Benjamin Riggan, assistant professor of electrical and computer engineering, is part of WatchID — a team of researchers from across the country participating in a competitive federal government research program to develop software systems capable of performing whole-body biometric identification from long distances and at elevated pitch angles.
According to the Intelligence Advanced Research Projects Activity website, the Biometric Recognition and Identification at Altitude and Range (BRIAR) program is vital because many intelligence agencies require the ability to recognize individuals under challenging scenarios – such as at long range (300-plus meters), through atmospheric turbulence, and from watchtowers or unmanned aerial vehicles (drones).
“If you think from 1,000 meters that you can get somebody’s fingerprint, by all means try, but it’s not likely to succeed given the limited resolution,” Riggan said. “Characteristics like a person’s face, gait, or physical measurements between joints — like the length of the bone from an elbow to the wrist — that’s the type of information that may help make recognition successful at long range.”
The multi-disciplinary research team is comprised of Intelligent Automation — A BlueHalo Company, the University of Nebraska-Lincoln, the University of Nebraska at Omaha, the University of Maryland College Park and Resonant Sciences.
Riggan is leading the NU system team, which will receive up to $1 million (or more) across BRIAR’s three program phases to support the cost of the research and the work of three graduate students.
BRIAR’s Phase I, which runs 18 months, is underway. Riggan said Nebraska’s contribution in this phase will be on whole-body biometric identification, particularly re-identification and facial recognition in both domain-adaptive and unsupervised systems and supporting large-scale data collection efforts.
As a former research scientist at the U.S. Army Research Lab, Riggan’s experience working on nighttime facial recognition—matching thermal face images with enrolled visible face images—will be beneficial in matching distorted, low-quality, outdoor imagery with higher-quality, indoor enrollment imagery
This phase, Riggan said, will face many logistical challenges. That includes finding places in the Lincoln area where researchers can fly drones far enough from Lincoln Municipal Airport so the drones will not interfere with airplane traffic. Riggan said one location for this data collection is the university’s research farm near 84th Street and Havelock Avenue.
Then there’s recruiting more than 200 subjects to be evaluated and have their biometric information collected both indoors and outdoors and after wardrobe changes. If Riggan’s team is selected to move on in the competition, he said, the second phase might require three times as many subjects for data collection.
Riggan noted that there may be concerns about this type of work, mostly centered on privacy issues. The team is emphasizing the use of ethical practices that are reviewed and approved by university Institutional Review Boards, such as the use of consenting human subjects across all data collections and allowing subjects to decide whether their identifiable data may be used in publications or presentations.
“It’s important to have a focus on privacy and performing responsible research while performing biometric research,” Riggan said.