Slashdot Mirror
Computer Scientists Scour Your Holiday Photos
Barence writes "Hundreds of thousands of images on Flickr are being used to teach a program to determine the geographic location of an image, simply by looking at it. The program attempts to mimic the way that humans can deduce the location of an image by searching for visual clues, such as similarities to pictures or locations they have seen previously. In its current state it can guess the location of a photo to within 200km, 16% of the time — extremely accurate given the complexity of the problem."
16% percent of the time it works every time.
The paper referenced in the article has an interesting density map of where their 20 million source photos were taken (ok, so they only ended up using 200 or so of these). It says it uses a logarithmic scale, and seems to imply that the vast majority of photos available to them on Flickr were taken in one of only a handful of locations:
Ok so there are a couple more than this, and my geography is appalling, but these seem to be the only areas that are are coloured red.
Dude, that's as accurate as my girlfriends map navigation. *sigh*
War is the statesman's game, the priest's delight, the lawyer's jest, the hired assassin's trade.- Shelley
I'll guess...New York City, without even looking at the pictures that should get me in that ballpark.
Have you read my blog lately?
... is a program that will remember the names of the people in the photos.
Intron: the portion of DNA which expresses nothing useful.
Show it a picture of the andromeda galaxy and throw its statistics way off.
If you can read this, I forgot to post anonymously.
of the time...
(Not counting those rich bastards who can afford taking a holiday on the ISS).
Where's Goatse?
Some drink at the fountain of knowledge. Others just gargle.
Well, there's spam egg sausage and spam, that's not got much spam in it.
metacafe link here and TED link here.
A-Bomb
Scientists surprised to discover it is possible for a machine to loose will to live.
It's a for loop that spits out "Your mom's basement".
Look at this set of pictures:
http://htmlhelp.com/~liam/Hawaii/Kauai/WaimeaCanyon/
Would you know simply by looking at the photos without the sign that this was not say the grand canyon? The whole correct to 200 km aspect is troublesome when the state of the art in computer vision cannot yet even answer that this is a picture of a canyon.
OsamaBinLaden2001 has deleted his account
200km, 16% of the time? I guess that sounds sorta neat... except that 84% of the time, it's off by more than 200km. Now, we know that the earth's circumference is 40000km, and it follows that nobody can ever be more than 20000km from any location on Earth.
So 16% of the time, it's accurate to within one percent of the TOTAL RANGE OF ERROR. The other 84% of the time, you're on your own. I wonder if I could manage that kind of accuracy just by sampling colors, classifying them by terrain, and then just picking a likely spot at random.
Yahoo! Pipes are awesome. How awesome? http://pipes.yahoo.com/jesdynf/slashdot
From the looks of the test selecting London all the time would have a
1/6 chance = 16.67% chance.
They need better double blind testing and a more diverse set of geographical locations.
Yes, I meant through the Earth distance and yes I did manage to use the radius.
That will teach me to post before drinking my coffee...
I propose we all take pictures with blue screen in them (not the whole background, just "enough") and then write a script to randomly replace the blue screen with alternative locations every time the picture loads.
Re-check your math that is wrong. .08%
Should be
The problem with geo-tagged flickr photos is that in many places the detail on the maps and aerial shots provided isn't defined enough to allow an accurate placement.
The even bigger issue is that, although some cameras now have GPS, the majority of geo-tagged shots are placed manually by humans who often get it wrong or deliberately place their photos onto a more popular location just to increase their traffic.
I'd like to present this with Moon landing pictures to see where the moon landing was staged! (hahaha... love it)
The dice analogy is right-on.
The problem is he just doesn't seem to realize that the chances of throwing doubles are 16.66%.
paintball
Reminds me of the experiment done in a Dutch military lab a couple of years ago. They trained a neural network to recognize whether a photograph taken out on a country road had a military vehicle in it or not.
The system recognized the photos from the training set perfectly, but did no better than random on images fed to it that were taken at different times.
Turns out all the training shots with a military vehicle in it had been taken on a sunny day, and the control shots without one had been taken when it was overcast. The system had been trained to recognize a different thing from what they intended!
There's an upcoming paper coming from MIT on this topic, Recognition of Natural Scenes from Global Properties: Seeing the Forest Without Representing the Trees that proves this isn't as hard as you might think.
To sum up this massive paper in a very small (and likely highly imprecise) nutshell, building models up from basic objects (the traditional method) is only one way to approach this. Using this method, you are correct; it's impossible to understand what a canyon is. Using the new global properties methods in this upcoming paper, you can gather basic elements that could easily help in assigning location properties, understanding that something pictured is a desert or forest, and theoretically using that data to help determine which desert or forest (this latter portion is beyond the scope of the paper, but great fodder for a future paper that builds upon these fundamentals).
While the method currently requires a high level of labeling in its images, it is hoped that this labeling becomes unnecessary on larger data sets.
Use my userscript to add story images to Slashdot. There's no going back.
For the researchers, it probably helps. They chose pics that had either GPS or location information -- so they could manually verify where the photos originated.
If they started out with a bunch of pics they didn't have any location information about
Cheers
Lost at C:>. Found at C.
Google should get behind this. I think their Picasa would benefit from it.
Generate some autotags.
What would be nice also is if they had a feature where if you labeled someone in a picture, if you uploaded another picture with that person in the picture, the program would prompt to auto tag.
I've been going through old family photos and it would save so much time if the programs I am using autolabeled based off details in the picture.
"Only one thing, is impossible for god: to find any sense in any copyright law on the planet." Mark Twain