Post on 31-May-2020
transcript
Lecture 1 - !!!
Fei-Fei Li!
Lecture 1: Introduc.on to “Computer Vision”
Professor Fei-‐Fei Li Stanford Vision Lab
20-‐Sep-‐13 1
Lecture 1 - !!!
Fei-Fei Li!
Welcome to CS131
Slid
e ad
apte
d fr
om S
vetl
ana
Laze
bnik
20-‐Sep-‐13 2
Lecture 1 - !!!
Fei-Fei Li!
CS131 is a brand new class!
• CS131 (fall, 2013): – Enthusias.c undergrads – Want to get to know this exci.ng technology
• CS231a (winter, 2014, Prof. Silvio Savarese) – Similar to exis.ng CS231a – Seniors, masters, and PhDs
• CS231b: CuRng Edge Computer Vision • CS331 (fall, 2013, Prof. Silvio Savarese)
– Advanced 3D reconstruc.on & recogni.on
20-‐Sep-‐13 3
Lecture 1 - !!!
Fei-Fei Li!
Today’s agenda
• Introduc.on to computer vision • Course overview
20-‐Sep-‐13 4
Lecture 1 - !!!
Fei-Fei Li!
Quiz?
20-‐Sep-‐13 5
Lecture 1 - !!!
Fei-Fei Li!
What about this?
20-‐Sep-‐13 6
Lecture 1 - !!!
Fei-Fei Li!
Image (or video) Sensing device Interpreting device Interpretations
garden, spring, bridge, water, trees, flower, green, etc.
What is (computer) vision?
20-‐Sep-‐13 7
Lecture 1 - !!!
Fei-Fei Li!
What is it related to?
Computer Vision
Neuroscience
Machine learning
Speech
Informa.on retrieval
Maths
Computer Science
Biology
Engineering
Physics
Robo.cs Cogni.ve sciences
Psychology
graphics,algorithms, system,theory,…
Image processing
20-‐Sep-‐13 8
Lecture 1 - !!!
Fei-Fei Li!
The goal of computer vision • To bridge the gap between pixels and “meaning”
What we see What a computer sees Sou
rce:
S. N
aras
imha
n
20-‐Sep-‐13 9
Lecture 1 - !!!
Fei-Fei Li!
Image (or video) Sensing device Interpreting device Interpretations
garden, spring, bridge, water, trees, flower, green, etc.
What is (computer) vision?
20-‐Sep-‐13 10
Lecture 1 - !!!
Fei-Fei Li!
1981: Nobel Prize in medicine
Hubel & Wiesel
20-‐Sep-‐13 11
Lecture 1 - !!!
Fei-Fei Li!
Potter, Biederman, etc. 1970s
Human vision is superbly efficient
20-‐Sep-‐13 12
Lecture 1 - !!!
Fei-Fei Li!
Thorpe, et al. Nature, 1996
20-‐Sep-‐13 13
Lecture 1 - !!!
Fei-Fei Li!
Thorpe, et al. Nature, 1996
150 ms !!
20-‐Sep-‐13 14
Lecture 1 - !!!
Fei-Fei Li!
Change blindess
Rensink, O’regan, Simon, etc.
20-‐Sep-‐13 15
Lecture 1 - !!!
Fei-Fei Li!
Rensink, O’regan, Simon, etc.
Change blindess
20-‐Sep-‐13 16
Lecture 1 - !!!
Fei-Fei Li!
segmenta.on
20-‐Sep-‐13 17
Lecture 1 - !!!
Fei-Fei Li!
Percep.on
20-‐Sep-‐13 18
Lecture 1 - !!!
Fei-Fei Li! 20-‐Sep-‐13 19
Lecture 1 - !!!
Fei-Fei Li! 20-‐Sep-‐13 20
Lecture 1 - !!!
Fei-Fei Li!
Image (or video) Sensing device Interpreting device Interpretations
garden, spring, bridge, water, trees, flower, green, etc.
What is (computer) vision?
20-‐Sep-‐13 21
Lecture 1 - !!!
Fei-Fei Li!
The goal of computer vision • To bridge the gap between pixels and “meaning”
What we see What a computer sees Sou
rce:
S. N
aras
imha
n
20-‐Sep-‐13 22
Lecture 1 - !!!
Fei-Fei Li!
Origins of computer vision: an MIT undergraduate summer project
L. G. Roberts, Machine Percep,on of Three Dimensional Solids, Ph.D. thesis, MIT Department of Electrical Engineering, 1963.
20-‐Sep-‐13 23
Lecture 1 - !!!
Fei-Fei Li!
What kind of informa.on can we extract from an image?
• Metric 3D informa.on • Seman.c informa.on
20-‐Sep-‐13 24
Lecture 1 - !!!
Fei-Fei Li!
Vision as measurement device Real-time stereo Structure from motion
NASA Mars Rover
Pollefeys et al.
Reconstruction from Internet photo collections
Goesele et al.
20-‐Sep-‐13 25
Lecture 1 - !!!
Fei-Fei Li!
Vision as a source of semantic information sky
water
Ferris wheel
amusement park
Cedar Point
12 E
tree
tree
tree
carousel deck
people waiting in line
ride
ride ride
umbrellas
pedestrians
maxair
bench
tree
Lake Erie
people sitting on ride
Objects Activities Scenes Locations Text / writing Faces Gestures Motions Emotions…
The Wicked Twister
Slid
e cr
edit
: Kr
iste
n G
raum
an
20-‐Sep-‐13 26
Lecture 1 - !!!
Fei-Fei Li!
Why study computer vision?
