Date of Award

3-2000

Document Type

Thesis

Degree Name

Master of Science

Department

Department of Electrical and Computer Engineering

First Advisor

Michael L. Talbert, PhD

Abstract

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 research demonstrates that text-based data accompanying UAV video yields sufficient information to identify and create data items that can be indexed to provide for rapid identification and retrieval of video segments of interest. Four attributes are derived or calculated from mission-related telemetry and target data: look-direction, look-distance, zoom, and solar illumination direction. These attributes provide indicators of potential scene content and image quality thus allowing analysts to select the best (clearest, most detailed) images of a target or target area. A relational database and two tools, a query and profile tool, are implemented to store the data and provide for the retrieval and presentation of video segments to the user. An analysis of the results shows the methodology to be favorable for locating and retrieving video segments of interest. Several recommendations to enhance the methodology are provided at the conclusion of the paper.

AFIT Designator

AFIT-GCS-ENG-00M-01

DTIC Accession Number

ADA381090

Comments

The author's Vita page is omitted.

Download

Share

COinS