Slashdot is powered by your submissions, so send in your scoop

 



Forgot your password?
typodupeerror
×
The Military Transportation Hardware

Automatic Life Jacket Detection For Drones 85

garymortimer writes "Sentient, an Australian company that makes drone software, has given UAVs the ability to search for small, high visibility objects such as life jackets. From the article: 'Kestrel Maritime is a software solution that processes electro-optical (EO) and infrared (IR) full motion video (FMV) from manned and unmanned vehicles (UAVs). The Life Jacket Detection enhances Kestrel Maritime EO capability to automatically detect small, high visibility objects whilst searching wide maritime areas.'"
This discussion has been archived. No new comments can be posted.

Automatic Life Jacket Detection For Drones

Comments Filter:
  • This can't be the first software of its kind... Five years ago, NASA was using much more subtle feature detection software in detecting interesting rocks and regions from satellite imagery of Mars. It seems like life jacket detection in oceans would be a much simpler reduction of that problem.
    • by Eevee ( 535658 )
      Well, unless NASA isn't telling us something, there's not a whole lot of ocean on Mars. Spotting a static object without a major time limit isn't exactly the same as having to spot a moving object in choppy seas before the person drowns or freezes, while keeping enough fuel to return to base. (Yes, I watch too much Deadliest Catch.)
    • by Hojima ( 1228978 )

      It's news because in addition to detecting for objects such as life jackets, breakthroughs in analyzing software also has the ability to search for pairs of concentric circles located on anyone in a visible area, and prioritize them by size.

      That's right I made a boob joke, go ahead and mod me down, it was worth it.

    • by rvw ( 755107 )

      This can't be the first software of its kind... Five years ago, NASA was using much more subtle feature detection software in detecting interesting rocks and regions from satellite imagery of Mars. It seems like life jacket detection in oceans would be a much simpler reduction of that problem.

      In WWII, they used pigeons to do this. Simply train them to pick a button when they see an orange spot somewhere. Then reward them with some food. I wonder how this compares to the software, in price and performance.

    • This can't be the first software of its kind... Five years ago, NASA was using much more subtle feature detection software in detecting interesting rocks and regions from satellite imagery of Mars. It seems like life jacket detection in oceans would be a much simpler reduction of that problem.

      Yes, but what is the cover story that it was not used?

    • by Yvanhoe ( 564877 )
      Color detection. Glad to hear that someone, somewhere, managed to sell this software as "state of the art AI bleeding edge software". I hope it helped fund the parts that the investor may found "trivial" like navigation and control.
  • Seems good (Score:4, Insightful)

    by serps ( 517783 ) on Sunday February 20, 2011 @10:20PM (#35264100) Homepage
    Nice positioning. Search and rescue staff will still fly around in helicopters with mk1 eyeballs because they don't trust the drone. However, while trying to sell the image-recognition package as a bolt-on to a heli will fail due to pushback from observers, selling in a drone package will be considerably more palatable, psychologically.
    • Re:Seems good (Score:5, Interesting)

      by camperdave ( 969942 ) on Sunday February 20, 2011 @10:54PM (#35264260) Journal
      Search and Rescue also fly around with pigeons [susanscott.net] which are trained to peck at a button when they see life-jacket orange. They hit at a 90% rate compared to a human's 38%. Humans in helicopters? If your floating in the drink I think you'd be better off with a drone. Granted, a rescue chopper could pick you up as soon as they saw you, but at nearly a 2/3 chance of being missed?
    • Helicopters will full rescue crew are expensive to build and operate. I would imagine the best use of these drones would be to blanket the search grid. Instead of a handful of planes and helicopters doing lawnmower patterns over thousands of square miles of ocean, you could put a drone over every few dozen square miles. Use them to supplement the human search (or vice versa), and have the rescue helos check out any positive hits the drones report.
      • by rtb61 ( 674572 )

        Only really acceptable to save money in this manner if the drones are large enough to drop a rescue raft or to act as a rescue raft themselves after making a splash down as near as practicable to the stranded person or persons.

