This post is also available in: עברית (Hebrew)
Thermal cameras are all over the modern battlefield, from intelligence, surveillance and reconnaissance assets such as drones or vehicle and dismounted targeting systems. But recognizing a face with software in real time has long been out of reach. A new technology may lead to enhanced real-time biometrics and post-mission forensic analysis for covert nighttime operations.
The US Army Research Lab scientists have paired artificial intelligence and machine learning to make a face image from the thermal image seen on many weapons sighting systems, according to an ARL release.
“This technology enables matching between thermal face images and existing biometric face databases/watch lists that only contain visible face imagery,” said Benjamin Riggan, an ARL research scientist. “The technology provides a way for humans to visually compare visible and thermal facial imagery through thermal-to-visible face synthesis.”
Current tech can do facial recognition in daytime or when a person is lit up, such as with a flashlight. But those are not options on a nighttime raid, according to armytimes.com.
“When using thermal cameras to capture facial imagery, the main challenge is that the captured thermal image must be matched against a watch list …,” Riggan said.
But by using captured images of terrorists or persons of interest, troops can use algorithms to search the databases full of photos to match up to their intended target.
Riggan and fellow researcher Shuowen “Sean” Hu, demonstrated their work using key facial areas of eyes, nose and mouth to enhance how the system can discriminate between images stored in the database from what the thermal cameras captured.
Though only in testing, the research will continue under funding from the Defense Forensics and Biometrics Agency, Riggan said.
Forget Photoshop: machine learning corrects photos taken in complete darkness, turns them into amazingly sharp images
We’ve all tried to fix poorly lit pictures in Photoshop, but the results always end up unsatisfactory. You can’t polish a turd, they say. Researchers at the University of Illinois at Urbana–Champaign would beg to differ, however. In a new study, the researchers demonstrated a novel machine learning algorithm that corrects photos taken in complete darkness, with astonishing results.
In order to take decent photos in low-lighting conditions, professionals advise that you set a longer exposure and use a tripod to eliminate blur. You can also increase the camera’s sensor sensitivity, at the cost of introducing noise, which is what makes the photos grainy and ugly.
The new algorithm, however, is capable of turning even pitch black photos into impressively sharp images. They’re not the best, but given the starting conditions, the results are miles away from anything we’ve seen any post-production software do before.
The researchers first trained their neural network with a dataset of 5,094 dark, short-exposure images and an equal number of long-exposure images of the same scene. This taught the algorithm what the scene ought to look like with proper lighting and exposure.
“The network operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data. We report promising results on the new dataset, analyze factors that affect performance, and highlight opportunities for future work,” the researchers wrote.
Some of the photos used to train the algorithm were taken by an iPhone 6, which means that someday similar technology could be integrated into smartphones. In this day and age, the software can matter just as much as the hardware, if not more, when it comes to snapping quality pictures. Think motion stabilization, lighting correction, and all the gimmicks employed by the cheap camera in your phone, in the absence of which photos would look abhorrent.
Who else is looking forward to using this new technology? Leave your comment below.