基于伪Zernike的多通道SAR多航过自动目标识别
计算机视觉与模式识别
2014-08-07 v3
摘要
在战场场景中，利用多种信息源的能力至关重要。从不同来源获取、在空间和时间上分离的信息提供了利用多样性来减少不确定性的机会。针对雷达平台自动目标识别（ATR）这一特定挑战，通道（如极化）和空间多样性均可为此关键任务提供有用信息。本文提出将伪Zernike矩应用于多通道多航过数据，利用多样性和不变性特性，实现高置信度ATR、低计算复杂度和低数据传输需求。通过真实数据验证了所提方法在不同配置和数据源可用性下的有效性。
引用
@article{arxiv.1404.1682,
title = {Pseudo-Zernike Based Multi-Pass Automatic Target Recognition From Multi-Channel SAR},
author = {Carmine Clemente and Luca Pallotta and Ian Proudler and Antonio De Maio and John J. Soraghan and Alfonso Farina},
journal= {arXiv preprint arXiv:1404.1682},
year = {2014}
}
备注
The paper has been withdrawn due to conceptual errors in the performance analysis and to the fact that a substantial restructuring of the paper is required