This Video Shows How Computers See the World - pragertharsen

How does a automaton "control" the world? The obvious answer is that they ensure it however we humans tell them to. We feed them the video footage that serve Eastern Samoa their "eyes," then we move on our merry way. Merely a refreshing telecasting called Robot Clear World makes the argument for a slightly more complex form of robot vision.

Robots and computers currently appendage the video that we give them using complicated algorithms, and that software is starting to give computers and robots their own distinct way of seeing. We still use cameras to suffice as robot eyes, but the bots can now use their own methods to ready sense of the footage we supply them. And those methods are, candidly, a bit spot creepy.

<p>Your browser does non support iframes.</p>

These kinds of algorithms are already in our lives; they're the same type that the Microsoft Kinect uses to track your movements, e.g.. But much more regent forms of this software net ball computers recognize faces, cars, the great unwashe, and street signs inside video recording footage.

In one exemplar from the video, computers see auto traffic patterns as procedurally generated arrows that show the charge of vibratory vehicles. In another example, the computer sees faces as a series of perpetually moving ovals. Timo Arnall, the video's creator, calls it "an try out in found machine-vision footage, exploring the aesthetics of the robot eye."

Robot Readable World compiles over 30 different examples of video recognition technologies (all listed on the video's verbal description), and puts them ended an unnerving soundtrack (a song titled "Cold Summer Landscape" by the band Blear Moon) to create a vision of how computers go complex forms and movement refine into something they pot interpret.

The interesting matter about these technologies isn't how much they let computers catch things the same way we do; instead, information technology's how otherwise robots see the world. Seeing the charitable of intense processing that information technology takes for a robot to act a simple task like turn a corner really drives home how, even out as robots clear the ability to replicate Thomas More and more human actions, the machines we're building are "thinking" in fundamentally different slipway.

[Vimeo via Beyond the Beyond]