基于子空间和神经网络的雷达目标识别软件设计

发布时间：2018-04-25 08:48

  本文选题：合成孔径雷达 + 神经网络　； 参考：《电子科技大学》2014年硕士论文

【摘要】：合成孔径雷达技术可以穿透云雾、可以昼夜工作、高分辨成像等特点,是当前非常重要的对地观测与军事侦察技术。在国民经济领域,通过SAR成像系统能够及时了解不同地区的地面目标情况与环境变化的情况,能够在农业生产、环境监测、资源勘查和防灾减灾等遥感应用领域发挥非常重要的作用。在国防建设中,通过SAR成像系统能够提供地面运动目标和军事目标的高分辨率机载SAR图像,在战场侦察、打击评估等领域有重大的军事应用需求。本论文研究目的是利用先进的高分辨率SAR图像,进行地面典型目标的识别和分类技术研究,并建立相应的典型目标样本库,完成SAR图像目标特征提取及自动识别等功能。论文成果可应用于星载SAR和机载SAR雷达系统,它的成功研发将提高这些系统的实际应用水平,提高星载和机载SAR图像的信息获取和数据处理能力,并可提高目标信息的可信度,降低目标或事件的模糊度,改进对目标或事件的探测能力,完成对战场态势和威胁的实时和完整评估,包括位置和身份估计,以及态势评估和威胁估计。论文成果还可应用于国民经济领域,比如城市规划,资源管理,农作物监控等。
[Abstract]:Synthetic Aperture Radar (SAR), which can penetrate clouds and fog, can work day and night, and has high resolution imaging, is a very important technology of Earth observation and military reconnaissance. In the field of national economy, the SAR imaging system can be used to understand the ground targets and environmental changes in different areas in a timely manner, and can be used in agricultural production and environmental monitoring. Resource exploration, disaster prevention and mitigation and other remote sensing applications play a very important role. In national defense construction, SAR imaging system can provide high resolution airborne SAR images of ground moving targets and military targets, which has great military application needs in the field of battlefield reconnaissance, attack evaluation and so on. The purpose of this paper is to use advanced high-resolution SAR images to study the recognition and classification of typical targets on the ground, and to establish the corresponding typical target sample database to complete the functions of target feature extraction and automatic recognition in SAR images. The results of this paper can be applied to spaceborne SAR and airborne SAR radar systems. Its successful research and development will improve the practical application level of these systems, improve the ability of information acquisition and data processing of spaceborne and airborne SAR images, and improve the credibility of target information. Reduce the ambiguity of the target or event, improve the detection ability of the target or event, complete the real-time and complete assessment of battlefield situation and threat, including location and identity estimation, and situation assessment and threat estimation. The results can also be used in the fields of national economy, such as urban planning, resource management, crop monitoring and so on.
【学位授予单位】：电子科技大学
【学位级别】：硕士
【学位授予年份】：2014
【分类号】：TN957.52
，

本文编号：1800622