Characterizing Human Activity in Spatiotemporal Data

Dr. Jack Cooper
Program Manager, IARPA

Abstract: The Intelligence Advanced Research Projects Activity (IARPA) invests in high-risk, high-payoff research programs to tackle some of the most difficult challenges in the Intelligence Community (IC) and push the boundaries of science to develop solutions that empower the IC to do its work better and more efficiently for national security. This talk will focus on three IARPA programs attempting to characterize human activity on a variety of scales through automated processing of large-scale spatiotemporal data. Efforts include a recently concluded program to identify specific activity in untrimmed security video, a current program to search broad areas for temporal activities in satellite imagery, and a new program seeking to model human mobility to a depth that enables both automated identification of anomalous trajectories and generation of normal activities. Specific thrusts within these programs will be highlighted, including geospatially-aware computer vision, scalable spatiotemporal data architectures, increased behavioral realism in microsimulations, and the creation of datasets in which trajectory anomaly detection algorithms can be scored and evaluated. The talk will highlight recent program successes, their impact to the state of the art, and the persistent challenges the community faces when leveraging diverse spatiotemporal data to understand human activity.

Biography: Dr. Jack Cooper joined IARPA in October of 2020. In his current assignment as a Program Manager, Dr. Cooper focuses on areas of scientific research that include remote sensing, computer vision, trajectory analytics, and large-scale microsimulation. He is IARPA's Program Manager for three programs focused on automating and scaling the IC's ability to detect and characterize human activity in a variety of mediums. These programs are SMART, which seeks to automate the broad area search for a specific activity in satellite imagery; DIVA which aims to automatically find and prioritize activities of interest in massive volumes of security video; and HAYSTAC which will automatically identify anomalous activity by deeply modeling normal human movement in large-scale trajectory data.

Prior to joining IARPA, Dr. Cooper worked at the National Geospatial-Intelligence Agency (NGA) in the Research Directorate, where he was a Senior Staff Scientist for Predictive Analytics. There Dr. Cooper created and executed significant programs to automate Motion GEOINT processing and analysis, resulting in the transfer of multiple analytics into operations in both NGA and IC Partner enterprises. During his time at NGA, Dr. Cooper also built research programs to prepare the agency for future satellite systems and data streams through field experiments, simulation, and creation of new processing algorithms and architectures.   Dr. Cooper graduated from Clemson University in 2012 with a Ph. D and Master's degree in Mathematical Sciences. He previously graduated from the University of Maryland in 2007 with a Bachelor’s degree in Mathematics and Government and Politics.