Playing with MSERs in trying to implement an algorithm for feature-based object tracking. The algorithm first finds MSERs, warps them to circles, describes them with a SIFT descriptor, and then indexes keyframes of sift vectors by using vocabulary trees. Of course that’s a ridiculously simplified explanation, but look at what it’s capable of!!!:
This is big. In less than a week, the Kinect has been hacked and ported for windows, osx, linux, java and processing, max/msp (almost), and flash…
Much much more to come: 
… Continue reading...
Please rate, share, and comment!
Memory @ AVAF 2010 from pkmital on Vimeo.
‘Memory’ is an augmented installation of a neural network by Parag K Mital & Agelos Papadakis.
hand blown glass, galvanized metal chain, projection, cameras; 1.5m x 2.5m x 3m
Ghostly images of faces appear as recorded movie clips within neural-shaped hand-blown glass pieces. As one begins to look at the neurons, they notice the faces as their own, trapped as disparate memories of a neural network.
Filmed and installed for the Athens Video Art Festival in May 2010 in Technopolis, Athens, Greece. The venue is a disused gas factory converted art space.
Also seen at Kinetica Art Fair, Ambika P3, London, UK, 2010; Passing Through Exhibition, James Taylor Gallery, London, UK, 2009; Interact, Lauriston Castle, Edinburgh, UK, 2009.
If you are one of the +500 million users of facebook, and you know your user id, try plugging it in here: http://zesty.ca/facebook/
This uses the Facebook Graph API to get information about Facebook users in a very accessible manner. Of course, it is only your “public” information that is accessible without authorization. But once you “allow” an application to access your information, you’re allowing access to EVERYTHING.
Generally, these items are publicly known:
{
"id": "0123456789",
"name": "Parag K Mital",
"first_name": "Parag",
"middle_name": "K",
"last_name": "Mital",
"locale": "en_US"
}
and also your Profile picture.
Check out a montage of the first 3600 Facebook user’s profile pictures, obtained just by using the public url: http://graph.facebook.com/USER_ID/picture
And an image of the average of all 3600 profile images:
Stuck behind a firewall restricting your access to the Internet? You may have already tried HotSpot Shield or various other anonymous proxies with some luck. But what happens when your Internet Service Provider (ISP) finds the server’s address and then blocks it? You’ll have to wait for HotSpot Sheild to change their address or find a new anonymous proxy…
Here’s a better solution: Tor.
Tor is like the underground railroad of the internet. There are an incredible amount of reasons why YOU should be using Tor. Even if you have no problems accessing the social networks, you are being logged everywhere you go: 216.73.216.224.
The way Tor deals with anonymity is by creating a vast network of distributed anonymous relays. Instead of taking your information straight from source to destination, it will instead go through the maze that is Tor, where each relay is another Tor user. This makes traffic analysis very difficult. As well, if you are in Iran or China or someone else that has decided that certain websites are bad for you, there is no one server to block. Every user that decides to be a relay is a server.
Here’s how to get … Continue reading...
This will be my second year supervising the Digital Media Studio Project at the University of Edinburgh. The course is a mix of over 60 Digital Composition, Sound Design, Digital Design in Media, and Acoustic and Music Technology MSc students. 10-15 supervisors pitch a project proposal and the students decide which ones they’d like to participate in. This year, I proposed Augmented Sculpture, and 3 students signed up of which 2 are Sound Designer and 1 is a Digital Designer. So far, they have managed to communicate tracking data via a reactivision framework and combine life-sized sculpture to interact with a sonic environment built in Max/MSP.
Chandan, Helen and Ev playing with a ReacTIVision controlled Max/MSP patch developed for the Digital Media Studio Project at Edinburgh University. This is the very first ever test run of the system, and it worked!
Follow more developments on their blog.… Continue reading...
TINT’s online exhibition using Add-art has gone live!
