Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Day2-1600-Telemetry, global traffic and OSM

sotm2017
September 01, 2017

Day2-1600-Telemetry, global traffic and OSM

sotm2017

September 01, 2017
Tweet

More Decks by sotm2017

Other Decks in Research

Transcript

  1. T E L E M E T R Y
    enhancing & unlocking new potential in OSM

    View full-size slide

  2. OV E RV I E W
    what is telemetry?
    how does Mapbox handle telemetry data?
    what we can calculate from telemetry data?
    what are the use cases?
    traffic

    View full-size slide

  3. T E L E M E T RY
    any data collected from a remote device
    [lng, lat, alt, timestamp]
    telemetry
    pipeline
    clock
    GPS sensor
    +

    View full-size slide

  4. “probe”
    [x, y, z, t]
    P RO B E VS . T R AC E

    View full-size slide

  5. “trace”
    [ [x, y, z, t], [x, y, z, t], [x, y, z, t], [x, y, z, t] ]
    P RO B E VS . T R AC E

    View full-size slide

  6. A N O N Y M I S AT I O N

    View full-size slide

  7. A N O N Y M I S AT I O N

    View full-size slide

  8. A N O N Y M I S AT I O N

    View full-size slide

  9. A N O N Y M I S AT I O N

    View full-size slide

  10. P R I VAC Y
    only store anonymised data
    data is encrypted using industry best practice
    clear boundaries around who has access & for what reason
    audit-able access logs
    more info – https://www.mapbox.com/telemetry/

    View full-size slide

  11. “probe”
    [x, y, z, t]
    “trace”
    [ [x, y, z, t], [x, y, z, t], [x, y, z, t], [x, y, z, t] ]

    View full-size slide

  12. B E A R I N G

    View full-size slide

  13. speed =
    distance
    duration
    S P E E D
    d
    ∆t

    View full-size slide

  14. acceleration =
    ∆speed
    duration
    AC C E L E R AT I O N

    View full-size slide

  15. U S E C A S E S

    View full-size slide

  16. VO LU M E
    from probe density
    missing streets
    satellite imagery alignment
    health of satellite imagery

    View full-size slide

  17. VO LU M E
    from probe density
    missing streets
    satellite imagery alignment
    health of satellite imagery

    View full-size slide

  18. VO LU M E
    from probe density
    missing streets
    satellite imagery alignment
    health of satellite imagery
    telemetry
    density
    raster
    satellite
    imagery
    edge detection
    edge detection
    vertical
    offset
    horizontal offset
    *

    View full-size slide

  19. VO LU M E
    from probe density
    missing streets
    satellite imagery alignment
    health of satellite imagery
    telemetry
    density
    poor imagery quality

    View full-size slide

  20. M A N E U V E R S
    from trace density
    restrictions (turns, one-ways)
    high-precision trajectory of
    lane centreline for ADAS
    traces present
    absence of traces

    View full-size slide

  21. M A N E U V E R S
    from trace density
    restrictions (turns, one-ways)
    high-precision trajectory of
    lane centreline for ADAS

    View full-size slide

  22. T R A F F I C
    from speed, bearing, acceleration
    road congestion
    traffic-aware navigation

    View full-size slide

  23. T R A F F I C
    from speed, bearing, acceleration
    road congestion
    traffic-aware navigation

    View full-size slide

  24. T R A F F I C

    View full-size slide

  25. W H Y T R A F F I C
    origin destination
    estimated
    trip duration
    (ETA)
    date-time
    traffic-powered OSRM
    OSRM public demo server

    View full-size slide

  26. LUA P RO F I L E
    rule-based
    static
    100% road coverage

    View full-size slide

  27. T R A F F I C P RO F I L E
    telemetry-based
    dynamic
    coverage fluctuates
    (never 100%)

    View full-size slide

  28. N O I S E R E M OVA L
    duration
    distance
    speed
    bearing
    deceleration
    acceleration
    modality

    View full-size slide

  29. P RO B E M ATC H
    distance from road
    bearing from road
    highway hierarchy

    View full-size slide

  30. P RO B E M ATC H
    distance from road
    bearing from road
    highway hierarchy

    View full-size slide

  31. P RO B E M ATC H
    distance from road
    bearing from road
    highway hierarchy

    View full-size slide

  32. P RO B E M ATC H
    distance from road
    bearing from road
    highway hierarchy
    higher rank
    lower rank

    View full-size slide

  33. P RO B E M ATC H
    tertiary road
    distance from road
    bearing from road
    highway hierarchy

    View full-size slide

  34. N O R M A L I S E D
    G R A P H
    traffic data uses
    split at
    road class change
    intersection
    merge otherwise.

    View full-size slide

  35. N O R M A L I S E D
    G R A P H
    traffic data uses
    split at
    road class change
    intersection
    merge otherwise.

    View full-size slide

  36. N O R M A L I S E D
    G R A P H
    traffic data uses
    split at
    road class change
    intersection
    merge otherwise.

    View full-size slide








  37. 0 20 40 60 80 100 120 140 160
    Speed [kph]
    Count [-]
    W H I C H S P E E D

    View full-size slide








  38. 0 20 40 60 80 100 120 140 160
    Count [-]
    W H I C H S P E E D
    primary
    secondary
    tertiary
    motorway
    trunk
    links
    alleys
    service roads
    …etc.
    Speed [kph]

    View full-size slide

  39. N O R M A L I S E D
    G R A P H
    traffic data uses

    View full-size slide

  40. E D G E - BA S E D
    G R A P H
    OSRM uses
    transform
    maneuver → edge
    street → node

    View full-size slide

  41. segments
    N O R M A L I S E D
    G R A P H
    traffic data uses
    E D G E - BA S E D
    G R A P H
    OSRM uses

    View full-size slide

  42. segments
    N O R M A L I S E D
    G R A P H
    traffic data uses
    E D G E - BA S E D
    G R A P H
    OSRM uses
    T R A F F I C
    M A P S
    I N C I D E N T S
    T U R N
    P E N A LT I E S
    R E A LT I M E
    T R A F F I C
    VO LU M E

    View full-size slide

  43. T E L E M E T RY
    ETA, error percentile, etc.
    layer against
    road network &
    attributes
    road network &
    attributes
    better, fresh satellite imagery
    where to
    focus
    (proactive)
    what is
    suspicious
    (proactive)
    where/what
    is an issue
    (reactive)
    where imagery
    is outdated
    DATA
    T E A M
    DATA
    T E A M
    S AT E L L I T E
    T E A M
    traffic

    View full-size slide