Day1-1440-High precision mapping with streetlevel imagery

Friday 2:40pm, Main hall
Oindrila Gupta

http://2017.stateofthemap.org/2017/high-precision-mapping-with-streetlevel-imagery/

Transcript

1. High Precision Mapping
   with Street-level imagery
   

   View Slide

2. Current state of the map:
   

   View Slide

3. 116.8million highways
   Source: Jennings Anderson
   

   View Slide

4. Source: Jennings Anderson
   28.6% (33million) roads have names
   

   View Slide

5. • 28.6% have names
   • 9.6% are oneways
   • 6.4% have speed-limits
   • 4.2% have access tags
   

   View Slide

6. 242million buildings
   Source: Jennings Anderson
   

   View Slide

7. • 3.6% have building levels
   • 1.6% have names
   

   View Slide

8. 11.6million amenities
   47% have names
   

   View Slide

9. How do we improve this?
   

   View Slide

10. Most common sources for remote
    mapping:
    

    View Slide

11. Satellite and
    aerial imagery
    

    View Slide

12. Third party
    data
    

    View Slide

13. GPS Traces
    

    View Slide

14. Street-level
    imagery
    

    View Slide

15. What is Street-level imagery?
    

    View Slide

16. Images having:
    • latitude, longitude
    • altitude (optionally)
    • bearing
    

    View Slide

17. Most common open-licensed, street-level imagery providers
    

    View Slide

18. Editing OpenStreetMap using
    street-level imagery
    

    View Slide

19. has plugins for:
    • Mapillary
    • OpenStreetCam
    

    View Slide

20. Download plugins:
    ‘Preferences’ ->
    ‘Plugins’
    

    View Slide

21. Open plugins from
    ‘Imagery’
    

    View Slide

22. View Slide

23. View Slide

24. has support for
    Mapillary
    

    View Slide

25. In ‘Map Data’ turn on
    ‘Photo Overlay’ and
    ‘Traffic Sign Overlay’
    

    View Slide

26. View Slide

27. Mapping common features from
    street-level imagery
    

    View Slide

28. Traffic Signs
    

    View Slide

29. detects traffic signs from images
    

    View Slide

30. View Slide

31. View Slide

32. View Slide

33. View Slide

34. View Slide

35. View Slide

36. View Slide

37. View Slide

38. View Slide

39. View Slide

40. Building Details
    

    View Slide

41. View Slide

42. How we use street-level
    imagery at Mapbox
    

    View Slide

43. Mapping Navigational assets
    

    View Slide

44. osm-navigation map: mapbox.github.io/osm-navigation-map/
    

    View Slide

45. Verifying user feedbacks
    

    View Slide

46. Detecting harmful/incorrect edits
    

    View Slide

47. Future Potential
    

    View Slide

48. Source: mapbox.github.io/osm-analysis-collab/editor-density
    Mappers are everywhere
    

    View Slide

49. Current Mapillary coverage
    

    View Slide

50. Email: oindrila@mapbox.com
    Twitter: Oindrila_G
    

    View Slide

51. Questions?
    

    View Slide