PUBLIC MARKS with tags data & geolocation

These are images of map generated entirely from GPS logs gathered by various versions of the Geoloqi sample application for iPhone and Android for the past 3.5 years. Once gathered, the data was run through a custom script that projects the GPS logs onto a 2D image plane. There is a little bit of logic to smooth out the lines and remove some (but not all) GPS noise.

Estimating geographic information from an image is an excellent, difficult high-level computer vision problem whose time has come. The emergence of vast amounts of geographically-calibrated image data is a great reason for computer vision to start looking globally — on the scale of the entire planet! In this paper, we propose a simple algorithm for estimating a distribution over geographic locations from a single image using a purely data-driven scene matching approach. For this task, we will leverage a dataset of over 6 million GPS-tagged images from the Internet. We represent the estimated image location as a probability distribution over the Earth's surface. We quantitatively evaluate our approach in several geolocation tasks and demonstrate encouraging performance (up to 30 times better than chance). We show that geolocation estimates can provide the basis for numerous other image understanding tasks such as population density estimation, land cover estimation or urban/rural classification.

If you had a visualization of every place you've been for 200 days, what could you do with it? What could it tell you about yourself and how could others use the data?

Technology allows us to see information in a way we never could before. Atlas of the Habitual is about creating data out of the everyday, the hyper-digitizing of your life.

knowing that the cinema is empty might attract people who wants to have empty rooms. The business case is possible too.

About being ubiquitous, there are two types of things. Accessible data on things, accessible data on people, I love the first one, I'm very worried about the second one.

I like GPS, because it is a (low quality) broadcast location grid system. It doesn't locate you, you locate yourself on a grid.

On the opposite, cellphone towers location systems are tied to an id (mobile phone contracts), it identifies your location. Very bad.

I wish cellphone towers where only creating a grid of geolocation.

Right now, I'm trying to decide if I want to run my own infrastructure for this stuff. From a privacy and creepiness factor it makes the most sense. At least for me. Maybe for anyone else, it's an equal kind of toss-up whether they'd be comfortable handing over their location data to me or to someone like Google.

These new interfaces enable developers to do nearly everything that you can do at http://blockchalk.com. It’s now possible to build client applications, mash-ups, and other tools based on BlockChalk geolocation data and services.

You can read the full API documentation here: BlockChalk API v0.6

So what does this mean? It means that BlockChalk is now more than just a nifty GPS app for your iPhone. It’s an open platform for storing and accessing user-generated content within a geographic context.

What makes the BlockChalk platform unique?

* It’s dead simple. There are no badges, medals, points, unicorns, pirates, or other viral gaming craziness. BlockChalk is about locations and the messages people leave there, that’s it.