How to get started with image processing and photogrammetry?

Question

Hi every body:

I am sorry about the Title for this question, but really I don't know how to name it. There is something that I have seen sometimes, and I ask myself how to do that kind of software. It's about the PitchTrax that MLB uses in its TV-games. I think that is did it using cameras or something like that... I would like to read (or to learn) how to do little applications using this kind of technology, but I don't know anything about that, really I don't know where "to start" studying for this... Do you know something about this??

I am sorry about my English.

Answer 1

I don't know pitch trax specifically (try google or their site)

But the general field of object tracking and image processing then openCV is probabyl a good place to start (as a programmer)

There is a good book at http://www.amazon.com/Learning-OpenCV-Computer-Vision-Library/dp/0596516134/ref=sr_1_1?ie=UTF8&s=books&qid=1262807256&sr=8-1

Answer 2

There's a bit of detail about how the technology works in this article in the NY Times.

It's not a lot, but it may help you get started with where to look. It mentions the company that wrote the PitchTrax software, and a bit about how they use stereoscopic camera technology to figure things out. There also seems to be some related info in this blog.

You may also want to buy (rather than develop) stereoscopic imaging - it's not a simple field.

Answer 3

Check out this blog post on Umpire Information System (Like PitchTrax): http://www.questec.com/q2001/prod_uis.htm

Answer 4

Looks like it uses cameras to track the ball as it is pitched. From here:

The UIS uses QuesTec's proprietary measurement technology. Quite different than "video insertion" technology that simply adds graphics to the broadcast video, QuesTec technology actually measures information about interesting events during the game that would not be available any other way. This technology is so innovative it appeared in a Scientific American article in September of 2000. The ball tracking component uses cameras mounted in the stands off the first and third base lines to follow the ball as it leaves the pitcher's hand until it crosses the plate. Along the way, multiple track points are measured to precisely locate the ball in space and time. This information is then used to measure the speed, placement, and curvature of the pitch along its entire path. The entire process is fully automatic including detection of the start of the pitch, tracking of the ball, location computations, and identification of non-baseball objects such as birds or wind swept debris moving through the field of view. No changes are made to the ball, the field of play, or any other aspect of the game, to work with QuesTec technology. The tracking technology was originally developed for the US military and the company has adapted it to sports applications.

So if you are looking to learn something about this, image processing would be a good place to start.

Answer 5

I have no idea.

But I can make stuff up that sounds good.

I'm guessing they're using several cameras (at least two, perhaps three) and image processing to "follow the ball".

Once they can identify the ball (not super difficult if you think about it), then each camera can know "it's space" in a 3D realm. Multiple cameras will fix the ball in space, and from that they can calculate the track.

In 3D Graphics, there's a concept called "Match Move" that is used to place 3D models in the space observed by cameras. You need to know the camera angles, etc. plus the focal lengths of the lenses to figure that out.

I imagine the underlying tech is related. One extracting objects from space, the other putting them in.

Answer 6

In general, you're looking for information about Augmented Reality- the wikipedia article isn't a bad place to start. Processing has some third-party OpenCV bindings, which could make it easy to play around with the technique.