Non-Cooperative Facial Recognition Video Dataset Collection Plan

Kimura, Marcia L. ; Erikson, Rebecca L. ; Lombardo, Nicholas J.

关键词: facial recognition;    dataset collection plan;   

DOI  :  10.2172/1126360
RP-ID  :  PNNL-22681
PID  :  OSTI ID: 1126360
Others  :  Other: 400904120

美国|英语

来源: SciTech Connect

【 摘 要 】

The Pacific Northwest National Laboratory (PNNL) will produce a non-cooperative (i.e. not posing for the camera) facial recognition video data set for research purposes to evaluate and enhance facial recognition systems technology. The aggregate data set consists of 1) videos capturing PNNL role players and public volunteers in three key operational settings, 2) photographs of the role players for enrolling in an evaluation database, and 3) ground truth data that documents when the role player is within various camera fields of view. PNNL will deliver the aggregate data set to DHS who may then choose to make it available to other government agencies interested in evaluating and enhancing facial recognition systems. The three operational settings that will be the focus of the video collection effort include: 1) unidirectional crowd flow 2) bi-directional crowd flow, and 3) linear and/or serpentine queues.