As the bird indicated, each computer is being used completely. We're right at the space and weight (mass!) limits already. We couldn't add redundant computers even if we needed to.
Basically, the vision code will eat as many cycles as we can throw at it and still be hungry for more. We have three cameras, trying to run as close to 30 frames a second as possible, with a very consiserable amount of processing to be done on each frame. In 2003 we were lucky to get through a complete cycle of all three cameras ever 1.5 seconds. This year, hopefully, that will be closer to 250 milliseconds, which will still be a long way from the target of 33.
![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png){kind=small}
no subject
Basically, the vision code will eat as many cycles as we can throw at it and still be hungry for more. We have three cameras, trying to run as close to 30 frames a second as possible, with a very consiserable amount of processing to be done on each frame. In 2003 we were lucky to get through a complete cycle of all three cameras ever 1.5 seconds. This year, hopefully, that will be closer to 250 milliseconds, which will still be a long way from the target of 33.