Research Summaries

Back Rigid and Articulated Object Detection in Aerial Imagery

Fiscal Year 2011
Division Research & Sponsored Programs
Department Modeling, Virtual Environments & Simuation Institute
Investigator(s) Zabrowski, Robert
Sponsor Space & Naval Warfare Systems Center-Pacific (Navy)
Summary UAVs (Unmanned Aerial Vehicles) collect several hours of video per mission individually, and several years of video in a one year period collectively. Therefore, operators must commit a proportional number of hours reviewing the collected imagery. This process makes the operators, whose review is susceptible to degradation caused by complacency, a single point of failure and potentially reduces the effectiveness of UAV collections. Real-time review of video from UAVs is limited by bandwidth. This project aims to use vision techniques for detection of rigid and articulated objects (cars and people) in aerial video for review, and to allow onboard detection to support transmitting only pertinent images back to a controlling station. Analysis will be performed to determine the spatial and temporal resolution required for effective object detection, ability to perform onboard object detection, and feasibility of articulated object detection for aerial imagery.
Keywords
Publications Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal
Data Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal