The use of biometric technology to identify known enemy combatants is a major theme in military circles right now, and there are multiple tests and trials running to evaluate what works best under different conditions. Challenges include enrollment and identification at a distance, from vehicles, from covert deployments and on the move—and so all kinds of innovative thinking are being applied. Now, the MIT Technology Review has reported that this includes a laser developed for the U.S. military to “identify people from a distance by their heartbeat.”
The focus for these technologies within the military is the recognition of known threats at distance. The most prevalent solution for standoff biometric detection is facial recognition, but that technology clearly requires visibility of a subject’s face and can be hampered by poor lighting and enrollment imagery. Jetson, the Pentagon’s new device, “uses a technique known as laser vibrometry to detect the surface movement caused by the heartbeat,” and can reportedly “identify people without seeing their faces… detecting unique cardiac signatures with an infrared laser.” Albeit, it currently only works out to distances of 200 meters, has an accuracy rate of around 95%, and needs a pre-enrolled database of cardiac signatures.
According to the MIT Technology Review, Jetson works by extending existing technology “used to check vibration from a distance in structures such as wind turbines [and] takes about 30 seconds to get a good return.” The system is currently limited to stationary targets who are not wearing heavy clothing—so, early days still. Most biometric identification technologies operate in controlled conditions. Shifting to a standoff, non-compliant, non-controlled environment increases the complexity many times over. This new technology will encounter the same problems as other technologies.
Cardiac identification joins gait recognition, voiceprint, facial recognition and fingerprinting as biometrics become ever more commonplace in identity assurance. From a military perspective, think connected IoT sensors leveraging central datasets in battlefield conditions. The U.S. Army’s Advanced Research Labs (ARL) envisages integrated sensors, wearables, weaponry and vehicles “to develop the fundamental understanding of dynamically-composable, adaptive, goal-driven IoBT (Internet of Battlefield Things),” including the fundamental challenge of target acquisition.
Alexander Kott, chief of ARL’s Network Science Division, and colleagues call this “the emerging reality of warfare.” Here scientists envisage laser missile shields and battlefields where ground and airborne vehicles, and even soldiers themselves, are autonomous robots. “Robots probably will fight robots,” says Kott, ”there’s no question about it.”
In that sense, biometric identification of humans joins a long list of new technologies being honed for the military but which will also have wider applications. Facial recognition has been the subject of significant criticism in recent months, given accuracy levels especially when applied to minorities. That said, the general accuracy of properly-applied facial recognition is higher than 95%, and it needs only a camera and a computer processor to work, no lasers are required.
Ultimately, standoff biometrics with better than 99.9% accuracy, open source images including social media scraped datasets, as well as behavioral analytics and object classifiers, will all find their way onto the frontline. The questions that will then come will all be around the decision-making process when machines have identified potential matches.
In the meantime, this technology may find its way into hospitals before it sees battlefield conditions.