Today we’re unveiling a major new project in Bing. Technically it’s an indexing, unification, and connection of the world’s geo-linked media. Informally, it’s the magic of:

  • Seeing your photos automatically connected to others;
  • Being able to simply create immersive experiences from your or your friends photos, videos, and panoramas;
  • “Fixing” the world, when the official imagery of your street is out of date;
  • Visually mapping your business, your favorite park, or your real estate for everyone to see;
  • Understanding the emergent information from the density and tagging of media.

The Read/Write World has 3 pillars: Clear Content Rights; Uniform Access and Open Source Viewers; and Real-Time Geo-Services.

Clear Content Rights
We strongly support media creators and owners controlling their content. The Read/Write World will be most useful to owners who allow others to re-use their content, and we support the Creative Commons licenses as the best way to manage and communicate this. If you want to retain absolute copyright control, or even make your geo-linked media available in the public domain, the Read/Write World supports this too. More detailed information here.

Uniform Access and Open Source Viewers
Being able to index all the geo-media is one thing, but what most people will really want to do is consume it in a smooth and connected way. They’ll want to “swim” through it, and they want to do this on desktops, mobile, and tablets.

To enable this kind of fluid access, we’ve created a small language for describing the geometric relationship between media elements. We call it RML, and describe it in the this post.

The Read/Write World project will create and support Open Source HTML5 viewing code, and will collaborate and support those people or companies who are interested in creating viewers for specific platforms and graphics stacks. Below is a rough video from our prototype viewer. It’s not ready for open sourcing just yet.

The goals of a Read/Write World viewer are ambitious. Our prototype shows the importance of being able to combine nadir, oblique, and “human scale” map imagery with photos (flat or multi-resolution), panoramas (equirectangular, cylindrical, cubemapped, …) video in different formats, models (locally or globally textured), and annotations. In order to span and connect these diverse representations, we’ve invented a little glue language that we modestly call “Reality Markup Language” (RML). Read up on RML here.

Real Time Geo-Services
The services side of the Read/Write world is where Bing is making it’s biggest effort. Current services in development incude

  • Instant indexing and editing of media described in RML
  • Accurate location matching between images, panoramas, videos and textures. The results are available in less than 1 second, and return RML homographies so that a viewer can show the geometric relationship between the media objects. A working demo of the Location Matching API is here.
  • Storage and CDN services. You do not need to use our storage to take advantage of the other services Read/Write World, but every user will get 20GB of free Microsoft-Azure-based storage and use of the Azure content distribution network for rapid worldwide delivery.
  • Resampling Services. So far, these include video stabilization and endpoint adjustment; panorama flattening and thumbnailing; tiling and untiling large images and panoramas

A prototype editor, connected to the Read/Write index, and calling the Location matching services is shown in the following video.

- The Bing Team