Slashdot Mirror
Finding Yourself With Photo Recognition
itchyfish writes "You are lost in a foreign city, you don't speak the language and you are late for your meeting. What do you do? Take out your cellphone, photograph the nearest building and press send.
For a small fee, photo recognition software on a remote server works out precisely where you are, and sends back directions that will get you to your destination.
Seems a little far fetched, but amazingly cool if it really works."
... a GPSr reading and request information about that location, we get this?
Sounds like a solution in search of a problem.
Some problems that I can see with it. What if your in a flat area with no buildings, landmarks, etc? Or even worse, a very rocky, natural area (say something similar to the grand canyon). And even barring those problems, wouldn't GPS just plain be easier? Take the same concept, have the phone grab its GPS location, have you enter the address you want to go, and both pieces of information are sent and the phone gets its route to get you where you want to go (with associated fee). Seems cool, though.
If the photo is taken and the data on the server isn't updated very frequently, couldn't items like cars and other movable objects interfere with the location calculation, as it bases it highly off of the details of the location?
Ideally, the much sought after all in one convergence device (fone/pda/etc.) would have built-in GPS, negating the need for this otherwise functionally sound service.
I wouldn't invest to much into this technology, as I think it'll be obsoleted before it comes to fruition.
-PHiZ
Pretend I said something meaningful or insightful here.
Is this really necessary? Not everything needs to be so darned tech, you know... maybe we should just get a map and use that.
You are lost in a foreign city, you don't speak the language and you are late for your meeting. What do you do? Take out your cellphone, ...
... get it stolen, and get screwed over the phonebill as well.
what kind of meeting is this, that is hold where you do not know the language, and have no clue to get around, did you parachuted to the meeting but missed the building?
what happened to phrasebooks?
man i'm bitter...
ato
There's a technology, that can take a poorly shot digital photo, and then match it to a database of images of every building in the world, come up with a single match, and then let you know where you are?
Does such a database exist? Could it possibly work without bringing up false positives? I mean, I don't have figures, but there are millions of buildings in any large urban area, and within those millions, they all have multiple sides, and then they all look radically different at different times of day. We're talking storage space that seems like it would be incredibly dificult to manage, let alone search efficiently and return good results from a cell-phone camera image.
Count me as a skeptic.
How about using mapquest before you leave?
-This sig has been discontinued after a sudden realization.
Find the nearest native, start talking and gesturing wildly. Point at a map or street sign and say the name of the place you are looking for. They'll figure it out.
Sorry I just don't see this one.
Presumably you first need someone to visit every major city and take photographs of every building... but wait, you need to know the positions that those photographs were taken from, so you need GPS, but if GPS doesn't work because it's sheilded from high buildings...
Obviously a skilled surveyor could work it out, but that transforms this photographing job into a highly skilled position, making it many times more expensive.
If it weren't for that then you could probably pay students 10c a photo.
Here's a few counter points I might have made up:
1. If you're in a large city GPS may no work, but the cell tower density would be so high that you could get an accurate location reading just based on triangulation of a few towers
2. U.S. GPS systems only have 10m accuracy. Once Europe launches their own system, this arbitrary restriction will no longer be in place (10cm accuracies should be possible). Besides, who stores map data more detailed than street level at the moment?
3. Who says GPS doesn't give rotational data? This can be determined magnenometers (sp?) or maybe even by testing the GPS signal polarity?
As another point, who is going to take the tens of thousands of pictures of the cities to begin with? What happens when similar buildings start causing match colisions in thier databases?
You are lost in a foreign city, you don't speak the language and you are late for your meeting. What do you do?
You start thinking about what the hell is this that is so important that you go to a foreign country to have a meeting where people don't understand your language and you bet all your chances on the assumption that your cellphone will find the carrier that will allow you data transfer without a subscription plan. If the meeting is so important in the foreign land, I would think that you would do little more homework than to just depend on a cameraphone!!
Imagine how difficult it would be to capture details like that in a major city such as NYC? I don't really need directions to find my way around Cambridge city center as you could almost throw a rock from the center and hit just about every building around, but London, Washington, Houston etc... are another story and the data required from their approach would require massive computational infrastructure.
