Can people be identified from drone videos?
The Intelligence Advanced Research Projects Activity is asking researchers to develop algorithms that can perform biometric identification of people in video captured under challenging range, atmospheric and view conditions.
The intelligence community wants to identify people in video taken by drones.
The Biometric Recognition and Identification at Altitude and Range (BRIAR) program aims to develop algorithm-based systems capable of whole-body (WB) biometric identification up to 1,000 meters away, from security cameras or drones and through visual interference like rain or fog.
“Expanding the range of conditions in which accurate and reliable biometric-based identification could be performed would greatly improve the number of addressable missions, types of platforms and sensors from which biometrics can be reliably used, and quality of outcomes and decisions,” the Intelligence Advanced Research Projects Activity (IARPA) said in a Dec. 10 solicitation.
In spite of the advances in facial recognition, many challenges remain for WB identification. Low-resolution images or those where the subject is in motion are difficult for current systems to process, as are images captured at high camera pitch angles, such as those collected from security cameras on building tops or via unmanned aerial vehicles.
As a result, IARPA said it wants to apply the advances in facial recognition to identifying other aspects of a human form -- such as shape, gait or measurement -- to determine the “universal, unique and permanent” WB biometric signals that can be used for verification, recognition or identification. BRIAR is asking researchers to develop algorithms that can perform biometric identification of people in visible-band video captured under challenging range, atmospheric and view conditions.
Because of the lack of sharable WB biometric research data to train algorithms with, BRIAR will also include a robust data collection initiative so researchers have diverse and relevant imagery for algorithm training and for testing and evaluating the algorithm’s accuracy.
The three-phase, four-year program aims to develop computationally efficient solutions that will work under a range of biometric capture conditions and with degraded imagery.
Research outcomes from the BRIAR program are intended to support missions such as counterterrorism, protection of critical infrastructure and transportation facilities, military force protection, and border security.
Read more about BRIAR here.