Professor wins IARPA subcontract to improve full-body long-range biometric identification


A West Virginia University (WVU) professor has been awarded a four-year, $750,000 subcontract to refine remote whole-body biometric data collection as part of an ongoing project by an organization research from the US Intelligence Community.

Jeremy Dawson, associate professor in the Department of Computer Science and Electrical Engineering at Lane, will form a research group with undergraduate and graduate students enrolled at the university to collect whole-body imaging data from hundreds of voluntary participants in order to meet the challenges of identifying people. at extreme distances and angles. The dataset will then be used to train and test biometric algorithms.

“Facial recognition performance is strongly impacted by distance, individual pose, lack of adequate resolution; all of these things weigh heavily on the ability of facial recognition systems to correctly identify people,” Dawson comments. “The data we collect will enable the development of new facial recognition algorithms robust enough to handle the harsh conditions present in real-world operational scenarios.”

Dawson says the biometric data set will be collected at a “relatively close distance” with cameras, then collect images from longer distances and extreme angles as participants perform specific actions like walking or interacting with their phone. “Collecting enough data in situations that would make it harder to recognize people is our primary goal,” Dawson says.

The goal is to create a large-scale biometric database of images and videos of a person’s face, gait, body shape and type in order to refine the identification accuracy of a biometric algorithm from low quality images obtained from a drone or security camera. Dawson adds that facial and full-body imagery will help improve human recognition as a whole across age, gender, and ethnicity, creating more equitable algorithms. WVU says the research will have potential in health care, law enforcement and national security.

The subcontract is part of the Biometric Recognition and Identification at Altitude and Range (BRIAR) program organized by Intelligence Advanced Research Projects Activity (IARPA), a research and development arm of the US Office of the Director of National Intelligence (ODNI). IARPA awarded contracts to companies and universities in March as part of its efforts to identify and recognize remote individuals and disturbances such as atmospheric turbulence using drones.

WVU is a contractor to Systems and Technology Research (STR), which won the BRIAR contract in March. The university will provide the biometrics data to STR and IARPA, which will then be used as a resource for the general biometrics research community.

ODNI has been working since 2019 to refine the biometric recognition of the whole body remotely. In 2020, he issued a request for information and released more details about what he was looking for, such as the ability to identify people with biometric data at 300 meters addressed by Dawson.

Article topics

biometric identification | biometrics | biometric search | facial recognition | financing | walking recognition | IARPA | long distance | research and development | West Virginia


Comments are closed.