But there is a problem. Explosions are easy to see. For many tasks other than bomber-hunting, however, an awful lot of staring at screens looking for things that are out-of-the-ordinary is involved. People are bad at this—and there is, besides, a lack of willing eyeballs. A study published last year by researchers at the rand Corporation, a think-tank, showed that America’s air force has responded to the flood of data from wami sensors by archiving most of it without inspection. Better means of sifting wami footage are needed. And technology is starting to provide them.
Chips called graphic-processing units, borrowed from the video-game industry, are helping. So is machine learning, the basis of much modern artificial intelligence. But special tricks are also being deployed—for example, a mathematical technique called higher-order moments anomaly detection that can distinguish moving objects reliably from background clutter by looking at groups of pixels in a video and deciding whether their changes from frame to frame are the result of actual movement or just electronic noise.
Meanwhile, wami devices themselves are becoming yet more effective. The latest, announced on April 25th by Transparent Sky, a firm in Albuquerque, New Mexico, promises to take the technology to another dimension. Literally. The video images it shoots are 3d rather than the 2d of a normal wami feed.
This type of aerial surveillance involves indiscriminately recording everything that is going on in a particular neighbourhood, and then looking for useful patterns in the resulting footage https://t.co/90rPv72vz1
— The Economist (@TheEconomist) May 6, 2022