Surface Ships Need More Offensive Punch, Outlook

Shapps is really a smart cookie isn't he? I mean who knew the Navy had to be able to destroy targets on the sea, in the air and on land?
Tomorrow's revelation - the RAF needs aircraft with wings on which to fly.
No, tomorrow's revelation is that the RAF needs anti-ship missiles to destroy targets at sea. :(


 
Last edited:
Last edited:
Which is fair, California doesn't accept that it's part of the US either.

When you run 1/5 of the country’s economy, roughly the size of France, and have over ten percent of the population of the U.S., you probably get an outsized say in things. Texas is similar in its stance. Florida and NYC are close contenders.
 

The dataset consists of a large number (~600) of publicly available images of AEGIS-equipped ships, with their SPY arrays and VLS blocks highlighted. The presumption is that this is being used to train AI/ML image-recognition tools. They speculate that the author could be anything from a military or university research team to a motivated undergrad using it as a showcase for employers. It's about an order of magnitude smaller than typical ML training datasets.

To me, it looks like this could be a first step toward a ship recognition/identification tool. There are pretty well-developed ML ship detection tools to find ships in overhead imagery but not too many (in public) that do specific ship-class identification. Training one specifically to recognize only AEGIS ships seems like an odd side-alley to go down unless it was just a proof-of-concept for a more general capability to identify specific ship classes.
 
The dataset consists of a large number (~600) of publicly available images of AEGIS-equipped ships, with their SPY arrays and VLS blocks highlighted. The presumption is that this is being used to train AI/ML image-recognition tools. They speculate that the author could be anything from a military or university research team to a motivated undergrad using it as a showcase for employers. It's about an order of magnitude smaller than typical ML training datasets.

To me, it looks like this could be a first step toward a ship recognition/identification tool. There are pretty well-developed ML ship detection tools to find ships in overhead imagery but not too many (in public) that do specific ship-class identification. Training one specifically to recognize only AEGIS ships seems like an odd side-alley to go down unless it was just a proof-of-concept for a more general capability to identify specific ship classes.
Given the number and open source nature of the images, I would probably think either an undergrad or university researcher would be responsible for it. Certainly shows what tools are currently available, although I expect a service system would use a much wider range of resources, gathered from a much wider range of systems (IIR and SAR).
 
“The Navy does not intend to replace Ticonderoga-class cruisers with CG(X). In the near term, the DDG 51 FLT III, and DDG(X) in the long term, fulfill the requirements historically supported by the Ticonderoga-class cruisers.

What a joke. In the meantime China is starting on their next batch of Type 055s, after getting eight in the water, while the USN stood there with its dick in its hands. If only we had a hull ready to go.

160421-N-YE579-005_(26543438313).jpg
 
if the shift towards war on terror didn't happen maybe we would have had the money to buy more peer to peer conflict type weapons. One could argue that if the war on terror didn't suck up all of our cyber security and spying talents, we wouldn't get that massive data breaches and tech steals that allows china to speed up 5th gen fighter missile and carrier tech.
 
The US hasn't built a proper cruiser since Long Beach. The Ticos were laid down a DDGs, and they're broadly interchangeable with the Arleigh Burkes. The fact that DDG(X) was originally referred to a Large Surface Combatant should tell you that the US Navy does not meaningfully view them as separate types anymore (not that they were to begin with).
 

Similar threads

Please donate to support the forum.

Back
Top Bottom