Posts Tagged research
Augmenting Aerial Earth Maps With Dynamic Information
Posted by Tom Carpenter in augmented reality, digital singularity on September 11, 2009
The Georgia Instituite of Technology will be presenting at ISMAR09 on “Augmenting Aerial Maps with Dynamic Information from Videos.” They have released a video and a website on their project. Their stated their goals are:
Abstract
We introduce methods for augmenting aerial visualizations of Earth (from tools such as Google Earth or Microsoft Virtual Earth) with dynamic information obtained from videos. Our goal is to make Augmented Earth Maps that visualize the live broadcast of dynamic sceneries within a city. We propose different approaches to analyze videos of pedestrians and cars, under differing conditions and then augment Aerial Earth Maps (AEMs) with live and dynamic information. We also analyze natural phenomenon (clouds) and project information from these to the AEMs to add the visual reality.
I find this paper and the video absolutely fascinating and altogether troubling. As we start bringing live camera views into the datasphere, we open ourselves up to many wonderful possibilities and also to new problems. The technology, as presented in the paper, is a long way from a ubiquitous environment of cameras being translated to the datasphere (to be then analyzed), but it shows we are on that path.
I may be overstating the dangers, because when it comes to collecting data, what can be measured can be improved and improving society is generally a good thing. But as cameras can begin to identify individuals and that can be tracked to social media, we have to make decisions about the ownership of personal data. I don’t mind if this data is used in an aggregate sense, but if my individual tastes and habits are tracked, then I think a line has been crossed.
This is a topic that will need more discussion as the technology improves.
If you want to hear more on the project and you are attending this year’s ISMAR. They will be presenting their paper on Tuesday afternoon between 1:00-1:50pm (subject to change).
Popularity: 17% [?]
Core Tools for Augmented Reality
Posted by Tom Carpenter in augmented reality on May 14, 2009
In this video Simon Wynda (I’m guessing at the spelling) gives a Core Tools for Augmented Reality demo. This demo was featured at the Microsoft Research Cambridge Lab on May 6th.
Simon demonstrates a geospatial AR application that recognizes its location from images and GPS data. Location notes are annotated in the view in one example.
The second part of the video he shows a hide-and-seek game utilizing AR. The view in the camera shows a cascade of bubbles floating by that a child would follow to a treasure chest. Simon demonstrates how even away from the chest, the bubbles float in the correct direction. Not a breakthrough by any means, but I like the direction of their creative thinking to make an interesting application.
This idea could be expanded into an adult hide-and-seek finding clues throughout a metropolitan area leading to a big event. Prospective attendees could answer questions along the way at certain locations related to the event. Would be a great viral marketing campaign.
Popularity: 1% [?]
Warping Augmented Reality
Posted by Tom Carpenter in augmented reality on May 5, 2009
Once again, Rouli at the Augmented Times has found another interesting set of videos. This time displaying a fascinating advance in augmented reality. So far, all AR, markerless or not, has been confined to using a 2D flat space as its jumping off point. The 3D shape can be anywhere based on the coordinate system the 2D shape uses, but they will have to recalculate the plane based on the 2D object location.
The breakthrough shown in these videos is the computer can understand a topographical object and then calculate the virtual object onto that topographical shape.
Slobodan Ilic explains how they use a triangulated mesh to create the 3D shape. By reducing the shape into a series of triangles they can reduce the overall size of the file, therefore making it easier to manipulate and apply AR to it. If you want to see a bunch more 3D mesh tracking you can find it here.
Technical jargon aside, this allows for some pretty cool stuff to be done with AR. Even the example video with the shirt looks amazing. It took until the broken occlusion part for me to figure what was the virtual object in the video.
As Rouli pointed out, the processing power needed is too much for the iPhone, so this breakthrough, while cool, is stuck on the desk computer for a while. I can think of a hundred and one uses if it could be run through the iPhone or using a future-technology like augmented vision, but for now we’ll have to wait for the rest of the technology to catch up.
Popularity: 1% [?]
Sign of the Singularity
Posted by Tom Carpenter in digital singularity on April 3, 2009
Vernor Vinge, the mathematician and author, once predicted the technological singularity which states that computational technology once achieving a certain threshold would accelerate past human intelligence. This possibility sounds like fiction, but it’s a concern serious technologists have voiced.
Recently, a team of researchers in Aberystwyth Univserity in Wales, created a robot that could formulate theories and make scientific theories on its own. The machine made its own independent scientific discovery about baker’s yeast. While we’re decades from declaring our love for our new robot overlords, this type of advance is another step towards the singularity.
Though I think its more likely in a few decades that we would all laugh about how we fretted over the robot apocolypse. We would chuckle because these new thinking machines had innovated cures for cancer, super-efficient renewable energy sources to replace fossil fuels, and a machine that goes “ping!”
I’m not downplaying the supposed danger, because I do think it is a possibility. However, the benefits of a machine that can think for itself in limited venues are immense. One of the interesting side effects of the Internet is the creation of a giant datasphere. Before data was locked away in print, but now it flows freely across the world. As data becomes more fluid, thinking machines that can create scientific discoveries would be extremely useful. Even the iPhone has something to add to the equation as a data collection device. Suddenly, grand problems with fractal-like complexities can be tackled by not-so-simple machines.
Of course, the unscrupulous could use such thinking machines to create a new mathematical models that could game the financial system for massive amounts of personal gain. This is happened in the 80s when computers allowed for complex computations and the field of derivatives was used in new and increasingly destructive ways. So while I do wonder about the threat of the technological singularity and possible robot apocalypse, for the time being, I’m more worried about the good old flesh and blood computers that have been wrecking havoc on our civilization for millenniums.
Popularity: 2% [?]
Subscribe
Recent Comments