Scene-centric identification and retrieval of unmanned aerial vehicle (UAV) video segments

摘要

With the acceptance of unmanned aerial vehicles (UAVs) as a primary platform within the Department of Defense (DOD) for gathering intelligence data, the amount of video information being recorded, analyzed, and archived continues to grow. Mechanisms for quickly locating and retrieving video segments of interest amongst the many hours of recorded video are required to accommodate the rapid turnaround expected in today's wartime planning environments. This paper demonstrates that attributes extracted or calculated from existing mission-related data (specifically telemetry and target data) can be indexed to support random access into archived video streams. These indexes allow video segments to be retrieved based on image characteristics and basic content thus supporting the search for clear, highly detailed images of targets and areas of interest.