QuickTopic free message boards logo
Skip to Messages


Background Layer Model for Object Tracking through Occlusion

^     All messages            7-22 of 22  1-6 >>
discount glasses
10:20 AM ET (US)
 In some cases, when buy glasses online without enough tips would offset the convenience granted by this source.

Why buy eyeglasses online

There are different ways to buy cheap eyeglasses online. But for those with little knowledge of online mens glasses store, the main tool is search engine like Google.com or Yahoo.com. It is worth mentioning that different eyewear products require customers to input different key words.
Spam deleted by QuickTopic 10-13-2011 02:03 AM
09:30 AM ET (US)
Supra Shoes on hot sale now,we carry a large inventory from Supra Footwear, Including Supra Shoes,Supra Skytop And Supra Avenger,Supra Bandit,Supra Bullet.
07:09 PM ET (US)
buy glasses
cheap glasses
03:45 AM ET (US)
  Messages 17-15 deleted by author between 07-25-2008 02:06 AM and 06-15-2010 02:01 AM
03:40 AM ET (US)
Deleted by topic administrator 05-16-2008 08:08 AM
04:52 PM ET (US)
Looking for information and found it at this great discussion. There's also some on coreg shortage webpage devoted to coreg shortage. metformin and pregnancy webpage devoted to metformin and pregnancy.
Shinko Cheng
07:16 PM ET (US)
Regarding Neil's question 2 about why the background shape layers sum to 1, lumping the background together into one pdf is a functional simplification. Doing so allows the front elements of the "background" to be considered the same class with a common motion as predicted by the motion model, so the algorithm will not need to assign the predicted "background" motion to each occluding "background" layer. One of the primary assumptions is that, that the "background" has a common motion model. I can imagine that we model the layer visibility probability for all the layers just as was done for each foreground layer, and then assume that every other layer is the background layer or some combination of layers be assigned the background, but that would mean an additional step is required to decide whether or not each layer contain the common "background" motion and classify each as such.

I like the idea of layers for segmentation. Specifically, I like the idea of using a deformable appearance model to distinguish between multiple objects in images. I can imagine that there would be a tradeoff between finding a model to describe appearance deformations to keep objects a single layer and allowing objects to be divided into different layers based on objects lacking fit with that particular apperance model.
Edited 11-06-2003 07:23 PM
Mike McCracken
12:33 PM ET (US)
I was curious about their use of 2d motion models. They say that background motion is described with a 2d affine model, and foreground layers undergo 2d rigid motion. This sounds like there would be some types of motion that would confuse the algorithm, including some camera motions - am I right, or is 2d enough? I just wasn't sure if they made that choice because it's enough or because it was some kind of tradeoff...
Neil Alldrin
04:31 AM ET (US)
A few questions.

1) They refer a couple times to the "direct method"; what is the direct method?

2) Why do they require the the shape maps for background layers to sum to 1? It seems like they could have removed this restriction with no harm done.

3) How well could layering methods be adopted to non-stationary cameras, where parallax would create non-uniform motion among all the background layers?

These questions are probably pretty stupid as I didn't read the paper as closely as I would have liked (starting before midnight would help :)).
Meifang Huang
02:23 AM ET (US)
The effect of shadows in Figure 4 is a very interesting problem. Normally we will consider the shadows as background layers,but when the object is moving under these shadows, the shadow would not be in the back of the object, instead, it will become a occluding background layer before the moving object and not completely occlud it. In this situation, the background layer model did help to solve this problem, because it can dynamically change the layer order, and assign a background layer along with a foreground layer to this semi-occluded object.
Meifang Huang
02:00 AM ET (US)
This paper is based on the authors' previous work of dynamic layer model, which extends the estimation of layer model to incremental estimation formulation. The key idea of this paper is that they use multiple background and foreground layers to segment the scene for tracking purpose. The multiple background layers would help to solve the complex background occluding problems and also do well for the object tracking.
01:48 AM ET (US)
Diem brought up the similarity of this work to Flexible Sprites and I'd like to expand on this.

Both papers use the graphical models framework and both setup the problem relatively similarly. I think the essential difference between the two works can be summarized as follows. Jojic & Frey focus their efforts on powerful graphical model techniques to solve the problem in a 'brute force' method -- one that incorporates as little additional information about the problem and domain. Zhou and Tao explicitly incorporate knowledge of the domain and use graphical models only as a framework, designing an algorithm adapted to the domain.

As a specific example, consider that Jojic & Frey don’t even have a motion model – that is you could reorder all the frames of a video and their technique still works. On the one hand this means that you don’t need a motion model to do tracking (at least on simple cases) – so possibly on very deviant motion a motionless model would do better. On the other hand that information is available and easy to incorporate – so doing so, as Zhou and Tao did, makes their technique more robust in typical tracking problems.

I think Zhou and Tao got it right. The paper by Jojic & Frey is more interesting from a graphical models standpoint, but it kind of misses the point – rather then throw extremely powerful graphical models machinery at the problem why not analyze the domain more carefully? Anyway, my guess is that the work by Zhou and Tao is much more robust.
^     All messages            7-22 of 22  1-6 >>

Print | RSS Views: 3060 (Unique: 1582 ) / Subscribers: 0 | What's this?