Slashdot Mirror

← Back to Stories (view on slashdot.org)

Software Describes Surveillance Footage In AI-Generated Text

Posted by timothy on from the now-he's-throttling-the-interstitial-ad dept.

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."

2 of 132 comments (clear)

  1. oh, academia by FuckingNickName · · Score: -1, Flamebait

    40 years ago you were where people retreated to if they didn't want to exploit the Far East as part of the political game.

  2. UCLA researchers by Anonymous Coward · · Score: -1, Flamebait

    Nice to see you generating cutting edge research that the United police States of America can use to spy againt all of society.

    I hope someone rapes these researchers kids, on camera, so that these researchers can read in text form how criminals have vaginally and analy penetrated their children.