Search and Rescue Drones Use AI to Find People Lost in Woods

When people get lost in the woods, time is of the essence to rescue them as the longer they stay there the more dangerous things become. But do we have the tools to organize such search and rescue operations efficiently and with great speed?

RELATED: SCIENTISTS CREATE UV LIGHT-EMITTING DRONE TO FIGHT COVID-19 FROM ABOVE

We soon may. Today, most forest search and rescue operations are done with helicopters. Personnel on these choppers fly over the areas where the lost people may most likely be and look for them. To aid them in their efforts, thermal imaging cameras are used.

These cameras are meant to highlight differences in body temperatures enabling rescue personnel to distinguish between the people and their environment. However, the devices sometimes get confused especially when it is hot and the trees and surrounding foliage also have elevated temperatures.

Researchers took these facts into consideration and decided to engineer drones that would be particularly adept at recognizing humans from everything that surrounds them. They achieved this by using a deep learning application to improve the images that are collected by drones.

An impressive rate of precision

"In the future, rescuing lost, ill or injured persons will increasingly be carried out by autonomous drones. However, discovering humans in densely forested terrain is challenging because of occlusion, and robust detection mechanisms are required. We show that automated person detection under occlusion conditions can be notably improved by combining multi-perspective images before classification," wrote the researchers in their study published in Nature Machine Intelligence.

"Here, we employ image integration by airborne optical sectioning (AOS)—a synthetic aperture imaging technique that uses camera drones to capture unstructured thermal light fields—to achieve this with a precision and recall of 96% and 93%, respectively." This is an impressive milestone compared to the 25% achieved by traditional thermal imaging.

Best of all, the team of researchers says the device is ready for use. We bet many organizations will be waiting in line to get their hands on this new technology!