Stories
Slash Boxes
Comments

SoylentNews is people

posted by Fnord666 on Sunday June 10 2018, @05:58PM   Printer-friendly
from the big-brother dept.

A new algorithm has been used to detect violence in drone-captured video footage:

A drone surveillance system capable of highlighting "violent individuals" in a crowd in real time has been built by [researchers].

The artificially intelligent technology uses a video camera on a hovering quadcopter to study the body movements of everyone in view. It then raises an alert when it identifies aggressive actions, such as punching, stabbing, shooting, kicking, and strangling, with an accuracy of about 85 per cent. It doesn't perform any facial recognition – it merely detects possible violence between folks. And its designers believe the system could be expanded to automatically spot people crossing borders illegally, detect kidnappings in public areas, and set off alarms when vandalism is observed.

The inventors are based at the University of Cambridge, in England, India's National Institute of Technology, and the Indian Institute of Science. They hope their autonomous spy drones will help cops crush crime and soldiers expose enemies hiding in groups of innocents.

Also at Science Magazine.

Eye in the Sky: Real-time Drone Surveillance System (DSS) for Violent Individuals Identification using ScatterNet Hybrid Deep Learning Network (arXiv:1806.00746)


Original Submission

 
This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
  • (Score: 3, Insightful) by Ethanol-fueled on Sunday June 10 2018, @06:29PM (4 children)

    by Ethanol-fueled (2792) on Sunday June 10 2018, @06:29PM (#691150) Homepage

    I can totally see this being deployed at sports events, when you and your buddy are both wearing the jerseys of the same team and you grab him in a headlock and give him a light knuckle-rub on his forehead when your team scores the game-winning goal, both of you laughing, only to have the jackbooted government thugs alerted and deployed to beat you like Rodney King.

    Starting Score:    1  point
    Moderation   +2  
       Insightful=1, Interesting=1, Total=2
    Extra 'Insightful' Modifier   0  

    Total Score:   3  
  • (Score: -1, Troll) by Anonymous Coward on Sunday June 10 2018, @06:33PM (3 children)

    by Anonymous Coward on Sunday June 10 2018, @06:33PM (#691151)

    We can't all get along, you gay Nazi kike lover.

    • (Score: 1) by Ethanol-fueled on Sunday June 10 2018, @06:37PM (2 children)

      by Ethanol-fueled (2792) on Sunday June 10 2018, @06:37PM (#691153) Homepage

      Yes, you are correct. But what happens when you implement this in Eurpoe during football (soccer) events? Everybody would now be classified as "violent" and the database would crawl to a halt from all the writes and other information-overload.

      • (Score: 3, Informative) by archfeld on Sunday June 10 2018, @07:26PM

        by archfeld (4650) <treboreel@live.com> on Sunday June 10 2018, @07:26PM (#691163) Journal

        This system would never survive an Oakland Raiders NFL game either. A riot when they win, a riot when the lose, and a brawl all the way through the game either way.

        --
        For the NSA : Explosives, guns, assassination, conspiracy, primers, detonators, initiators, main charge, nuclear charge
      • (Score: 3, Interesting) by frojack on Sunday June 10 2018, @11:52PM

        by frojack (1554) on Sunday June 10 2018, @11:52PM (#691213) Journal

        the database would crawl to a halt from all the writes

        So, self solving problem then?

        It would also be easy to troll,
        Three guys in the crowd could saturate every drone's attention with stage punches, and nerf bats, and rubber knifes, and draw in all the police, while the real criminals were unloading TVs and calmly walking them down the street.

        --
        No, you are mistaken. I've always had this sig.