07/2016 17
The Matrix movies, ESC Entertainment, XYZRGB, NRC
Special effects: shape capture
COMP 9517 S2, 2016
25/07/2016 18
Pirates of the Carribean, Industrial Light and Magic Click here for interactive demo
Special effects: mo<on capture
COMP 9517 S2, 2016
25/07/2016 19
Sports
Sportvision first down line How do they superimpose the first-down line on the field on televised football games?
Nice explanation on www.howstuffworks.com
COMP 9517 S2, 2016
25/07/2016 20
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
COMP 9517 S2, 2016
25/07/2016 21
Vision-‐based interac<on (and games)
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!
Digimask: put your face on a 3D avatar.
“Game turns moviegoers into Human Joysticks”, CNET Camera tracking a crowd, based on this work. COMP 9517 S2, 2016
25/07/2016 22
Vision in space
• Vision systems (JPL) used for several tasks – Panorama s<tching – 3D terrain modeling – Obstacle detec<on, posi<on tracking – For more, read “Computer Vision on Mars” by MaRhies 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.
COMP 9517 S2, 2016
25/07/2016 23
Robo<cs
http://www.robocup.org/
NASA’s Mars Spirit Rover http://en.wikipedia.org/wiki/Spirit_rover
COMP 9517 S2, 2016
25/07/2016 24
Medical imaging
Image guided surgery Grimson et al., MIT
3D imaging MRI, CT
COMP 9517 S2, 2016
25/07/2016 25
More CV Applica<ons • Vision-‐based HCI
– EyeMouse: a vision-‐based eye control system
– To use human head and eyes to control computers, so how?
– Computer vision and a webcam to track the eyes and head
– Shakes and winks to control a mouse pointer on the screen
– Face expression recogni<on – Challenge: cluRer and real <me
• Game Controller: Cam-‐Trax 25 COMP 9517 S2, 2016
25/07/2016 26
• Geographical: GIS – Interpre<ng satellite images – Road detec<on for crea<ng maps – Edge detec<on, Road edge classifica<on and linking – Challenge: complex and wide scene, occlusion, low resolu<on or large data size.
COMP 9517 S2, 2016 26
25/07/2016 27
• Medical Imaging – Enhance imagery, or iden<fy important phenomena or events, or visualise informa<on obtained by imaging
– Parenchymal bands: linear structures touching the lung boundary
– Segment and classify candidate regions into posi<ve (parenchymal bands) and nega<ve (others) class
– Challenge:
COMP 9517 S2, 2016 27
• O[en aRached to other structures, in this case a nodular mass • Similar appearance to blood vessels
25/07/2016 28
• Video Surveillance – Traffic Monitoring – Object tracking – Ac<on recogni<on, driving, stopping, etc
– Vehicle speed – Coun<ng – Challenge: occlusion, illumina<on changes and non-‐linear speed
28 COMP 9517 S2, 2016
25/07/2016 29
• Image/video retrieval – Content-‐based retrieval – Search engine – Challenge: big data volume, seman<c
COMP 9517 S2, 2016 29
25/07/2016 30
• Text Recogni<on – Conver<ng informa<on from paper documents into digital form
– Challenge: seman<c interpreta<on
COMP 9517 S2, 2016 30
I looked as hard as I could see, beyond 100 plus infinity an object of bright intensity-‐ it was the back of me!
• Applica<on Videos
25/07/2016 COMP 9517 S2, 2016 31
COMP 9517 S2, 2016 25/07/2016 32
Goals of Computer Vision
• Extract useful informa<on from images • Complexity of visual data is a challenge • Recent progress due to higher processing power, memory, storage capacity
• Image-‐>measurements-‐>model-‐>algorithms for learning and inference
32
COMP 9517 S2, 2016 25/07/2016 33
Computer Vision Topics • Requires a solid understanding of camera and of the physical process of imaging to:
-‐ obtain simple inferences from individual pixel values
-‐ combine the informa<on available in mul<ple images into a coherent whole
-‐ enforce some order on groups of pixels to separate them from each other or infer shape informa<on
-‐ recognise objects using geometric informa<on or probabilis<c techniques.
33
COMP 9517 S2, 2016 25/07/2016 34
Cri<cal Issues
• Sensing: how do sensors obtain images of the world?
• Encoded Informa1on: how do images yield informa<on of the scene, such as color, texture, shape, mo<on, etc.?
• Representa1ons: what representa<ons are appropriate to describe objects?
• Algorithms: what algorithms process image informa<on and construct scene descrip<ons?
34
25/07/2016 35
Computer Vision Processes • Low level processes
– use little knowledge of image content – include image compression, noise filtering, edge
extraction, ... – use data which resemble the input image, eg. matrix of
picture elements
• High level processes – based on knowledge, goals, plans – use Artificial Intelligence methods – simulate human cognition and decision making based on
information in the image – cognitive processes, geometric models, goals, plans,...
35 COMP 9517 S2, 2016
25/07/2016 36
Low Level Vision
• almost en<rely digital image processing – sensing: image capture and digi<sa<on – pre-‐processing: improve image quality: suppress noise, enhance object features, edge extrac<on
– image segmenta1on: separate objects from background, par<<on image into objects of interest
– descrip1on: compute features which differen<ate objects-‐ also called feature extrac*on
– Classifica1on: assign labels to image segments (regions)
36 COMP 9517 S2, 2016
25/07/2016 37
High Level Vision
• About knowledge construc<on, representa<on and inference – recogni1on: iden<fica<on of objects – interpreta1on: assign meaning to groups of recognized objects
– scene analysis
37 COMP 9517 S2, 2016
25/07/2016 38
For Reading
• Chapter 1, Szeliski • Chapter 1, Shapiro and Stockman
COMP 9517 S2, 2016
25/07/2016 39
Acknowledgement
• Some images on applica<ons taken from the textbook resources for the text by Szeliski 2010, with original sources credited where possible
• Videos credited
COMP 9517 S2, 2016