Dynamic Data Driven Applications Systems (DDDAS) modeling for Automatic Target Recognition Erik Blasch a , Guna Seetharaman a , Frederica Darema b a Air Force Research Laboratory, Information Directorate, Rome, NY, 13441 c Air Force Research Laboratory, AFOSR, Arlington, VA, 22203 ABSTRACT The Dynamic Data Driven Applications System (DDDAS) concept uses applications modeling, mathematical algorithms, and measurement systems to work with dynamic systems. A dynamic systems such as Automatic Target Recognition (ATR) is subject to sensor, target, and the environment variations over space and time. We use the DDDAS concept to develop an ATR methodology for multiscale-multimodal analysis that seeks to integrated sensing, processing, and exploitation. In the analysis, we use computer vision techniques to explore the capabilities and analogies that DDDAS has with information fusion. The key attribute of coordination is the use of sensor management as a data driven techniques to improve performance. In addition, DDDAS supports the need for modeling from which uncertainty and variations are used within the dynamic models for advanced performance. As an example, we use a Wide-Area Motion Imagery (WAMI) application to draw parallels and contrasts between ATR and DDDAS systems that warrants an integrated perspective. This elementary work is aimed at triggering a sequence of deeper insightful research towards exploiting sparsely sampled piecewise dense WAMI measurements – an application where the challenges of big-data with regards to mathematical fusion relationships and high-performance computations remain significant and will persist. Dynamic data-driven adaptive computations are required to effectively handle the challenges with exponentially increasing data volume for advanced information fusion systems solutions such as simultaneous target tracking and ATR. Keywords: Dynamic Data Driven Applications System (DDDAS), Information Fusion, Automatic target recognition, Wide-Area Motion Imagery, Situation Awareness 1. INTRODUCTION Dynamic Data Driven Applications System (DDDAS) is a concept where measurements form a symbiotic feedback control for applications with or without simulation augmentation [1, 2, 3]. As a control system, DDDAS dynamically uses collected data to (1) guide the measurement process and (2) choose among processing methods over a trade space of two or more interdependent factors. An automatic target recognition (ATR) application operating on sensed data can be thought of as an information fusion system made popular in the 1980s [4]. ATR, like DDDAS, seeks to reduce uncertainty through filtering past data, estimating target classification against models such as that of simultaneously tracking and identifying a target [5, 6]. Using the DDDAS concept, current ATR trends include information management, large volume data processing, and system software over an enterprise for real-world systems design [7]. DDDAS as a concept, supports the advanced systems-level processing needed for complex ATR systems. DDDAS since its inception has been applied to numerous areas where complex real-world conditions are not predetermined by the initialization parameters and initial static data [8, 9, 10]. Three common areas include environmental modeling, situation awareness, and systems-level applications. DDDAS environmental modeling includes oceans [11] and wild fires [12, 13]. Other examples include social services such as transportation [14], emergency medical response [15], and waste distribution [16]. Combining the above applications in a complex system could facilitate accurate weather prediction for emergency response as demonstrated by the Engineering Research Center for Collaborative Adaptive Sensing of the Atmosphere (CASA) formed by the National Science Foundation [17]. These applications for environmental assessment have similar goals of information fusion stochastic modeling for uncertainty assessment [18]. Even diverse applications such as cyber situational awareness [19] have been a forum for DDDAS [20] and ATR situational awareness. These applications are similar to data registration and terrain environmental modeling frequent in the ATR literature. Automatic Target Recognition XXIII, edited by Firooz A. Sadjadi, Abhijit Mahalanobis, Proc. of SPIE Vol. 8744, 87440J · © 2013 SPIE · CCC code: 0277-786X/13/$18 · doi: 10.1117/12.2016338 Proc. of SPIE Vol. 8744 87440J-1 Downloaded From: http://spiedigitallibrary.org/ on 08/28/2013 Terms of Use: http://spiedl.org/terms