论文部分内容阅读
为提高极化合成孔径雷达(SAR)遥感图像对海面舰船目标的检测性能,提出了一种基于条件熵的多视极化SAR图像的舰船目标检测方法。首先将多视极化SAR数据进行Cloude特征分解,然后使用特征向量得到对应分量的相似性参数,利用特征值和相似性参数构造事件的概率和条件概率,从而构造功率条件熵。最后,该文提出了一种基于Parzen窗的杂波概率分布的估计方法,并基于该方法得到的概率分布提出了一种检测阈值的搜索方法。使用该方法,可以增加目标和杂波的对比度,并能准确搜索检测阈值。
In order to improve the detection performance of Polarimetric Synthetic Aperture Radar (SAR) remote sensing images on the surface of a ship, this paper proposes a method of detecting the target of a ship based on the conditional entropy of multi-view Polarimetric SAR images. Firstly, multi-view polarimetric SAR data are decomposed by Cloude features, and then the similarity parameters of corresponding components are obtained by using eigenvectors. The eigenvalues and similarity parameters are used to construct the probability and conditional probability of events to construct power conditional entropy. Finally, a method of estimating the clutter probability distribution based on Parzen window is proposed in this paper. Based on the probability distribution obtained by this method, a search method of threshold detection is proposed. Using this method, you can increase the contrast of the target and the clutter and accurately search for the detection threshold.