自动目标识别
人工智能
计算机科学
合成孔径雷达
计算机视觉
目标捕获
图像质量
模式识别(心理学)
图像处理
分类器(UML)
图像(数学)
作者
L.M. Novak,G.J. Owirka,W. S. Brower,Alison L. Weaver
摘要
■ Lincoln Laboratory has developed a new automatic target recognition (ATR) system that provides significantly improved target-recognition performance compared with ATR systems that use conventional synthetic-aperture radar (SAR) image-processing techniques. We achieve significant improvement in target-recognition performance by using a new superresolution imageprocessing technique that enhances SAR image resolution and image quality prior to performing target recognition. A computationally efficient two-stage template-based classifier is used to perform the target-recognition function. This article quantifies the improvement in target-recognition performance achieved by using superresolution image processing in the new ATR system.
科研通智能强力驱动
Strongly Powered by AbleSci AI