And I fear that there won't be enough "lost tourists" to make this a paying proposition.
But how much would it be worth to professional historians -- or to Hollywood, or just to you personally -- to be able to "walk" through a virtual representation of New York circa 1890?
Or London in Holbein's time?
This is one of those projects -- much like something called ARPANET, which had to rely on government handouts but later made some guy named Steve Case a fortune -- that will never fund itself but will be of literally incalculable value to posterity.
Let's be realistic -- physics and fanaticism not being mutually incompatible, eventually "freedom fighters" -- whether named Atta, McVeigh, or Patrick Magee -- will make bee-lines for our biggest cities, carrying suitcase filled with two precisely machined hemispheres of plutonium. And everything but the maps of those cities will be lost.
Hopefully the Cambridge researchers will by then have completed their -- apparently -- quixotic project, and we will at least have, in redundant storage, a rather precise picture of what will be lost to radioactive ruin, a snapshot of urban life in the twenty-first century.
Opinions on the Twiddler2 hand-held keyboard?
I was ranting too much to say it..
This is cool technology, and research into this kind of thing is cool. But it's just not commercial IN THIS FORM.
The best application i can think of is for publishers to be able to find a crappy image using google and then submit it to corbis or any other pro image library and ask for a high quality shot of the same scene... but i'm not that inventive.
The viability of this has got to be pretty poor:
1) The database would have to be huge -- Not every meeting or event that I attend takes place in the city center.
2) Along the same lines, they need to store every face of these buildings.
3) The image processing better be really good at color correction and noise filtering (weather, blurry photos)
4) Wouldn't people just go buy a map?
5) Wouldn't distortions introduced from a cell-phone lens make the system less accurate?
- rabs
... for which we do not yet have an adequate probelm
Mole? 4? Cars?
Quite insightful, jea6. The practical application for this technology that the article was predicated upon are silly, and you proved it elegantly: all urban areas have street signs and text recognition is loads easier that the sort of computer vision proof-of-concept being described.
That last bit is what the article is really reporting on--research into intelligent computer vision. The fact that this research is being applied to giving walking directions to stupid humans has far more to do with securing funding than anything else. In other words, if you see people snapping digital photos of office buildings in the near future, you can continue to report them to the Office of Homeland Security.
My other
To me, it would appear that an easier solution might be to use GIS data in combination with the cell phone signal and comparisons of rough morphological features of buildings.
For most people even photos aren't necessary. Using the data from nearest cells a mobile could be pinpointed within 100 m accuracy (in urban terrain, it degrades down do about 1000 m in rural terrain). It's enough if you are sent a map with the neighbourhood - the biggest problem then is the size of your mobile's screen.
Such services (sending a map of the neighbourhood, with interesting points, like ATMs, marked) already exist in Poland (Europe). I find them quite helpful.
homepage: www.tls.pl
signature: not found
CCTV cameras all over the city capture images for face recognition, if you get lost...take your own photo and send it. The server compares the image to those in the face recognition database, and returns the where the most recent match was taken.
Ha!! I tricked you, it isn't a better way at all!!
"the diffrences in the lens curveture ought to give results that don't reflect the true geometry of a building. So it'd be interesting to find out how, if they solved this problem."
This is one of those enigma style puzzles: you can solve because you know there is a solution. You know that the image is of a building and that the image contains long straight edges. Edge detection would pull out several long curves instead. The problem is reduced to finding the lens function to apply that produces the most long straight lines.
The work Steve Mann did on photogrammetry (search for "video orbits", I think the project is on sourceforge now) included lens characterization functions for exactly the reasons you describe (he was stitching images together). Only a couple of parameters were required; in the video orbits case you just guessed them, but then Mann didn't have the advantage of knowing there were long straight edges in the image. You just need to fit these parameters to maximize the straight edges in the image.
Mann's work also covered 'dechirping' transforms that remove perspective effects.
"You are lost in a foreign city, you don't speak the language and you are late for your meeting. What do you do? "
You go into the nearest hotel and ask the nice English-speaking person behind the reception desk.
Even on Mars the hotel receptionists speak perfectly-accented English.
erroneous: look me up in a dictionary