A dynamic group of entrepreneurs have come up with a novel idea of sharing car space on an auction platform. Be it travel to the subway, super market or on a long trip, “share your car space” is a hep and novel way to get around. The auction platform will accept bids on travel, say you are a driver and you drive to the subway or train station every week days in the morning and drive back in the evenings, you can share your space with a willing neighbor and get paid. You will be benefiting in many ways, your subway or train station will save on parking space problems by not having to provide additional parking spots for single driver driven cars, you will save the economy by contributing to less emissions, and you will save on fuel bills and maintenance by charging for the share! You can make friends too! You contribute to the environment by doing your part to reduce the effects of global warming and with soaring gas prices and car maintenance costs, car share with cabie car is a winning solution. Share your space! Be part of the new generation drive! www.cabiecar.com

Excellent work. Very nice to see someone taking so much interest and pain on such an intresting subject. great work!! Visit pfizer piroxicam webpage devoted to pfizer piroxicam. propranolol inderal webpage devoted to propranolol inderal. too!

The ARQuake project is not at Penn State, but at the University of the South Australia.

See www.tinmith.net

Recently at TACC (Texas Advanced Computing Center) I saw that they have a new tracking system that I was told is a great improvement over current systems. I now wish I had written down what technology it uses. Does anyone know of other systems currently in use?

Also re: ARQUake, I had the chance to play that in the vis lab at penn state once, and I can personally attest that although it does seem like a cool idea, in practice it's just a really great way to get sick.

Finally, I didn't really understand on page3 where they discuss that a constant error term is OK for slow frame rates while a higher-order term is better for faster rates. Why do you need to look further back (including information from previous frames) if the frame rate is higher? It seems like higher frame rate would make consecutive frames less different for the same motion, so how does this help?

Jing, the main tracker unit transmits a magnetic field that essentially goes through all things non-metalic. The actual tracker picks up on the magnetic field and is able to send an orientation back to the main unit based off the physics of the magnetic field. Yes, magnetic trackers are still around (in fact Ascension still sells the Flock of Birds system). Many tracking systems purchased these days are usually purchased either to capture user motion (like for movies) or for simulation (like for military purposes). Magnetic trackers can be used for this *as long as there aren't many metallic sources near by* (it throws off the whole system)! So, many places that use tracking may have to resort to other options (such as optical tracking). However, magnetic tracking is still pretty common.

As for your second question, yes other things can be used as landmarks. In fact, this is what I'm doing in my research and I'll talk about it tomorrow.

Sunny, to answer your question, think about what would happen if you looked at a perfect square box with only one landmark. How would you know what side is which? So basically, the reason why they use multiple landmarks is to help know which side is which. The system could treat multiple landmarks on the same objects as connected but there is really no need to do this. For this particular system, the landmarks behave independently. So, to answer your question, if there are multiple landmarks on the same object, then they are seen as two different landmarks even though they are on the same object.

It is interesting to see that how the two different tracking systems (vision-based and magnetic) could cooperate and compensate to get the better head pose. The landmark tracking results are used to solved for the head pose, and after solution selection and some optimization, the corrected head pose is sent back to compromise with the result from the magnetic head tracker and help the landmark prediction for next frame. We could regard this system as a feedback system, and it will go well if the previous prediction is right, but is there also the chance that the system will go worse and give bad prediction.

Landmarks are defined by different colored bullseye on objects, but I noticed that different faces of the same object have different colored bullseye on them. Does that mean the same logical object is treated as different landmarks depending on which direction you're looking at the object?

Sunny.

This paper certainly is very interesting to read.

How does a magnetic tracker work? Is it still in use today?

Landmarks are very important to registration, but looks like they are all pre-defined. How practical would this be in a real-world situation? Would it be possible to use some other object in the scene as landmarks instead of the two-color concntric circular dots?

A few more things... First, videos related to this paper are here:

http://www.cs.unc.edu/~us/web/quicktime.htm

Also, regarding AR Quake. Unfortunately, it doesn't work very well... Although it looks nice on their webpage, a lot of results have been "hand-waved". I think they did it to gather a lot of attention into their research (such as Slashdot).

My presentation is also about AR, a bit more recent and purely based on computer vision. It's nice to know how AR evolves through years.

BTW, those who love playing Quake may want to visit http://wearables.unisa.edu.au/arquake/ . I found this is an interesting example of AR.

Edited by author 10-06-2003 10:26 PM
Some cool stuff, too bad it focused so much on technical issues. It seems that the computer vision techniques they used were extremely primitive, although the real time constraints of 1996 probably account for much of that. Using the cute artificial landmarks whose real loctation was precisely determined beforehand was annoying to a computer vision person -- but perhaps it's a realistic trick for AR? Also, an interesting thing about the application was that quantifying performance was difficult -- I like the trick of using simulation to test an AR system.

I look forward to learning more about current AR systems!

This paper is a little different than the papers we have done so for, as it is similar to a systems paper. However, it serves as a motivating paper to the vision world because the computer vision portion of the research is vital part of the system. This is certainly one potential application that would put computer vision in everyone's homes. Here's looking forward to the future! ;)

Since I am presenting this paper, I thought I would give a brief introduction. This particular paper had a big impact within the Augmented Reality community as it was one of the first to do Augmented Reality well. Although the technology is a bit dated (1996), many of the ideas from this paper are still relevant today. As a part of my presentation, I will also provide an up to date view of Augmented Reality. There have been some interesting developments since 1996.