Jump to content
BANGKOK 19 August 2019 19:12
webfact

Facebook uses AI to map Thailand's roads

Recommended Posts

Facebook uses AI to map Thailand's roads

 

Facebook.jpg

White lines represent mapped roads, pink lines represent predicted ones//FACEBOOK

 

Facebook has used artificial intelligence (AI) to map 300,000 miles of previously unmapped roads in Thailand and made the results available to the public.

 

The project had been completed in 18 months, less than half the time it would have taken 100 mapping experts to do it manually, Facebook said.

 

The maps could be used for disaster response and urban planning. Many parts of the world remain unmapped.

 

Full story: https://www.bbc.com/news/technology-49091093

 

bbc.jpg

-- © Copyright BBC 2019-07-25

Share this post


Link to post
Share on other sites

I suppose I am thinking the same as all of you, why? "Disaster response and urban planning" seems to be washing this for public consumption. I can't believe the ultimate motive is not monetary for Facebook.

  • Like 1

Share this post


Link to post
Share on other sites

The roads will also be policed by Facebook users.

  • Haha 2

Share this post


Link to post
Share on other sites

MRTtoMRT, the linked article answers your comment of monetary interests for FB.

Facebook's desire to map the world is linked with its ambitions to expand rural internet access and add more users to its social network.”

More users = more clicks/ad revenue.

  • Like 2

Share this post


Link to post
Share on other sites

What Facebook fail to state is the inaccurate manner in which their AI mapping worked.  The OSM community in Thailand had for years, been working slowly on mapping the Country, with the aim of producing a free to use and accurate map for any user.  Information was added backed by a strong local knowledge, which resulted in a usable GPS navigation system based on OSM data.  Main road were main roads, and jungle tracks were tracks.

Then along came Facebook with its unlimited resources and steamrollered a project in Thailand with scant regard for contributors ... sure they paid lip service to us, with offers of collaboration, and contact emails ... but in reality, all our comments went unanswered, or simply ignored.

Sure, their imagery identified roads we had not plotted, but along with that came the irrigation ditches, the tracks though rice paddies, driveways to private houses, and in once case, an airport runway !   All went on the map as "residential roads", leaving any GPS system free to route the user on a physical challenge to make it to their destination.

Local users commented, but the geeky humans who were checking the AI, living thousands of miles away, having never visited Thailand, just ignored our comments.  They would soon move onto bigger and better things, while sticking this "success" down on their resume.

A good example for those not involved in mapping, would be if Wikipedia went out and used robots to scour the net for any data relevant to the page title and automatically add it in a haphazard way.  Sooner or later users would distrust what had now become a cluttered site, with information that was not vetted correctly.

The same has happened the Thai map ... nobody trusts it any more.  We can correct one road at the time, but the sheer magnitude of the Facebook inputs mean it will never be fully corrected.

So, my apologies to those who end up driving their new Toyota into a drainage ditch ... and to those rural house owners that now find an HGV coming down their drive... you all have Facebook to thank !

 

  • Like 1
  • Thanks 1

Share this post


Link to post
Share on other sites
6 hours ago, bluesofa said:

Yeah, forget predictive text - that's old hat.

We want new technology for Thailand 4.0 - predictive accident forecasting. Accurate to the nearest ten metres and two minutes.

 

Don't forget, there's data from thousands upon thousands of previous accidents to build a very reliable model.

 

"Don't forget, there's data from thousands upon thousands of previous accidents to build a very reliable model."

 

And every bit of data says the same thing "Brake Failure"

 

  • Haha 2

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

  • Recently Browsing   0 members

    No registered users viewing this page.

×
×
  • Create New...