US Intel Agency Seeks Long-Range Biometric Spy Tech Able to Identify People From Afar

© AP Photo / Mark LennihanA fog hangs above a light pole with a surveillance camera at the World Trade Center, Tuesday, Feb. 20, 2018, in New York
A fog hangs above a light pole with a surveillance camera at the World Trade Center, Tuesday, Feb. 20, 2018, in New York - Sputnik International
Subscribe
The Intelligence Advanced Research Projects Activity (IARPA), the tech research arm within the US’ Office of the Director of National Intelligence, submitted a Request for Information (RFI) on Friday, seeking industry input on the possible creation of a biometric identification system that can spot individuals from afar.

The solicitation, which notes that the RFI is “solely for planning purposes and does not constitute a formal solicitation for proposals,” specifies that the Biometric Recognition and Identification at Altitude and Range (BRIAR) program aims to develop tools that are able to “facilitate unconstrained face recognition in which the pose, illumination, and expression of the subjects is not controlled or limited.”

“The IARPA Janus Program and its resulting research is an example of such recent advances. However, there remains challenges in diverse face detection, verification, and identification when dealing with low-resolution or noisy imagery (e.g., motion blur, atmospheric turbulence),” reads the notice.

“Further research in the area of biometric recognition and identification at altitude and range may support protection of critical infrastructure and transportation facilities, military force protection, and border security.”

In its industry request, the research agency specifically requests a wide variety of datasets, including images successfully snapped at a long-range distance of more than 300 meters or at pitch angles of above 20 degrees, and if biometric datasets were captured from aerial platforms. 

Additionally, IARPA seeks to explore various types of biometric signatures, including but not limited to an individual’s gait, height and gender, rather than solely focusing on a single datapoint in the event that their face is partially obscured.

RFI responses are due October 21, 2019.

This latest development comes months after IARPA issued a solicitation for teams with the ability to train computer vision algorithms to better track people through a large network of security cameras.

Newsfeed
0
To participate in the discussion
log in or register
loader
Chats
Заголовок открываемого материала