introduction
play

Introduction Computer Vision Fall 2018 Columbia University - PowerPoint PPT Presentation

Introduction Computer Vision Fall 2018 Columbia University Cameras everywhere Also scary times What is vision? What does it mean, to see? The plain man's answer (and Aristotle's, too) would be, to know what is where by looking.


  1. Introduction Computer Vision Fall 2018 Columbia University

  2. Cameras everywhere

  3. Also scary times

  4. What is vision? “What does it mean, to see? The plain man's answer (and Aristotle's, too) would be, to know what is where by looking.” — David Marr, 1982 1945 - 1980 (35 years old)

  5. Computational Photography

  6. Biometrics • "the most recognized photograph” in the history of the National Geographic magazine • No one knew her identity… 1984

  7. Biometrics 1984 2002

  8. Optical Character Recognition

  9. Security and Tracking “The work was painstaking and mind-numbing: One agent watched the same segment of video 400 times. The goal was to construct a timeline of images, following possible suspects as they moved along the sidewalks. It took a couple of days” Washington Post

  10. Health

  11. Gaming

  12. Shopping

  13. Special Effects

  14. Visual Search

  15. Self-driving Cars

  16. Space Exploration

  17. Augmented Reality

  18. Worldwide Insight Walmart in Wichita, Kansas

  19. What is vision? Slide credit: Kristen Grauman

  20. Image Formation Object Film Slide credit: Steve Seitz

  21. Image Formation Object Barrier Film Add a barrier to block off most of the rays Slide credit: Steve Seitz

  22. Representing Digital Images Slide credit: Deva Ramanan

  23. Representing Digital Images Slide credit: Deva Ramanan

  24. Representing Color Images Color images, RGB color space B R G

  25. Illumination “Neither Autopilot nor the driver noticed the white side of the tractor trailer against a brightly lit sky, so the brake was not applied.” — Tesla Company Blog Slide credit: S. Ullman

  26. Occlusion René Magritte, 1957

  27. Class Variation Slide credit: Antonio Torralba

  28. Clutter and Camouflage

  29. Color

  30. Motion Slide credit: S. Lazebnik

  31. Ill-posed Problem

  32. Ill-posed Problem

  33. Ill-posed Problem

  34. Cambrian Explosion Time

  35. Cambrian Explosion "The Cambrian Explosion is triggered by the sudden evolution of vision,” which set o ff an evolutionary arms race where animals either evolved or died. — Andrew Parker Slide credit: Fei-Fei Li

  36. Evolution of Biological Eye

  37. A quick experiment 
 Animals or Not? You will see a mask, then image, then mask. What do you see? Slide credit: Jia Deng

  38. Slide credit: Jia Deng

  39. 150$ms$!!$ Thorpe, et al. Nature, 1996

  40. Why not build a brain? About 1/3rd of the brain is devoted to visual processing

  41. Do we have the hardware? 10 11 parallel neurons 10 8 serial transistors

  42. We don’t know the software

  43. Adelson Illusion

  44. Illusionary Motion

  45. Scale Ambiguity

  46. The Ames Room

  47. The Ames Room (E ff ect used in Lord of the Rings)

  48. Heider-Simmel Illusion

  49. What objects are here? Slide credit: Rob Fergus and Antonio Torralba

  50. Context Slide credit: Rob Fergus and Antonio Torralba

  51. Context Slide credit: Fei-Fei Li, Rob Fergus and Antonio Torralba

  52. Tool 1: Physics and Geometry

  53. Tool 2: Data and Learning

  54. Two Extremes of Vision Slide credit: Aude Oliva

  55. Evolution of Vision Datasets Created here in 1996 Slide credit: Aude Oliva

  56. Course Information Computer Vision Fall 2018 Columbia University

  57. About Me UC Irvine

  58. About Me MIT UC Irvine

  59. About Me MIT Google UC Irvine

  60. About Me MIT Google Columbia UC Irvine

  61. What about you? • Major? • Year? • Research area?

  62. Staff and Office Hours • Carl Vondrick 
 O ffi ce Hours: Monday 4:30pm to 5:30pm 
 CSB 502 (temporary) • TAs: • Oscar: TBA • Xiaoning: Monday, 5-6pm, CS TA Room • Bo: Tuesday, 3-4pm, CS TA Room • James: TBA • Luc: TBA

  63. FAQ: Can you add me? • We’re at capacity: 110 people enrolled • 200 people on wait list • If you don’t plan to take class, please drop soon

  64. FAQ: Do I need to know C? • No. The problem sets will use Python . • Familiarity with linear algebra and calculus will be helpful but not required.

  65. FAQ: How to contact you? • No emails — please use Piazza • You can send private messages on Piazza • Course sta ff goes o ffl ine 7pm to 10am and weekends

  66. Grading • 60% Problem Sets • 40% Final Project • No exams or quizzes

  67. Problem Sets • 5 problem sets, equally weighted • Turn in via CourseWorks before class starts. Submit both PDF writeup and code online. • One problem set may be a week late. No other extensions. • Solutions available during TA o ffi ce hours. • Done individually, but you can have high-level discussion in pairs. Write up assignments individually

  68. Final Project • Individually or pairs (recommended) • Final poster presentations: Dec 5 and Dec 10 • 4 page report in CVPR format • Suggested projects and grading rubric to be announced

  69. Academic Honesty • Academic dishonesty may result in… • You fail course. • We refer your case to the Dean’s o ffi ce.

  70. Readings (Optional) http://szeliski.org/Book/

  71. New Course • Feedback appreciated. • Please let us know if something works or not!

  72. Next Class: Linear Filters

Recommend


More recommend