    • by afidel ( 530433 )
      I doubt the drones will even be able to fly in the kind of conditions that cause most coastguard calls. Now for analyzing the video provided from the FLIR pod on the rescue copter, that's probably a great helper for the crew.
      • Well they are close to all weather, the UAS fighters en route certainly will (X47)
        • by afidel ( 530433 )
          Globalhawk's very cool but I doubt it could fly below cloud deck during a noreaster on the Bearing Sea as an example of what I'm talking about. In fact I doubt any fixed wing aircraft could do it.
  • by soundhack ( 179543 ) on Sunday February 20, 2011 @10:21PM (#35264104)

    Wow, I get that this has search and rescue applications, but the first time I read it I thought this was developed as a way to kill ejected pilots.

    Too many flight sim games I guess.

    • by e4g4 ( 533831 )

      search and rescue applications [...] I thought this was developed as a way to kill ejected pilots.

      It seems ideally suited to both tasks...

    • :) Same here. ... Al Qaida in Pakistan wearing bright yellow life vests? Huh? ....ohhhhhh, now I get it: search and rescue NOT search and destroy. Oh man, I think our war-focused culture is warping my mind.
    • Wow, I get that this has search and rescue applications, but the first time I read it I thought this was developed as a way to kill ejected pilots.

      Exactly. I mean, these are *drones*, right? Since when is technology like this actually designed from the get-go for "good"?

      Is this some sort of sick joke?

      I for one am *not* amused by what is surly once again a sick, sick cruel abuse by the Military-Industrial Complex. Shame on garymortimer [suasnews.com] for submitting this astroturf, and even more shame on samzenpus for posting it.

      They've got to you, haven't they, samzenpus? How much did they pay you?

    • Historically speaking pilots make excellent hostages.

      • Meh. Whose pilots are we gonna capture these days? Irans airforce probably wouldn't survive takeoff, and Kim Jong Il's boys would probably defect before we had a chance to shoot at them. Unless the Taliban has bought some crop-dusters, I don't think it's much of an issue for the next couple decades.

    • by Ihmhi ( 1206036 )

      You've got an enemy combatant - a highly trained one at that - alone and unarmed (or, at best, lightly armed) in the middle of the ocean. Why would you kill him when you could just as easily capture him?

    •     That's pretty much what I thought of when I saw the story too.

          Advanced technology is usually done for military purposes, not humanitarian ones.

          Equipping drones to detect people on the ground (or in the water) is more likely for targeting than for search and rescue.

  • in b4 refugees!

    *ducks for cover

  • High visibility is relative, in the IR band a speedboat full of pirates is high visibility. The military value of this could be huge. Regardless it looks like all coast guard and search and rescue ships will need to carry drones.
    • What about just having the drones based on land, flying around high-risk areas (possibly only when an alarm is raised), and when someone is found in the water, we send out a helicopter? I don't know about the economics, but my guess is that the drone fleet is reasonable enough in comparison to having a load of helicopters sent out each time a mayday is heard.

      • "What about just having the drones based on land, flying around high-risk areas (possibly only when an alarm is raised), and when someone is found in the water, we send out a helicopter? I don't know about the economics, but my guess is that the drone fleet is reasonable enough in comparison to having a load of helicopters sent out each time a mayday is heard."

        If a mayday is sent out (and for this argument let's assume it's legit, I don't know how many are sent that aren't.) There may not be time for drone

        • by TooMuchToDo ( 882796 ) on Sunday February 20, 2011 @11:32PM (#35264454)

          http://en.wikipedia.org/wiki/Northrop_Grumman_RQ-4_Global_Hawk [wikipedia.org]

          "It can survey as much as 40,000 square miles (100,000 square kilometers) of terrain a day."

          Performance
          Maximum speed: 497.1 mph (800.0 km/h; 432.0 kn)
          Cruise speed: 404 mph (351 kn; 650 km/h)
          Range: 15,525 mi (13,491 nmi; 24,985 km)
          Endurance: 36 hours
          Service ceiling: 65,000 ft (19,812 m)

          Faster than a helicopter, and with these new algorithms, better at finding people. I say we send the drones.

        • by izomiac ( 815208 )
          I'd imagine a helicopter could get there pretty quick, as the drones have a limited operating range and are flying in a search pattern rather than a bee-line to the victim. OTOH, I wonder how well the small drones will operate in stormy weather, when most ships run into trouble...
          • Drones can be built to handle worse weather than a human pilot could. Drones don't have the squishy-body limitation on sudden accelerations. You could do things like kick in a rocket engine for 2 seconds and do a 20 gee ballistic exit from a death spiral, etc.

