|
|
![]() ![]() |
|
Thread Tools | Display Modes |
![]() |
|||
Veteran
Join Date: Mar 2023
Location: Washington, DC
Casino cash: $-6809500
|
NFL to potentially use optical tracking system to measure 1st Downs for 2024
Quote:
Quote:
|
||
Posts: 4,248
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
![]() |
![]() |
#31 |
MVP
Join Date: Feb 2013
Casino cash: $-678884
|
They're still going to use the sticks and chain as a backup.
|
Posts: 18,321
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
![]() |
![]() |
#32 |
Supporter
Join Date: Dec 2004
Location: Ozarks
Casino cash: $-359436
|
|
Posts: 34,822
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
![]() |
![]() |
#33 | |||
Mindful Taoist German
Join Date: Aug 2000
Casino cash: $6551662
|
Quote:
If they can fix that I'm all in. For some reason I fully expect this roll out to start with a complete and immediate failure. Hopefully they've tightened all the screws on this process already...
__________________
Quote:
Quote:
|
|||
Posts: 78,093
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
![]() |
![]() |
#34 |
Supporter
Join Date: Dec 2004
Location: Ozarks
Casino cash: $-359436
|
I could not agree more, it is maddening!
|
Posts: 34,822
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
![]() |
![]() |
#35 |
Has a particular set of skills
Join Date: Dec 2003
Location: On the water
Casino cash: $-641038
![]() |
It looked like on our final drive in overtime that we made the first down twice on 3rd down. But, they marked it short. Twice we had to make a 4th down or we lose the SB. Maybe if this is in place they call down to the refs and tell them it was a 1st down.
__________________
Mahomes is not a game manager. Release the Kraken. |
Posts: 81,276
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
![]() |
![]() |
#36 | |
Veteran
Join Date: Oct 2010
Casino cash: $3625409
|
Quote:
Words like "Optical Tracking" sound like they're playing around with computer vision, AKA convolutional neural networks and drawing bounding boxes. Using that kind of technique you wouldn't need sensors you'd use a model that's been trained on tens of thousands of hours of video and you measure the probability of false alarm and probability of detection. Get the PD up to 99% and the PFA down and then you can have some level of confidence that you're outperforming the human. |
|
Posts: 4,520
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
![]() |
![]() ![]() |
|
|