Slashdot Mirror
Software Describes Surveillance Footage In AI-Generated Text
holy_calamity writes "A computer vision research group at UCLA has put together a system that watches surveillance footage and generates a text description of the events in real time. It only works on traffic cameras for now but demonstrates how sophisticated computer vision is becoming. Interestingly, the system was built thanks to a database of millions of human-labeled images put together by Chinese workers."
It a whole lot more objective than leaving it up to police officers. If it weren't for the obvious privacy issues in whoever's running this knowing where my car has been, I'd be happy if every intersection had this sort of thing. Traffic flow would be improved immensely. Of course the privacy thing really is a deal breaker when it comes to this level of surveillance (I'd trust the AI, but unfortunately, these sort of systems always have a human in the mix).
I'd much prefer that we'd all switch to AI controlled cars.
It a whole lot more objective than leaving it up to police officers.
If every law was 'objectively' enforced 24/7, life would be unbearable and most of us would be in jail; the end result would be social collapse or civil war.