how do these people do it?

[ahack3r]

hey Society Of Robots, I just joined in the hopes of learning more about computer vision robots. I want to know how autonomous motion tracking robots like http://zero-op.com/mercenary and
http://www.paintballsentry.com/ do it? I've read what they say on their sites, but how can someone else get at least a similar result with open source products?

After hours of research, I have narrowed my choices to these:

software possibilities:
http://code.google.com/p/weaponsgradekavelaars/
http://code.google.com/p/airsoft-sentry-gun/
http://opencv.willowgarage.com/wiki/Welcome

hardware possibilities:
http://www.trossenrobotics.com/p/desktop-robot-turret.aspx
http://www.trossenrobotics.com/p/phantomX-robot-turret.aspx
http://www.robotshop.com/arduino-experimentation-kit-9.html

In your opinion, what are the best two choices for a fast, autonomous, open source, motion tracking device?

thank you for any help and information.

[Henry342]

To be honest, I've tried all the open source stuff and it sucks real bad. To the naive user it seems similar but when you actually go and try to use the different programs in real life scenarios you start to see how vastly inferior the open source stuff is. Also, I'm almost certain zero-op is out of business. Their site hasn't changed for a year or more and no one answers at their email address. http://www.paintballsentry.com/ is very active though.

[ahack3r]

To be honest, I've tried all the open source stuff and it sucks real bad. To the naive user it seems similar but when you actually go and try to use the different programs in real life scenarios you start to see how vastly inferior the open source stuff is. Also, I'm almost certain zero-op is out of business. Their site hasn't changed for a year or more and no one answers at their email address. http://www.paintballsentry.com/ is very active though.

yes, Zero-Op seems to be very dead.  :'( can someone at least give me information on what microcontroller, servo controllers and how they went about programming it all? I realize that you can't know for sure, but whats a good guess? lets figure this out together, if in 2 years I have this beast working, all who help will be mentioned in the youtubes

[Henry342]

What's wrong with the paintball sentry site? The prices are very reasonable and is really the only solution out there. Zero-Op was trying to sell their system for $3000. It's no wonder they went out of business.

[Hawaii00000]

Here's how would do this.
Build/buy a turret with two servos controlling movement and webcam for vision.
Use a microcontroller (Arduino/Axon) to control the servos and communicate to a laptop via serial.
Buy/30 day trial Roborealm and run it on the laptop.

Personally I think this is the easiest way. Unfortunately Roborealm isn't free after the trail. Its $95 or something like that.

[ahack3r]

Here's how would do this.
Build/buy a turret with two servos controlling movement and webcam for vision.
Use a microcontroller (Arduino/Axon) to control the servos and communicate to a laptop via serial.
Buy/30 day trial Roborealm and run it on the laptop.

Personally I think this is the easiest way. Unfortunately Roborealm isn't free after the trail. Its $95 or something like that.

I may just end up buying it. thanks for the help.

[Henry342]

I've messed with the open source stuff quite a bit. It is a nice concept I guess but currently the link you posted before ( http://www.thesentryproject.com ) is just worlds better the any of that other stuff. Well, it depends on what you're after. If you just want to spend hours and hours tinkering but don't really care about how good the end result is then go with one of the small open source projects. However, if you need it to work correctly and well in real life scenarios then the only choice is http://www.thesentryproject.com (IMO). As far as cost goes, I ended up wasting more money and time fussing with arduinos, compilers, and junk before I finally just bought the $50 kit from the sentry project. Doing the math, if I had just gone with them in the first place it would've cost me a lot less for much better result. Lessons learned I guess...