            Drones are cheap to fly. One vision of their use is to have the USCG maintain 24/7 patrols of the coast, with the drone on patrol and the rescue helicopter both dispatched to the scene when a mayday is received. The drone would usually arrive first a

        • If you know where the mayday is then you just send a lifeboat and/or helicopter straight there. I doubt these drones will change that.

          The problem is when you have a report of someone missing and/or a mayday from someone who is unable to provide their own location. You then have to search a potentially huge area to try and find them. Afaict there simply aren't the resources (at least here in the UK) to dispatch more than one or two search and rescue helicopters to an incident. If drones are cheaper than heli

      • by Kinky Bass Junk ( 880011 ) on Sunday February 20, 2011 @10:48PM (#35264246)
        Responding to mayday calls is never a matter of budget. It is always a matter of saving lives as quickly and safely as possible. While scrambling UAVs to search would be good to assist, you would still want to scramble a staffed rescue helicopter at the same time.
        • The response to an individual call may not be but the availiable resources are. At a high level someone will have to decide what resources to spend the money available for search and rescue on. Someone else will have to decide how best to deploy those resources to the calls that are coming in at any moment.

      • Seems like a fleet of drones operating from a ship would be one way of dealing with the Somali pirate problem. Drones are cheap enough to operate that 24/7 high altitude surveillance of the pirate coast is possible, with other surveillance drones dispatched as needed to track any potential pirate boats. Armed drones could intercept a possible pirate boat that was approaching another vessel, and could sink the damn thing if it began to fire on its victim.

        The drone pilots could be hired at cheap wages and t

  • It seems like it would be a good additional resource in SAR, not instead of manned helicopters and trained SAR personnel. There's a limit to the number of expensive helicopeters and costly trained crews, using these in conjunction would enable a lot more area to be covered quickly
  • Just so long as it works better than this software [slashdot.org].
  • Here, I'll fix it:

    "The Life Jacket Detection (LJD) enhances Kestrel Maritime EO (KMEO) capability to automatically detect (CAD) small, high visibility objects (SHVOs) whilst searching (WS) wide maritime areas (WMAs)."

    That should do it (TSDI).
  • Oh My God (OMG). That Is So Cool. (TISC) unmanned vehicle (UAV)/drone (drone) software(SW) for the win! (FTW!)

    K.

  • Now we can recover all those expensive life jackets.

  • This is developed by an Australian company, Australian governments interest is in "boat people" illegal immigrants detection, they currently fly around in P3 Orion's all day looking for rotting old boats on a one way trip from Indonesian waters. Drones are a massive cost saving there.

    Search and rescue just makes it sound all nice, but the real application is in border protection, replacing expensive aircraft with cheap drones which can be in the air constantly and can cover a much larger area (check a map,

  • They can scan full motion video, in real time, looking for objects that are made up of a highly contrasting color? Isn't this just an HSV partitioning? My iPhone can do that in real time (actually, it's a 3G, so it can't do anything at all, thanks for the upgrades Steve).
    • So then the USCG will just snatch you, strap you and your phone to an UAV, and fly you out over the sea/ocean.
      Hell, with you and your phone on board, they don't even have to send out a helo...just have the UAV dip down so you can grab the victim.
      Get a grip....

      COTS: Civilian/Citizen Off The Streets

      • Get a grip on what? The plain fact of the matter is that the capability described by TFA is one that has been around since the beginning of computer vision research and is not worthy of the awe, wonder, and excitement espoused in other responses. It is a simple algorithm, and can run quickly on commodity hardware, but I guess since it says "UAV" in the title, everyone wants to salivate and clap and otherwise act like fools over old table scraps. THERE'S NOTHING NEW HERE /.!

        Get a grip indeed.

  • How long until the drones spot that they're not wearing life jackets and start demanding them

  • Please don't go. The drones need you. They look up to you.
  • I honestly thought this was going to be an article about military technology, since a (pathetic or humorous, take your pick) segment of insurgents seem to believe that wearing a "life jacket" is somehow protecting them from being shot.

  • Oh sure, the drone can spot you, call for help, and loiter around as long as it can to reassure you that, yes, someone is coming. I bet the drone could even have some supplies attached to a hard point, maybe a capsule with a life raft and five man-days worth of supplies suitable to the area.

    Hell, I bet the drone could even act as a WiFi hotspot or wireless repeater. You wouldn't get pulled out of the water right away, but you could sure as hell post all about it on Facebook.

I have hardly ever known a mathematician who was capable of reasoning. -- Plato

Working...