Image Segmentation for Target Attitude using a Priori Knowledge

Weapons systems testing and analysis is crucial to engineering, understanding, qualifying, and deploying advanced weapons systems. With the boom in camera technology over the past decade and commercial availability of high-speed imaging systems, using image based methods to support weapons testing and analysis has become the state of practice for military test ranges. Existing capabilities of image based analysis rely largely on input from human analysts, pristine environmental collection conditions, and/or complex workflows for data collection and analysis. To provide a more automated, accurate and robust capability, research and development in the area of automated computer vision algorithms for target attitude estimation is needed. To meet these challenges, Toyon proposes to leverage a developed Bayesian estimation framework for target attitude estimation that has demonstrated performance on related weapons testing data. This algorithm will serve as the cornerstone of the Phase II prototype Analysis Toolbox for Target Attitude using Bayesian Object Estimation in Imagery (ATTA-BOEI). The standalone ATTA-BOEI software prototype will enable target attitude and provide other useful automated image analysis tools such as background estimation and removal. The end product will be a rich and reliable analysis capability for weapons testing and evaluation.