f Fossett search: geotagging plus crowdsourcing! at Stephenson blogs on homeland security 2.0 et al.

« Flight 93, te salutamus! What this blog and my work are all about | Home | My first data visualization! word cloud of bin Laden video »

Fossett search: geotagging plus crowdsourcing!

By WDavidStephenson | September 12, 2007

On Monday I predicted .that geotagging might someday be a valuable Homeland Security 2.0 tool.

I guess “someday” meant today.

Early this morning I heard a NPR story (here’s BBC version) about how Richard Branson had paid several satellite companies to shoot new images of the area where his pal Steve Fossett’s plane might have crashed.

Then he hired Amazon’s “Mechanical Turk” service (you gotta read why it’s called that!) to analyze the images:

“Today, we build complex software applications based on the things computers do well, such as storing and retrieving large amounts of information or rapidly performing calculations. However, humans still significantly outperform the most powerful computers at completing such simple tasks as identifying objects in photographs—something children can do even before they learn to speak.

“When we think of interfaces between human beings and computers, we usually assume that the human being is the one requesting that a task be completed, and the computer is completing the task and providing the results. What if this process were reversed and a computer program could ask a human being to perform a task and return the results? What if it could coordinate many human beings to perform a task?

“Amazon Mechanical Turk provides a web services API for computers to integrate ‘artificial artificial intelligence’ directly into their processing by making requests of humans. Developers use the Amazon Mechanical Turk web service to submit tasks to the Amazon Mechanical Turk web site, approve completed tasks, and incorporate the answers into their software applications. To the application, the transaction looks very much like any remote procedure call: the application sends the request, and the service returns the results. Behind the scenes, a network of humans fuels this artificial artificial intelligence by coming to the web site, searching for and completing tasks, and receiving payment for their work.”

Quick like a bunny, I went to the Mechanical Turk site, signed up, and was assigned a small area (see above image) to scour for any signs of Fossett’s plane (to double check, you can also download that specific image, and plug it into Google Earth to be able to manipulate it, try various angles, etc., using Google Earth tools).

Sadly, I didn’t find the plane. However, given the combination of the high resolution of satellite images today and this system of combining it with “artificial artificial intelligence” (AKA crowdsourcing) you’ve got to assume that there’s at least as much chance, if not more, that one of us Mechanical Turks will find it as one of the spotters, who are, after all, moving and can’t go over such a small sector repeatedly.

Granted, not everyone who is missing has a billionaire friend who is willing to foot this kind of expense, but this kind of exercise will definitely build public understanding of the approach, and may result in creation of corps of volunteers who are willing, from the comfort of their homes, to comb geotagged images in the future after natural disasters, when climbers are lost, etc.

Wow!

Tell a friend:

Technorati tags:

Sphere: Related Content

Topics: technology, empowering public, collaboration, e-gov transformation, networked security | |