TECHNOLOGY AREA(S): Electronics,
OBJECTIVE: The objective of this project is to develop/implement an artificial intelligence/machine learning (AI/ML) algorithm employed in video surveillance cameras to detect identities, track identities, and disseminate identities through facial recognition from live video surveillance cameras anywhere.
DESCRIPTION: The U.S. Army has a need to enhance security measures at Forward Operating Bases (FOBs) and other secured facilities by detecting threatening individuals, preventing infiltration by non-authorized personnel and rapidly authenticating authorized personnel. To meet this need PM DoD Biometrics is in need of advanced identity verification, biometric identification leveraging real-time video surveillance monitoring and exploitation technologies. The primary objective of the desired capability is to rapidly (in near real time) determine or verify a person’s identity from live video surveillance by automatically detecting, tracking and submitting high-quality face images to a cloud-based enterprise face recognition and alerting system. The system will deliver this capability anywhere, anytime and using any digital video surveillance camera which has Internet/network connectivity. The US Army desires an AI/ML-based face detection, face tracking and face search submission edge-device(s) which is capable of monitoring live video surveillance feeds (from commodity video surveillance cameras to include embedded cameras on Android and iOS devices) coupled with an enterprise cloud-based watch list management and face recognition matching capability. This system is intended to standardize and centralize edge-device management/authorization, face matching, face match adjudication, authoritative watch list management, and alerting/notification mechanisms. The system must be scalable to biometrically enable a large array (10k+) of video surveillance cameras.
PHASE I: The objective is to develop an overall system design that includes specification of AI/ML based techniques employed, specification of architecture required to support concept of operation, sensor specifications required to achieve detect, track, match, and disseminate functions, recognition techniques employed by algorithm, and protocol for employment with current identity operations and intel platforms.
PHASE II: Develop and demonstrate a prototype system in a realistic environment. Conduct testing to prove feasibility over extended operating conditions.
PHASE III: Upon completion of research, software developed could be integrated into current biometric collection capabilities.
KEYWORDS: Machine Learning, Artificial Intelligence, Facial Recognition