Visualization Interface for Sensor Team Aggregation (VISTA)

This proposal is to develop a Visualization Interface for Sensor Team Aggregation (VISTA).VISTA will take video sensor feeds from multiple, distributed UAVs and combine them in near-real-time into a synthetic 3D environment rendered with the original video. VISTA builds on the highly promising SUAVE 3D viewing interface that we have developed under sponsorship from the Air Force Office of Scientific Research (AFOSR) and Office of Naval Research (ONR).This proven concept greatly improves surveillance and target detection in multiple geo-registered image streams (up to 13 have been successfully tested).In this proposal we adapt the existing SUAVE product to explicitly address the multi-platform sensor operators challenge, which is of major interest to government, industry, and academia. In previous work, we assumed that Digital Terrain Elevation Data (DTED) data provided the basic 3D frame for the rendering.But in the VISTA effort we will extract 3D information directly from the video data in near real time, using results applied from a large NSF research project by consultant Prof. Simon Lucey of the Carnegie Mellon University (CMU) Robotics Institute.In addition, we will adopt intelligent human support aids to ensure that the operator gets maximum value from the resulting visualization.