A technology called Photosynth, developed by Microsoft Research in collaboration with University of Washington, has the potential to change the way we look at maps.

Photosynth takes a large collection of photos of a place or object, analyzes them for similarities, and displays them in a reconstructed 3-Dimensional space.

This is quite possibly one of the most exciting pieces of technology that i’ve seen in a long time. It allows you to put together a series of photos, and using data from the images alone, the application detects the location and perspective and automatically recreates a 3D model that you to navigate as if it were one large detailed model. What’s exciting about this technology is that one day it might be possible to run this with a large photo repository, such as flickr, where there are millions of photos of places all over the world. This also has the potential of allowing us to recreate massive 3-dimensional models of popular cities, with a variety of perspectives.

You can see a video demonstration of this technology at Throw Away Your TV.

I can also see this becoming very useful if it were used together with global mapping software. Microsoft has also being developing technology that allows you to navigate streets using a car’s perspective. The difficulty in building a system of this sort is that that it requires all the information to be manually collected by people and all the data needs to be front loaded at the start of the project. This has the long term problem of becoming out of date very quickly, and I imagine that it’d be difficult to update, since cities change erratically. For example, restaurants turn over quickly, so analyzing the changes and updating individual parts of cities will become extremely difficult. With this technology, maps are organically updated by people who casually take photographs in cities. As the city changes and new photographs of locations come in, the application will automatically update those parts of the city. This even has the potential creating a timeline of the city, where you’ll be able to go back in time and navigate cities as it was years before.

I think this technology will become even more powerful if cameras come with built in GPS systems, where metadata, such as the location in earth, is stored in right on the photograph. This will allow applications to more quickly create massive and complete 3D maps of the entire world.

Another part of this project which is quite promising the potential development of “smart cameras.” These cameras will be able to retrieve information about locations and things you photograph from the internet, immediately accessible after you take the photo.

Photosynth begins by processing an image and creating a point cloud that gives the image a unique identifier, a DNA-like profile that describes the features that have been recognized in the image.

Photosynth could connect your photographs into a seamless web of images and information, allowing you to browse a virtual universe of interconnected scenes that constantly evolves and changes over time.

But I see this as the beginnings of the technology that will eventually create complete 3D and navigateable map of earth. It was probably hard to imagine that we’d have something as advanced as Google Earth available for everyone with a computer; where anyone can learn the layout of any city in the world. And today it seems hard to imagine that we’d one day not only be able to learn the city layout, but also learn shops on the corners of cities we’ve never visited.

UPDATE:
digg it?