Mapillary

From OpenStreetMap Wiki
Jump to: navigation, search
Available languages
Mapillary link showing the Mapillary Malmö office
Mapillary Global Coverage Jan 2015

Mapillary (mapillary.com) is a service for sharing geotagged photos developed by a startup, located in Malmö, Sweden. Its creators want to represent the whole world (not only streets) with photos [1][2]. They believe that for covering all interesting places in the world, there needs to be an independent, crowd-sourced project and a systematic approach to cover interesting areas. Services like Google, having especially equipped cars with camera mounts, are not going to be able to cover the world in sufficient detail [1]. According to them, the local knowledge is almost unbeatable, and people know what really matters in capturing a photo [1]. They are interested in coverage of any outdoor place and this can contribute to a system that represents the world with high level of detail [1]. Most of the "intelligence" of image processing is done on the server side using Big data technologies and computer vision, making the data collection super simple for the user. As a result, Mapillary will improve with each new photo since all new photos are related to any existing photos in the vicinity. Here is a short presentation [3] for a brief technical overview. The idea is that the users of the data are empowered to increase coverage in areas that interest them [1]. The developers of Mapillary believe there is a place in the market for a provider of neutral and independent pictures [1][2]

The contributors can install the Mapillary app on WindowsPhone, Android or iPhone, there are successful reports from even Kindle App Store, Jolla and Blackberry devices that can run Android apps. After registration, the user can start taking photos.

At developer resources, the JSON API is documented, including an embeddable Widget.

Mapillary Examples

The Mapillary Workflow

Main article: Mapillary/Data collection with Mapillary

Traffic sign recognition

A traffic sign recognition algorithm has processed the Mapillary images in the United States and in Europe[4]. To view the results, point the browser to any Mapillary image, click on the filter button in the lower left corner and enable the traffic sign filter.

If incorrectly marked traffic signs are spotted, feedback can be given by enabling a traffic sign mode when logged into Mapillary [5]. You can also provide feedback when you click on the box around the detected traffic sign in the Mapillary image. The traffic sign can then be changed in the dialog.

License

The images on Mapillary can by used under Creative Commons Attribution-ShareAlike 4.0 International License (CC-BY-SA).[6] There is special permission to derive data from the photos for contributing to OpenStreetMap. The GPX tracks can be used without restriction.

The license was changed on 29 April 2014 from CC-BY-NC to CC-BY-SA. [7]

References

  1. 1.0 1.1 1.2 1.3 1.4 Welcome to Mapillary! (en), by Jan Erik Solem. Posted on 1 Jan 2014.
  2. 2.0 2.1 Mapillary Manifesto (en), by Jan Erik, Johan, Peter and Yubin (a.k.a the Mapillary team).
  3. Technical Overview (en) by Peter Neubauer
  4. "Traffic Sign Recognition". 2015-01-27. http://blog.mapillary.com/update/2015/01/27/traffic-signs.html. Retrieved 2015-03-15. 
  5. "Traffic Sign Recognition Feedback". 2015-02-11. http://blog.mapillary.com/update/2015/02/11/traffic-sign-recognition-feedback.html. Retrieved 2015-03-15. 
  6. [1]