Upload
others
View
3
Download
0
Embed Size (px)
Citation preview
Introduction25-Sep-2018
1
Lecture: Introduction to Computer Vision
Juan Carlos Niebles and Ranjay KrishnaStanford Vision and Learning Lab
Introduction25-Sep-2018
2Welcome to CS131
Introduction25-Sep-2018
3Jason SalavonGAN experiment on Twitter
Introduction25-Sep-2018
4Mario Klingemann, GAN experiment on Twitter
Introduction25-Sep-2018
5Memo Akten
Introduction25-Sep-2018
6
What you should expect to learn in this class.• What is computer vision?• Which problems fall under this umbrella?• Which applications are possible today and in the near future?• What are common research questions?• What is the history behind these problems and how did it lead to
deep leading?• What tools will help you develop a framework to solve these
problems?
Introduction2
5-S
ep
-20
18
7
CS131 is the introductory course for computer vision
• CS131 (fall, 2017):
– Overview of computer vision and all its applications
–Will prepare you for an industry job in vision
• CS231a (winter, 2018, Prof. Silvio Savarese)
– Advanced Computer Vision
– focusing on 3D vision
• CS231n (spring, 2018):
– Convolutional Neural Networks
Introduction25-Sep-2018
8
Mathematics
ComputerScience
Biology
Engineering
Physics
Psychology
Computer Vision
Neuroscience
Machine learning
Speech, NLP
Information retrieval
Robotics
Cognitive sciences
Algorithms, theory,…
Imageprocessing
Systems, architecture, …
optics
Introduction25-Sep-2018
9
Today’s agenda• Introduction to computer vision• Course overview
Introduction25-Sep-2018
10
Quiz?
Introduction25-Sep-2018
11
What about this?
Introduction25-Sep-2018
12
Image (or video) Sensing device Interpreting device Interpretations
garden, spring,bridge, water,trees, flower,green, etc.
What is (computer) vision?
Introduction25-Sep-2018
13
The goal of computer vision• To bridge the gap between pixels and “meaning”
What we see What a computer sees Sour
ce: S
. Nar
asim
han
Introduction25-Sep-2018
14
Image (or video) Sensing device Interpreting device Interpretations
garden, spring,bridge, water,trees, flower,green, etc.
What is (computer) vision?
Introduction25-Sep-2018
15
1981: Nobel Prize in medicine
Hubel & Wiesel
Introduction25-Sep-2018
16
Potter, Biederman, etc. 1970s
Human vision is superbly efficient
Introduction25-Sep-2018
17Thorpe, et al. Nature, 1996
Introduction25-Sep-2018
18Thorpe, et al. Nature, 1996
150 ms !!
Introduction25-Sep-2018
19
Rensink, O’regan, Simon, etc.
Change Blindness
Introduction25-Sep-2018
20
Rensink, O’regan, Simon, etc.
Change Blindness
Introduction25-Sep-2018
21
Segmentation
Introduction25-Sep-2018
22
Perception
Introduction25-Sep-2018
23
Introduction25-Sep-2018
24
Introduction25-Sep-2018
25
Image (or video) Sensing device Interpreting device Interpretations
garden, spring,bridge, water,trees, flower,green, etc.
What is (computer) vision?
Introduction25-Sep-2018
26
Paintings in 1838
Introduction25-Sep-2018
27
1812: Jacques-Louis-DavidThe Emperor Napoleon at his Study at the Tuileries
Introduction25-Sep-2018
281808: Ingres, La grande baigneuse
Introduction25-Sep-2018
29
“From today, painting is dead”— painter Paul Delaroche
at a demonstration of the Daguerreotype, 1839
Introduction25-Sep-2018
301837: Niépce, First photo of one’s meal
Introduction25-Sep-2018
31
1838
: Bou
leva
rd d
u Te
mpl
e, D
ague
rre
Introduction25-Sep-2018
321838: First selfie, Robert Cornelius
Introduction25-Sep-2018
33DeepDreams[Mordvintsev et al. 2015]
Introduction25-Sep-2018
34
Neural Style Transfer[Gatys et al. 2015]
Introduction25-Sep-2018
35Neural Style Transfer[Gatys et al. 2015]
Introduction25-Sep-2018
36
CycleGAN [Zhu et al. 2017]
Introduction25-Sep-2018
37
The goal of computer vision• To bridge the gap between pixels and “meaning”
What we see What a computer sees
Sour
ce: S
. Nar
asim
han
Introduction25-Sep-2018
38
Origins of computer vision:an MIT undergraduate summer project
L. G. Roberts, Machine Perception of Three Dimensional Solids, Ph.D. thesis, MIT Department of Electrical Engineering, 1963.
