More Pixels Law: How The Camera is Becoming the World's Most Important Sensor

An introduction to the importance and methods of computer vision. Presented at O'Reilly's Solid Conference 2014.

Transcript

1. More Pixels Law
   How The Camera is Becoming the World's Most Important Sensor
   Greg Borenstein
   @atduskgreg
   MIT Media Lab, Playful Systems
   

   View Slide

2. View Slide

3. OpenCV for Processing
   
   github.com/atduskgreg/opencv-processing
   

   View Slide

4. github.com/atduskgreg/opencv-processing-book
   

   View Slide

5. View Slide

6. Graph designed
   by Jason Huff
   

   View Slide

7. Duke University AWARE Program
   
   mosaic.disp.duke.edu
   

   View Slide

8. Argus Drone Platform
   
   DARPA
   

   View Slide

9. Coarse Gaze Estimation in Visual Surveillance
   
   Oxford University’s Active Vision Group
   

   View Slide

10. View Slide

11. View Slide

12. View Slide

13. View Slide

14. View Slide

15. View Slide

16. Cardiio
    

    View Slide

17. Depth from Motion
    Android “Lens Blur” feature
    

    View Slide

18. github.com/jetpacapp/DeepBeliefSDK
    

    View Slide

19. Capture
    Calibrate
    Filter
    Track
    Shape
    Train
    Predict
    

    View Slide

20. View Slide

21. Capture
    !
    !
    !
    !
    !
    

    View Slide

22. Capture
    Calibrate
    !
    !
    !
    !
    

    View Slide

23. View Slide

24. Capture
    Calibrate
    !
    !
    !
    !
    

    View Slide

25. Capture
    Calibrate
    Filter
    !
    !
    !
    

    View Slide

26. View Slide

27. View Slide

28. View Slide

29. View Slide

30. View Slide

31. View Slide

32. View Slide

33. View Slide

34. View Slide

35. Capture
    Calibrate
    Filter
    !
    !
    !
    

    View Slide

36. Capture
    Calibrate
    Filter
    Track
    !
    !
    

    View Slide

37. View Slide

38. View Slide

39. View Slide

40. View Slide

41. View Slide

42. View Slide

43. docs.opencv.org/doc/tutorials/features2d/feature_detection/feature_detection.html
    

    View Slide

44. View Slide

45. View Slide

46. Capture
    Calibrate
    Filter
    Track
    !
    !
    

    View Slide

47. Capture
    Calibrate
    Filter
    Track
    Shape
    !
    

    View Slide

48. View Slide

49. View Slide

50. View Slide

51. arnab.org/blog/so-i-suck-24-automating-card-games-using-opencv-and-python
    

    View Slide

52. arnab.org/blog/so-i-suck-24-automating-card-games-using-opencv-and-python
    

    View Slide

53. View Slide

54. Capture
    Calibrate
    Filter
    Track
    Shape
    !
    

    View Slide

55. Capture
    Calibrate
    Filter
    Track
    Shape
    Train
    Predict
    

    View Slide

56. Supervised Learning
    Gather
    Label
    Represent
    Train
    Predict
    

    View Slide

57. View Slide

58. Label: A
    Label:B
    Label: C
    

    View Slide

59. View Slide

60. View Slide

61. Thanks
    Greg Borenstein
    @atduskgreg
    gregborenstein.com
    github.com/atduskgreg/opencv-processing
    github.com/atduskgreg/opencv-processing-book
    

    View Slide