Predator Outdoes Kinect At Object Recognition

mikejuk writes "A real breakthough in AI allows a simple video camera and almost any machine to track objects in its view. All you have to do is draw a box around the object you want to track and the software learns what it looks like at different angles and under different lighting conditions as it tracks it. This means no training phase — you show it the object and it tracks it. And it seems to work really well! The really good news is that the software has been released as open source so we can all try it out! This is how AI should work."

Comments

Re:I for one..

[Ruke]

I'm looking forward to looking at the GPL'd source code. There are a lot of ways to do object tracking, and they've all generally got problems, but I was rather impressed with this presentation. It was able to track the moving vehicle while it passed into and out of shadows (non-uniform saturation), as well as track that panda while it turned around (changing its shape), and it was able to distinguish a black-and-white version of the presenter's face (not based on color). It was able to recognize objects that moved off screen, which seems to indicate that it's not just drawing a snake around the moving object. Furthermore, it doesn't seem to need to be specifically programmed to track each object (as we saw the presenter just drag-and-drop a box around his hand/face.)

Nothing new or great

[Anonymous Coward]

As a person who does on a daily to daily basis research on object tracking, and having seen implementations and performances of many trackers (including this one) on real world problems (including gaming), this is nowhere a new approach or an approach which outperforms many other ones published in recent computer vision conferences.

From TFA:
"It is true that it isn't a complete body tracker, but extending it do this shouldn't be difficult."

Going from this to body tracking is a HUGE step, it's not a really easy thing to do. I don't know there is a strange hype around this one which I can't really understand the reason, it's coming up on many websites etc, while as I said not being a great tracker.

Re:Um

[deapbluesea]

it should be no problem to track individual limbs to generate a skeleton of the user

I'm not so sure about that. He is using a tracking algorithm paired to a template matching algorithm. His claim is that, although both methods have high error rates, their errors are mostly orthogonal to each other. In other words, one method works better sometimes, the other method works better sometimes, and combined, they do a pretty good job. In his videos he's left out scenes where there is a large area of near constant intensity. I'm curious how his method deals with this as there aren't enough details to track, nor are there enough features to template match. Also, with arms and legs, if the texture is generally the same between the two (say you are wearing sweatpants and a sweatshirt of the same color), then there really isn't enough information for the tracker to work with in order to distinguish a leg from an arm. Straight arms and straight legs will both match the template, the tracker will likely struggle with the relatively large area of constant intensity.

That's not to detract from Kalal's research - this is really good work - I just want to point out that it very likely suffers from a few achilles heals not mentioned in his video.

Now pair this method with the kinect, and you might see a real improvement.