Dual Affine Transform Method and Extended Kalman Filter for Target Extraction and 3-D Position Location from Video Images

Period of Performance: 12/18/1998 - 12/18/2000

$598K

Phase 2 SBIR

Recipient Firm

Compusensor Technology Corp.
352-C Christopher Avenue
Gaithersburg, MD 20879
Principal Investigator

Research Topics

Abstract

This Phase II proposal is submitted to NSWCDD as a result of the Phase I contract N00178-97C-3029. We propose a Phase II effort to continue the research and development of a computer system for 3-D geolocation of ground targets using UAV mounted digital camera and GPS receiver. Our artificial vision approach to geolocation of ground target has advantages of not using pre-surveyed ground points and GIS database and being autonomous. The Phase I work has shown the feasibility of building such a real-time, low cost, high accuracy geolocation system. Phase II work will build a protype computer system for demonstration and further testing and evaluation. The Phase II work will include both algorithmic process enhancement and software development. We will make sophistication of key processes, orientation of exposure stations, and incorporate a lens distortion correction process. We will build graphic user interface to facilitate experiments, demonstration, testing, and evaluation. We will build the whole process into a well documented computer software, which after testing and evaluation will be the starting point of Phase III development of a specialized computer system product.