Personal photo albums
Surveillance and security
Movies, news, sports
Medical and scientific images
• Vision is useful: Images and video are everywhere!
20-‐Sep-‐13 27
Lecture 1 - !!!
Fei-Fei Li!
Special effects: shape and mo.on capture
Sour
ce: S
. Sei
tz
20-‐Sep-‐13 28
Lecture 1 - !!!
Fei-Fei Li!
3D urban modeling
Bing maps, Google Streetview Source: S. Seitz
20-‐Sep-‐13 29
Lecture 1 - !!!
Fei-Fei Li!
3D urban modeling: Microsoj Photosynth
hkp://labs.live.com/photosynth/ Source: S. Seitz
20-‐Sep-‐13 30
Lecture 1 - !!!
Fei-Fei Li!
Face detec.on
• Many new digital cameras now detect faces – Canon, Sony, Fuji, …
Source: S. Seitz
20-‐Sep-‐13 31
Lecture 1 - !!!
Fei-Fei Li!
Smile detec.on
Sony Cyber-shot® T70 Digital Still Camera Source: S. Seitz
20-‐Sep-‐13 32
Lecture 1 - !!!
Fei-Fei Li!
Face recogni.on: Apple iPhoto sojware
hkp://www.apple.com/ilife/iphoto/
20-‐Sep-‐13 33
Lecture 1 - !!!
Fei-Fei Li!
Biometrics
How the Afghan Girl was Iden.fied by Her Iris Pakerns
Source: S. Seitz
20-‐Sep-‐13 34
Lecture 1 - !!!
Fei-Fei Li!
Biometrics
Fingerprint scanners on many new laptops, other devices
Face recogni.on systems now beginning to appear more widely hkp://www.sensiblevision.com/ Source: S. Seitz
20-‐Sep-‐13 35
Lecture 1 - !!!
Fei-Fei Li!
Op.cal character recogni.on (OCR)
Digit recognition, AT&T labs
Technology to convert scanned docs to text • If you have a scanner, it probably came with OCR sojware
License plate readers http://en.wikipedia.org/wiki/Automatic_number_plate_recognition
Source: S. Seitz
20-‐Sep-‐13 36
Lecture 1 - !!!
Fei-Fei Li!
Toys and Robots
Lecture 1 - !!!
Fei-Fei Li!
Mobile visual search: Google Goggles
20-‐Sep-‐13 38
Lecture 1 - !!!
Fei-Fei Li!
Mobile visual search: iPhone Apps
20-‐Sep-‐13 39
Lecture 1 - !!!
Fei-Fei Li!
Automo.ve safety
• Mobileye: Vision systems in high-‐end BMW, GM, Volvo models – “In mid 2010 Mobileye will launch a world's first applica.on of full emergency braking for collision mi.ga.on for pedestrians where vision is the key technology for detec.ng pedestrians.”
Source: A. Shashua, S. Seitz
20-‐Sep-‐13 40
Lecture 1 - !!!
Fei-Fei Li!
Vision 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… “ Source: S. Seitz
20-‐Sep-‐13 41
Lecture 1 - !!!
Fei-Fei Li!
Vision-‐based interac.on (and games)
Microsoft’s Kinect
Source: S. Seitz Assistive technologies
Sony EyeToy
20-‐Sep-‐13 42
Lecture 1 - !!!
Fei-Fei Li!
Vision for robo.cs, space explora.on
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 Makhies et al.
NASA'S Mars Explora.on Rover Spirit captured this westward view from atop a low plateau where Spirit spent the closing months of 2007.
Sour
ce: S
. Sei
tz
20-‐Sep-‐13 43
Lecture 1 - !!!
Fei-Fei Li!
Today’s agenda
• Introduc.on to computer vision • Course overview
20-‐Sep-‐13 44
Lecture 1 - !!!
Fei-Fei Li!
Contac.ng instructor and TAs
• ALL EMAIL CORRESPONDENCES TO ANYONE OF US: – cs131-‐fall1314-‐staff@lists.stanford.edu
• Instructor: Prof. Fei-‐Fei Li • Teaching Assistants
– Luke Allen, Master candidate – Johnson, Ph.D. candidate, CS – Jiayuan Ma, master candidate, CS
20-‐Sep-‐13 45
Lecture 1 - !!!
Fei-Fei Li!
Overall philosophy • Breadth
– Computer vision is a huge field – It can impact every aspect of life and society – It will drive the next informa.on and AI revolu.on – Pixels are everywhere in our lives and cyber space – CS131 is meant as an introductory course, we will not cover all topics
of CV – Lectures are mixture of details techniques and high level ideas – Speak our “language”
• Depth – Computer vision is a highly technical field, i.e. know your math! – Master bread-‐and-‐buker techniques: face recogni.on, corners, lines,
features, op.cal flows, clustering and segmenta.on – Programming assignments: be a good coder AND a good writer – Theore.cal problem sets: know your math! – Final Exam: your chance to shine!
20-‐Sep-‐13 46
Lecture 1 - !!!
Fei-Fei Li!
Syllabus
• Go to website…
20-‐Sep-‐13 47
Lecture 1 - !!!
Fei-Fei Li!
Grading policy
• Program Set 0: 8% – Normalizing background knowledge
• 3 theore.cal Problem Sets: 12% x 3 = 36% • 3 programming assignments: 12% x 3 = 36% • Final Exam: 20% • Late policy
• 5 free late days – use them in your ways • Ajerwards, 25% off per day late • Not accepted ajer 3 late days per PS
• Collabora.on policy • Read the student code book, understand what is ‘collabora.on’ and what is ‘academic infrac.on’
20-‐Sep-‐13 48