Here is what the website has to say about our piece:
… Continue reading...Parag K Mital and Agelos Papadakis – Memory
Parag K Mital and Agelos Papadakis have worked together on a number of occasions, their piece Memory, being the most celebrated. In this piece, they explore augmented sculpture in an installation environment, allowing the audience to become an integral part of the sculpture. Creating great tension in the viewer, they have literally chained together brilliant works of glass resembling neurons to create entangling neural networks of 25 face-sized glass pieces together in a 3×3×5 meter industrial warehouse space. Within two of the glass neurons are hidden cameras tracking audience member’s faces and recording them to a computer hidden above. Using a projector and projection mapping onto each neuron, a recorded clip of one of its audience members plays as a neural network of different faces occasionally firing with a mesmerizing display. Through the disarrayed glass, ones face morphs ever so slightly, though those familiar with that face are able to recognize it still. However, the majority of faces may seem unknown to the audience members and serve merely as a memory of the
As part of the Kinetica Art Fair 2010, Memory is required to fill in a risk assessment form. This entails listing out all the possibly tragic events that can occur, how many people could potentially die, and a design of the installation as seen from top-down and the side. Having only seen pictures of the space before, deciding on the design was a bit tricky (let alone figuring out how many people would die). The piece itself is not very modular and has to make use of the space (take a look at what I mean). It is basically a web that latches onto whatever it can find in the space. As such, we really needed a nice model of the space in order to model the installation.
I went through an attempt of photoshopping the few pictures with some ridiculous looking lines. It didn’t seem to capture the space. Next attempt was with Illustrator. Hmm. Nope not much further. Maybe just draw the thing? Nope. I couldn’t seem to get the scale right or even think about how to lay out the design in a space I wasn’t really sure about. I just couldn’t visualize the … Continue reading...
If you aren’t using Adblock Plus, you should be. If you are, you should be using Add-art. This clever extension will replace all online advertisements with pictures of art.
Now for the real news, TINTarts has selected a number of pieces to be part of an online add-art exhibition starting January 16th and Memory will be one of them. Get your add-art now and leave a comment if you happen to see Memory while browsing.… Continue reading...
Though AR has been around for awhile (ACM Special Issue in 1993 though dedicated conferences beginning in 1997), it seems to be at a point where it is finally hitting the mainstream. A number of development libraries have been around for awhile (ARToolkit, FlARToolkit, ARTAG, D’Fusion @Home, Mixed Reality Toolkit (MRT), Unifeye Viewer Xtra, Mirage Builder, and Studierstube Tracker). Though with the advent of the iPhone App Market and the Google Android Market Place, we are finally starting to see some practical applications that seem to be a head start towards a meta-tagged world. I’ll continually add more here and try to group them as I see fit. But the basic premise of these applications allows users to create a digital layer over the physical one. I think the SixthSense video demo shows this concept brilliantly (though most of the demo is more concept than reality).
Using the camera to detect features in a scene:
(1) Google Goggles
(2) SixthSense (the demo is more concept than reality)
(3) SREngine
‘
Augmented Reality Browsers (see a comparison of a few here):
(1) Layar
(2) WWSignpost
(3) Wikitude (though this seems … Continue reading...
No more void *‘s apparently. And they’ve got constructors and destructors.
Check out the documentation here: http://opencv.willowgarage.com/documentation/cpp/index.html
Notably, the memory management seems to be much nicer as destructors are called when there are no more references to the object.
As well, quickly accessing data row or plane major seems to be much easier now:
e.g. plane access:
// split the image into separate color planes
vector
split(img_yuv, planes);
// access with iterators:
MatIterator_
it_end = planes[0].end
As well, they have implemented STL-like class traits for easily declaring matrices with the normal c++ primitives without having to remember CV_64F etc…
e.g.:
Mat A(30, 40, DataType
Mat B = Mat_
There is a whole lot more introduced including a revamped interface system, many more machine learning and computer vision algorithms, OMP integration, and probably a lot more. I’ll be playing with it to see what else is going on. Hopefully the openframeworks community will pick up on it as well and integrate it into their next major release. I know I’ll be doing so for my projects.… Continue reading...
