Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 


Forgot your password?
Close
typodupeerror
×
Cellphones Communications Handhelds

Researchers Track Cell Phones Indoors By Listening In 35

Posted by timothy from the audio-daily-double dept.
starzia writes "Researchers at Northwestern University and the University of Michigan have developed a technique which aims to extend the reach of mobile phone location tracking. Their free iPhone app, Batphone, extracts a location 'fingerprint' from a short recording of ambient sound. This software-only approach allows the device to determine its location with high accuracy using its built-in microphone. Unlike prior indoor tracking techniques, Batphone does not rely on the presence of Wi-Fi access points to serve as landmarks, although these can be used to assist the system when available. They also posted a web game which allows you to test your own ability to recognize rooms by listening. Technical details are in a paper which was presented at the MobiSys conference on Thursday. This is from the same people who brought you laptop sonar."
This discussion has been archived. No new comments can be posted.

Researchers Track Cell Phones Indoors By Listening In More

Researchers Track Cell Phones Indoors By Listening In

Comments Filter:

  • NOTHING TO FEAR BIUT !! (Score:1)

    by Anonymous Coward

    the man listening in !! Skype and Microsoft are conspirators in this, have no doubt !!

  • I don't see the utility. "Gee, I can't tell if I'm in my kitchen or my living room. If only there was an app for this!"

    • Re: (Score:1)

      by Anonymous Coward

      How about "Gee, I can't tell where my teenage daughter and her boyfriend are. Kitchen or Bedroom?

      Get the point now? :o)

      • How is stalking underage girls any better than stalking people in general?

        • The word used was "teenage", not "underage".

          You're revealing more about your interests than you maybe want to admit.

      • She's in the bedroom, her phone is in the kitchen. Unless the phone has a vibrate mode, in which case she and the phone are in the bedroom, and the boyfriend is in the kitchen...

    • Or maybe "gee, I'm a boss that wants to know where their employees are, lets use something like this" :)

      On a more serious note, this will require training and labeling of the system, wifi/rfid based models just work everywhere (with varying degrees of success)

      • On a more serious note, this will require training and labeling of the system

        Which, of course, means that the tinfoil hat wearers can stop thinking that this will be useful as some sort of government tracking tool.

        • Which, of course, means that the tinfoil hat wearers can stop thinking that this will be useful as some sort of government tracking tool.

          I don't think tinfoil hats are going to be very useful here. Now, a shag carpet hat or a loaded rubber hat might change the resonant frequency of the room enough to be useful.

      • Maybe I missed something in TFA, but I don't remember it mentioning any ability to track someone else's phone, it just tells me the current location of my phone. Even if it does have that capability, it would be simple enough to spoof... just leave the phone in the kitchen (or at your workstation, etc.) while you scamper off to do something naughty.

        It might be more useful if it had a shared, central database of sound profiles, which was coupled with a blueprint/map of each building. That might help if you w

        • Well, with all the homework done, it could easily be adapted to spy on your employees, especially if they are using a company phone.

          You could leave your company phone somewhere, true, but if someone happens to call you... :)

          The shared database is a bit more tricky. I'd imagine that using the phone in a purse or in your pant's pocket would give out different signals, so each case would have to be trained individually. Only after a few months of training with enough people recording "soundprints" would you be

    • Re: (Score:2)

      by garcia ( 6573 )

      I'm in my kitchen with my phone, I'd like it to tell the server to turn the lights on and then off when I leave.

      • Re: (Score:1)

        by gl4ss ( 559668 )
        buy a motion sensor. this technique wouldn't work from your pocket anyways and do you keep your phone in your pocket at home? but what's more important is that listening to the microphone with sw keeps the cpu on and stressed.

      • Re: (Score:1)

        by ddusza ( 775603 )
        I'm in the bathroom...wait for the sound of the flush before turning off the lights this time!

      • Ok, that at least sounds like a useful application. Not sure if "sound profiling" would be my first choice for implementing it, but at least it's useful.

  • So, if I play a recording of white noise or different ambient noises, how well will this work?
    Even better, a recording of a muezzin's call to prayer.

  • Where did the name come from? (Score:3)

    by blindseer ( 891256 ) <blindseer.earthlink@net> on Saturday July 02, 2011 @10:35AM (#36641320)

    Is the name in reference to a bat's echolocation ability or is it a reference to the "Dark Knight" movie where such a software system was used by Batman to find the bad guys?

    Only the Shadow knows.

    • Technically, the Dark Knight software was reference to a bat's echolocation ability, so... ;) Either way, it's pretty cool... until the government gets a warrentless wiretap and uses it to watch us in our homes. If that ever happens, I can guarantee that Morgan Freeman will be pissed... again...

  • and depending on what I was doing at the time, I would apparently have one or more of the following in my house

    a) a concert hall capable of holding an entire orchestra
    b) a datacenter with a crazy amount of fan noise (phone tends to get left on my desk, right next to the computer)
    c) a sawmill (I'm told I snore, loudly)

    I guess I don't see this being particularly useful.

  • They could probably do even better by getting the phone to emit a loud clapping sound, approximating a dirac delta so they could measure the impulse response of the room. The fourier transform of that should have some nice distinctive shapes. On the other hand, that wouldn't be nearly as unobtrusive, and most smart phones have crappy speakers, so you wouldn't get much response.

  • They're not alone in this effort (Score:4, Informative)

    by r_jensen11 ( 598210 ) on Saturday July 02, 2011 @12:38PM (#36642028)

    Nokia has been working on this since at least 2009, just search for their Kamppi trial [nokia.com]. I know that it's fashionable to knock Nokia on many things, but they do (or is it did?) work on some very fore-front things.

    Somebody else created a similar application for his Nokia phones:
    http://www.techalps.com/nokia/any-minnesota-readers-please-give-this-mall-of-america-app-a-try.html [techalps.com]

Slashdot Top Deals

E = MC ** 2 +- 3db

Close