1. Introduction to Computer Vision
Based on slides by
Jinxiang Chai,
Svetlana Lazebnik,
Guodong Guo
Assembled and modified
by Longin Jan Latecki
September 2012 1

2. What is Computer Vision?
Computer vision is the science and technology of machines that see.
Concerned with the theory for building artificial systems that obtain information from images.
The image data can take many forms, such as a video sequence, depth images, views from multiple cameras, or multi-dimensional data from a medical scanner 2

3. Computer Vision Make computers understand images and videos.
What kind of scene?
Where are the cars?
How far is the building? …

4. Components of a computer vision system
Camera
Lighting
Scene Interpretation
Computer
Scene
Srinivasa Narasimhan’s slide

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

6. Is that a queen or a bishop?
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 a queen or a bishop?

7. Vision is multidisciplinary
Computer Graphics
HCI
From wiki

8. Why computer vision matters
Health
Security
Safety
Fun
Comfort
Access

9. A little story about Computer Vision
In 1966, Marvin Minsky at MIT asked his undergraduate student Gerald Jay Sussman to “spend the summer linking a camera to a
computer and getting the computer to describe what it saw”. We now know that the problem is slightly more difficult than that. (Szeliski 2009, Computer Vision)

10. A little story about Computer Vision
Founder, MIT AI project
In 1966, Marvin Minsky at MIT asked his undergraduate student Gerald Jay Sussman to “spend the summer linking a camera to a
computer and getting the computer to describe what it saw”. We now know that the problem is slightly more difficult than that.

11. A little story about Computer Vision
In 1966, Marvin Minsky at MIT asked his undergraduate student Gerald Jay Sussman to “spend the summer linking a camera to a
computer and getting the computer to describe what it saw”. We now know that the problem is slightly more difficult than that.
Image Understanding

12. Ridiculously brief history of computer vision
1966: Minsky assigns computer vision as an undergrad summer project
1960’s: interpretation of synthetic worlds
1970’s: some progress on interpreting selected images
1980’s: ANNs come and go; shift toward geometry and increased mathematical rigor
1990’s: face recognition; statistical analysis in vogue
2000’s: broader recognition; large annotated datasets available; video processing starts; vision & graphis; vision for HCI; internet vision, etc.
Guzman ‘68
Ohta Kanade ‘78
Turk and Pentland ‘91

13. How vision is used now
Examples of state-of-the-art

14. Optical character recognition (OCR)
Technology to convert scanned docs to text
If you have a scanner, it probably came with OCR software
Digit recognition, AT&T labs
License plate readers

15. Face detection Many new digital cameras now detect faces
Why would this be useful? Main reason is focus. Also enables “smart” cropping.
Many new digital cameras now detect faces
Canon, Sony, Fuji, …

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

17. 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… “

18. Vision-based biometrics
“How the Afghan Girl was Identified by Her Iris Patterns” Read the story
wikipedia
Age 12, Age 30,
The mathematical odds against such an event are 6 million to one for her right eye

19. Login without a password…
Face recognition systems now beginning to appear more widely
Fingerprint scanners on many new laptops, other devices

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

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

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

23. Sports Sportvision first down line
Since 1998
Sportvision first down line
Nice explanation on

24. Slide content courtesy of Amnon Shashua
Smart cars
Slide content courtesy of Amnon Shashua
Mobileye [wiki article]
Vision systems currently in many car models

25. Google cars

26. Interactive Games: Kinect
Object Recognition:
Mario:
3D:
Robot:
3D tracking, reconstruction, and interaction:

27. Vision in space Vision systems (JPL) used for several tasks
NASA'S Mars Exploration Rover Spirit captured this westward view from atop a low plateau where Spirit spent the closing months of 2007.
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.

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

29. NASA’s Mars Spirit Rover
Mobile robots
NASA’s Mars Spirit Rover
Saxena et al. 2008
STAIR at Stanford

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

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

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

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

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

35. Challenges: viewpoint variation
Michelangelo
slide credit: Fei-Fei, Fergus & Torralba

36. Challenges: illumination
image credit: J. Koenderink

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

38. Challenges: deformation
Xu, Beihong 1943
slide credit: Fei-Fei, Fergus & Torralba

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

40. Challenges: background clutter

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

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

43. 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

44. 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

45. 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

46. Computer Vision vs. Graphics
3D2D implies information loss
sensitivity to errors
need for models
graphics
vision

47. Imaging Geometry

48. Camera Modeling Pinhole Cameras Lenses
Camera Parameters and Calibration

49. Image Filtering and Enhancing
Linear Filters and Convolution
Image Smoothing
Edge Detection

50. Region Segmentation

51. Color

52. Texture

53. Image Restoration / Nose Removal
Original
Synthetic

54. Perceptual Organization

55. Perceptual Organization

56. Shape Analysis

57. Computer Vision Publications
Journals
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI)
#1 IEEE, Thompson-ISI impact factor: 5.96
#1 in both electrical engineering and artificial intelligence
#3 in all of computer science
Internal Journal of Computer Vision (IJCV)
ISI impact factor: 5.358, Rank 2 of 94 in “CS, artificial intelligence
IEEE Trans. on Image Processing …
Conferences
Conf. of Computer Vision and Pattern Recognition (CVPR), once a year
International Conference on Computer Vision (ICCV), once every two years
Europe Conference on Computer Vision (ECCV), once every two years