Computer Vision Lecture 1

1. Computer Vision
(A36606)
Course Faculty: Mrs Sakina Hazrat Sayyed

2. Introduction to Computer Vision
Why Image?

5. Human Vision and Computer Vision:

6. Computer vision vs human vision
What we see What a computer sees

10. What is Computer Vision?
• Vision is about discovering from images what is
present in the scene and where it is.
• In Computer Vision a camera (or several cameras) is
linked to a computer. The computer interprets images
of a real scene to obtain information useful for tasks
such as navigation, manipulation and recognition.

11. The goal of computer vision
Make computers understand images and videos.
What kind of scene?
Where are the cars?
How far is the
building?
…

12. Computer Vision is multidisciplinary :

13. What is Computer Vision NOT?
• Image processing: image enhancement, image
restoration, image compression. Take an image and
process it to produce a new image which is, in some
way, more desirable.
• Computational Photography: extending the
capabilities of digital cameras through the use of
computation to enable the capture of enhanced or
entirely novel images of the world.

14. Difference Between Image Processing and
Computer Vision:

15. Brief History of Computer
Vision

23. Fischler
and
elschlager
1973

33. Applications of Computer
Vision

34. 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 readers
http://en.wikipedia.org/wiki/Automatic_number_plate_recognition

35. Face detection
• Many new digital cameras now detect faces
– Canon, Sony, Fuji, …

36. Smile detection
Sony Cyber-shot® T70 Digital Still Camera

37. 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… “

38. Vision-based biometrics
“How the Afghan Girl was Identified by Her Iris Patterns” Read the story
wikipedia

39. 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/

40. Object recognition (in mobile phones)
Point & Find, Nokia
Google Goggles

41. The Matrix movies, ESC Entertainment, XYZRGB, NRC
Special effects: shape capture

42. Pirates of the Carribean, Industrial Light and Magic
Special effects: motion capture

43. Sports
Sportvision first down line
Nice explanation on www.howstuffworks.com
http://www.sportvision.com/video.html

44. 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

45. Google cars
http://www.nytimes.com/2010/10/10/science/10google.html?ref=artificialintelligence

46. Interactive Games: Kinect
• Object Recognition:
http://www.youtube.com/watch?feature=iv&v=fQ59dXOo63o
• Mario: http://www.youtube.com/watch?v=8CTJL5lUjHg
• 3D: http://www.youtube.com/watch?v=7QrnwoO1-8A
• Robot: http://www.youtube.com/watch?v=w8BmgtMKFbY

47. 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.

48. Industrial robots
Vision-guided robots position nut runners on wheels

49. Mobile robots
http://www.robocup.org/
NASA’s Mars Spirit Rover
http://en.wikipedia.org/wiki/Spirit_rover
Saxena et al. 2008
STAIR at Stanford

50. Medical imaging
Image guided surgery
Grimson et al., MIT
3D imaging
MRI, CT

51. Vision as a source of semantic information
slide credit: Fei-Fei, Fergus & Torralba

52. Object categorization
sky
building
flag
wall
banner
bus
cars
bus
face
street lamp
slide credit: Fei-Fei, Fergus & Torralba

53. Scene and context categorization
• outdoor
• city
• traffic
• …
slide credit: Fei-Fei, Fergus & Torralba

54. Qualitative spatial information
slanted
rigid moving
object
horizontal
vertical
slide credit: Fei-Fei, Fergus & Torralba
rigid moving
object
non-rigid moving
object

55. Challenges in Computer
Vision

56. Challenges: viewpoint variation
Michelangelo 1475-1564 slide credit: Fei-Fei, Fergus & Torralba

57. Challenges: illumination
image credit: J. Koenderink

58. Challenges: scale
slide credit: Fei-Fei, Fergus & Torralba

59. Challenges: deformation
Xu, Beihong 1943

60. Challenges: occlusion
Magritte, 1957 slide credit: Fei-Fei, Fergus & Torralba

61. Challenges: background clutter

62. Challenges: object intra-class variation
slide credit: Fei-Fei, Fergus & Torralba

63. Challenges: local ambiguity
slide credit: Fei-Fei, Fergus & Torralba

64. Challenges or opportunities?
• Images are confusing, but they also reveal the structure of
the world through numerous cues
• Our job is to interpret the cues!
Image source: J. Koenderink

65. Bottom line
• Perception is an inherently ambiguous problem
– Many different 3D scenes could have given rise to a particular
2D picture
Image source: F. Durand

66. Bottom line
• Perception is an inherently ambiguous problem
– Many different 3D scenes could have given rise to a particular 2D
picture
• Possible solutions
– Bring in more constraints ( or more images)
– Use prior knowledge about the structure of the world
• Need both exact measurements and statistical inference!
Image source: F. Durand