[OSM-dev] Project Proposal - Waze Integration

[Eric Marsden]

>>>>> "pr" == peter  <petervotzi at gmail.com> writes:

  pr> I have proposed a student project called "Incorporation of Traffic
  pr> Information and OpenStreetMap data"[1] , which has similar goals like
  pr> the integration of waze. But deals more with the server part of the
  pr> application and will be (of course) as open as openstreetmap is.

  Hi Peter,

  Your proposal is interesting, but given the technical challenges you
  will face, it seems overly optimistic to me. I'm also not convinced
  that many people would be sufficiently motivated to manually report
  transient information such as "roadworks here", so I think your focus
  should be on automated extraction of information from live GPS logs.

  I expect that matching poor quality GPS logs (think smartphones) to
  OSM data (without concern for the dynamic nature of this data), and
  generating information with sufficient confidence about missing ways,
  turn restrictions, missing or incorrect oneway tags would already be a
  good challenge. Generating information about traffic conditions would
  be another possibility, but with less direct utility to OSM.

  Concerning the matching of GPS logs, I suggest you read the paper
  "Hidden Markov Map Matching Through Noise and Sparseness"[1] and perhaps
  prior art from the CarTel project[2]. 

  [1] http://research.microsoft.com/en-us/um/people/jckrumm/
  [2] http://cartel.csail.mit.edu/doku.php
  
-- 
Eric Marsden