Re: CMUCam Next Year?
 

[quote=russell]Coding the CMU cam isn't actually all that tough. Its coding the CMU cam on a FIRST Robot Controller, and having it deal with all the chaos (and lighting conditions) on a FIRST field thats tough./QUOTE]

I for one am hoping to see a repeat of the CMU Cam in 2006. It is a shame that it was so wildly underutilized last year, since it does so much - much more than a camera, at least. This is an opportunity for some really powerful programming, and not only for autonomous. And, lighting conditions are not as critical as you might believe.

There's a great series of five articles on how to do robot camera vision in the July through November issues of SERVO magazine, explaining most of the significant details. Due to copyright issues, I can't provide copies of the articles, sorry.

Don

Re: CMUCam Next Year?
 

Mike, thats a very good analysis. I also don't want it for that reason. However, I would like to have under different game conditions, say searching for one, undeniable color, say a big, white baton. Simply, the camera would be used only for the purpose of lining something up, not the control of an entire robot across rather large distances. Something the variations in lighting would not affect as much. Whatever the most robust color is, FIRST needs us to look for that, and that only.

Re: CMUCam Next Year?
 

Since I've been designing my robot for the Trinity Fire Fighting Robot Competition, I've been addicted to Infrared stuff. I really think that a thermopile array such as the TPA81 may provide the power of the CMUCam with the flexibility of working in the real world.

Re: CMUCam Next Year?
 

That would create a very dynamic game, much like the real world. Heating the game objects ( pretty simple actually, a big hair dryer blowing though pipes the batons are set into) would allow you to easily lock onto them, and pick them up. Then, if they were dropped, they would cool down and become indistinguishable to others, another challenge. And robots could warm them to a specific temp. to mark them too, though that wouldn't be too useful.

Re: CMUCam Next Year?
 

Shh! Don't go around telling people that we're using batons next year!

;)

Re: CMUCam Next Year?
 

Ooops.....um, I meant that by heating the inflatable Billfreds in a PVC tube...

Re: CMUCam Next Year?
 

From what I have gathered (our team gave up on the CMUcam at kickoff) the CMUcam was very easy to damage, so if it does come back FIRST better make it more robust. I personally like the IR sensor idea, but it might be a bit unfair, since they'd work better in a enviroment with a bigger difference, so they'd work better at Canadian regionals than, say, Texas. It would be funny, albeit dangerous, if the IR sensors are too sensitive and pick up a FP or judge's computer/projector as a scoring object and procedes to attempt to "score" with it.

Re: CMUCam Next Year?
 

That is a valid concern, as referees are heat emmiting objects, so the game object would have to be heated to a high heat, so 110 degrees, or cooled, like 40 degrees. Probably cooling would be better. In this way you would start eliminating the margin for error. But, teams still wore green with the CMUcam this year. Moe still has all its members, from what I know...:D

Re: CMUCam Next Year?
 

Lol thats cause no one actually used the camera. I mean not litterally no one, but probably no one enough that it wasnt an issue.

Re: CMUCam Next Year?
 

I havent entirely worked out kinks involved with depth perseption but i would get the cameras to focus on the same object(dunno how yet) and then use the directions they are pointing to determine how far away the baton i mean object is

Re: CMUCam Next Year?
 

The reason for using two cameras is so you can triangulate and determine the distance to an object, right? Think about this: You can use two cameras, or just one camera from two positions.
For example: Mount the camera on a horizontal arm a foot long, then quickly move the camera from one end to the other - you keep the same object in view, but it 'moves' in the frame a bit. measure that and you can calculate distance.
OK, more brain food: Does it have to move horizontally? How about vertically? Or, what if the camera is fixed and the robot moves???
Finally, you can do it with one camera and without moving. If you know the size of the object, it's just a matter of 'measuring' it. If you don't know the size, put the camera up high and measure the down angle to center the object in the frame. Using simple trigonometry you can calculate the distance to the object.

There, that should get you started. Please let us know how it turns out.

Don

Re: CMUCam Next Year?
 

Lack of focus might change the size of the color blob, but it won't change the color, which is what the camera is tracking.


If they both start searching from the same angle, they'll both likely find the same object. You can also do some error checking to verify that they're both at the same tilt angle, size of the blob is roughly equal, pan angles make sense, etc.

-Kevin

Re: CMUCam Next Year?
 

For using trig to find where an objct is i wrote an autonomous that does this but it only works correctly when the object is on the ground, the point of 2 cameras i so that i can tell how far away it is in any direction including up and down

Re: CMUCam Next Year?
 

so basically if we had higher powered cameras this year that actually focused on what they were supposed to, then it would be possible to do the trig thing(of course higher powered processor would be needed for higher powered cam).
doubt it would be very accurate with the two cams. Sometimes even the human brain fails in this. Better would be to know the size of the object and find out how much it changes....somehow.
there's gotta be another way to be more accurate.

Re: CMUCam Next Year?
 

The problem with the Camera was the calibration software was junk. I think better calibration software would make all the diffrence. We also ran out of memory in the controler.