Humans aren’t particularly good at spotting sharks using aerial data. At best, they’ll accurately pinpoint sharks 30 percent of the time — not very helpful for swimmers worried about stepping into the water. Australia, however, is about to get a more reliable way of spotting these undersea predators. As of September, Little Ripper drones will monitor some Australian beaches for signs of sharks, and pass along their imagery to an AI system that can identify sharks in real-time with 90 percent accuracy. Humans will still run the software (someone has to verify the results), but this highly automated system could be quick and reliable enough to save lives.
The detection AI is a quintessential machine learning system. The team trains the system to both look for sharks based on aerial videos as well as distinguish them from other life on the water. That approach doesn’t just help it identify sharks, though. It can also flag dolphins, whales and other sea creatures of interest, which could give researchers an additional way to track populations.
Also, the use of drones doesn’t just save helicopters valuable flight time. The drones hold beacons and life rafts, so they can offer immediate help to anyone who’s in distress. Little Ripper is also developing an electronic ‘repellent’ that the drones could use to keep sharks at bay until rescuers arrive.
Australia isn’t relying solely on drones. The country has been deploying nets along its northeastern shores to prevent sharks from entering areas in the first place. However, drones could at least augment those methods, and would arguably be friendlier to the local ecosystem. Instead of fencing off areas and potentially blocking access to other species, authorities could use robotic fliers to deal with sharks only when they pose a genuine threat.
Published at Sun, 27 Aug 2017 05:25:00 +0000