SAR Image Generation of Ground Targets for Automatic Target Recognition Using Indirect Information

The effectiveness of using the simulated synthetic aperture radar (SAR) images military targets in databases for automatic target recognition (ATR) is widely known. However, to be useful, they must sufficiently similar measured images; otherwise, can degrade ATR performance. Two factors affect quality SAR images: precision associated computer-aided design (CAD) model and accuracy speed numerical techniques used solve electromagnetic problems image generation. In this study, a method 3D CAD modeling proposed; when direct access not feasible only indirect information available. Further, bistatic formation concept based on shooting-and-bouncing-ray technique adopted; helps achieve an comparable that monostatic method. Moreover, it highly enhanced computation speed. combination, these proposals provide efficient fast generate database effectively support activities. We demonstrate proposed by comparing with ones structural similarity as measure; further, we evaluate rate obtained images. show measure bears strong relation rate, which aspect may further contribute considerable time savings validating refining databases.