节点文献

SAR图像变化检测及相关技术研究

Related Research on SAR Image Change Detection

【作者】 黄勇

【导师】 黄顺吉;

【作者基本信息】 电子科技大学 , 通信与信息系统, 2006, 博士

【摘要】 图像变化检测技术旨在检测不同时间段的同一场景图像之间发生的变化。图像变化检测技术主要依赖于辐射值或局部纹理的变化。这些变化可能是由于地表覆盖的真实变化引起的,或者是由照射角、大气条件、传感器精度。地面湿度等条件变化引起的。变化检测的基本前提是相对于由一些随机因素引起的变化由对象本身变化引起的辐射值或局部纹理的变化是可分的。合成孔径雷达具有全天候、全天时的特点,可方便地获得同一地区不同时间段的图像,于是SAR图像变化检测是它的一个重要应用领域。SAR图像变化检测是遥感技术的主要应用之一,它通过对不同时期图像的比较分析,根据图像之间的差异来得到我们所需要的变化信息。SAR图像变化检测已经应用于很多方面,如对人工检测比较困难的热带雨林、沙漠等自然条件恶劣的地区进行监测,以了解生态环境变化的情况;对农田进行监测,分析农作物生长状况;对军事目标进行监测,了解兵力部署、军事调动等情报;对城区环境进行监控,合理规划城市布局,土地使用的管理和规范,非法占地和违章建筑的监控等。 随着研究环境和持续发展相关的许多地物变迁现象都是动态变化过程,随着遥感观测技术及SAR成像技术的发展,获取多波段、多极化、多时段的SAR图像的能力已大大提高,可为这些动态过程问题的研究提供丰富的信息源。但是由于地球系统的开放性、复杂性和不确定性,如何有效地提取所需的信息,揭示出其变化等规律,是当前急需解决的问题,通过对不同时段的多通道(多波段或多极化等)的SAR图像之间的变化检测来获取地表覆盖的变化情况便成为一个日益重要的课题研究方向之一。 本文研究了利用合成孔径雷达图像进行变化检测技术及相关技术的研究。研究的内容涉及SAR图像分割、图像分类,图像自动匹配等技术及变化检测技术等。对本文开展的各项研究工作,使用E-SAR图象等数据进行试验及分析验证,所提供的实验结果验和证算法的有效性,并显示了SAR图象在变化检测方面有良好的应用前景。

【Abstract】 Detecting regions of change in multiple images of the same scene taken at different times is of widespread interest due to a large number of applications in diverse disciplines. The change results from many factors, including the changes of targets, texture in the scene, angle of view, atmosphere conditions, and sensors’ precision. In synthetic aperture radar (SAR) image, it may take place because of the parameters of SAR system, such as wave band, polarization, resolution, direction, height and so on. With the development of techniques, change detection has been applied in such fields as remote sensing, surveillance, medical diagnosis and treatment, civil infrastructure, and underwater sensing, assessment of deforestation, damage assessment, urban developments, monitoring vegetation, and other environment changes. The major advantage of SAR is its all-weather capability that allows the acquisition of time series of imagery with exact acquisition dates under all climatic conditions, so change detection of SAR images has become one of the promising research fields.Several detection methods will be described in detail in order to identify what change in images. Going with the development of SAR applications, Change detection has been playing more and more important in remote sensing community. As one of the major applications in SAR technique, change detection also is connected with other SAR technique, such as data correcting, speckle reducing, image segmentation, classification, image features. Change detection and other related technique will be researched in the dissertation. The experiment image data comes from Experiment-SAR and all tests will bring forth the validity of presented algorithms and show the hopeful future of SAR change detection technique.

  • 【分类号】TN957.52
  • 【被引频次】43
  • 【下载频次】2091
  • 攻读期成果
节点文献中: 

本文链接的文献网络图示:

本文的引文网络