Introduction25-Sep-2018
39
What kind of information can we extract from an image?• Metric 3D information• Semantic information
Introduction25-Sep-2018
40
Vision as measurement deviceReal-time stereo Structure from motion
NASA Mars Rover
Pollefeys et al.
Reconstruction fromInternet photo collections
Goesele et al.
Introduction25-Sep-2018
41
sky
water
Ferris wheel
amusement park
Cedar Point
12 E
tree
tree
tree
carouseldeck
people waiting in line
ride
ride
ride
umbrellas
pedestrians
maxair
bench
tree
Lake Erie
people sitting on ride
ObjectsActivitiesScenesLocationsText / writingFacesGesturesMotionsEmotions…
The Wicked Twister
Vision as a source of semantic information
Slid
e c
red
it:
Kri
ste
n G
rau
man
Introduction25-Sep-2018
42
Why study computer vision?• Vision is useful: Images and video are everywhere!
Personal photo albums
Surveillance and security
Movies, news, sports
Medical and scientific images
Introduction25-Sep-2018
43
Special effects: shape and motion capture
Sour
ce: S
. Sei
tz
Introduction25-Sep-2018
44
3D urban modeling
Bing maps, Google Streetview
Source: S. Seitz
Introduction25-Sep-2018
45
3D urban modeling: Microsoft Photosynth
http://photosynth.netSource: S. Seitz
Introduction25-Sep-2018
46
Face detection
• Many digital cameras now detect faces– Canon, Sony, Fuji, …
Source: S. Seitz
Introduction25-Sep-2018
47
Smile detection
Sony Cyber-shot® T70 Digital Still Camera Source: S. Seitz
Introduction25-Sep-2018
48
Face recognition: Apple iPhoto software
http://www.apple.com/ilife/iphoto/
Introduction25-Sep-2018
49
Biometrics
How the Afghan Girl was Identified by Her Iris Patterns
Source: S. Seitz
Introduction25-Sep-2018
50
Biometrics
Fingerprint scanners on many new laptops, other devices
Face recognition systems now beginning to appear more widelyiphone X just introduced face recognition
Introduction25-Sep-2018
51
Optical character recognition (OCR)
Digit recognition, AT&T labs
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
Source: S. Seitz
Introduction25-Sep-2018
52
Google maps: Annotate all houses and streets
Goodfellow et al. 2014
Introduction25-Sep-2018
53
Toys and Robots
Introduction25-Sep-2018
54
Mobile visual search: iPhone Apps
Introduction25-Sep-2018
55
Snapstacles and Google glasses
• That’s Ranjay in undergrad ->
Introduction25-Sep-2018
56
Automotive safety
• Mobileye: Vision systems in high-end BMW, GM, Volvo models – “In mid 2010 Mobileye will launch a world's first application of full
emergency braking for collision mitigation for pedestrians where vision is the key technology for detecting pedestrians.”
Source: A. Shashua, S. Seitz
Introduction25-Sep-2018
57
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
Introduction25-Sep-2018
58
Amazon Go
Introduction25-Sep-2018
59
Vision-based interaction (and games)
Microsoft’s Kinect
Source: S. Seitz
Assistive technologies
Sony EyeToy
Introduction25-Sep-2018
60
Augmented Reality
Introduction25-Sep-2018
61
Virtual Reality
Introduction2
5-S
ep
-20
18
62
Vision for robotics, space exploration
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.
Sour
ce: S
. Sei
tz
Introduction25-Sep-2018
63MGMT “When You Die”