没有合适的资源?快使用搜索试试~ 我知道了~
计算机研究 -基于近邻传播聚类的极化SAR图像分类.pdf
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 110 浏览量
2022-06-27
14:21:11
上传
评论
收藏 6.98MB PDF 举报
温馨提示
试读
67页
计算机研究 -基于近邻传播聚类的极化SAR图像分类.pdf
资源推荐
资源详情
资源评论
万方数据
摘要
I
摘要
极化合成孔径雷达(Polarimetric Synthetic Aperture Radar,简称 POLSAR)由于
具有比合成孔径雷达(Synthetic Aperture Radar,SAR)更多的极化信息,在近些年,
它已经成为合成孔径雷达发展的重要方向之一,极化 SAR 图像解译也随之显得越
来越重要。而极化 SAR 图像分类是极化 SAR 图像解译的重要内容之一,在农业、
军事、海洋等领域都有广泛的应用。
本文主要着眼于基于近邻传播聚类算法的极化 SAR 图像分类方法的研究。在
近年来,近邻传播聚类算法已经成为机器学习领域的研究热点,它可以自适应地
获得聚类数目,而且该方法快速有效。本文以近邻传播聚类算法为基础,结合聚
类分析和极化 SAR 图像特点,提出了用于极化 SAR 图像分类的方法,主要工作如
下:
1. 提出了一种基于近邻传播聚类算法的极化 SAR 图像分类方法。该方法将基
于类别间的 Wishart 距离取代原算法中的欧式距离作为近邻传播聚类算法的相似性
测度,并结合 Yamaguchi 分解对极化 SAR 图像进行初始分割,然后在初始类别划
分的的基础上对整幅图像用能反映极化 SAR 数据分布的 Wishart 分类器进行迭代
分类,进一步提高分类精度。将该方法用于真实的极化 SAR 图像分类,该方法具
有较高的分类精度,能够自适应获得类别数。
2. 提出了一种基于超像素算法和近邻传播聚类算法的极化SAR图像分类方
法。该方法将极化SAR图像的Pauli分解得到三个特征作为Turbopixle超像素算法的
输入,用Turbopixle算法对极化SAR图像进行预分割处理,将图像分割成互不重叠
的小区域,并将每个区域作为近邻传播聚类算法的输入数据点,从而提高算法效
率;在传统Turbopixle算法基础上,通过像素点间的空间关系,构造了一种新的超
像素的map图,提高了Turbopixle算法的性能。对比已有的几种经典极化SAR分类
方法,该方法取得了较好分类效果及分类精度。
3. 提出了一种基于极化特征和改进的近邻传播聚类算法的极化SAR图像分类
方法。首先,根据相干矩阵特征得到的三个参数对图像进行初始划分;然后,利
用改进的近邻传播聚类算法对获得的初始划分进行聚类,获得预分类结果;最后,
该方法在预分类的结果的基础上,对整幅图像进行复Wishart迭代划分进一步提高
分类的精度。对比已有的几种经典的极化SAR分类方法,该方法能够对非去噪的
极化SAR图像进行分类,保持数据的原有特性。
关键词:极化 SAR 近邻传播聚类算法 Turbopixle Yamaguchi 分解 图像
分类 超像素
万方数据
基于近邻传播聚类的极化 SAR 图像分类
Ⅱ
万方数据
Abstract
III
Abstract
Polarimetric Synthetic Aperture Radar (POLSAR) has more information than
Synthetic Aperture Radar (SAR), in the recently years, it has become the one of the
important directions of the development of SAR, so Polarimetric SAR image
interpretation also will become increasingly important. The polarimetric SAR image
classification is an important part of Polarimetric SAR image interpretation, and has
been widely applied in the agricultural, military, marine and other fields.
This paper mainly focuses on the study of the polarimetric SAR image
classification method based on Affinity Propagation Clustering algorithm. Recently,
Affinity Propagation Clustering algorithms has become a hot research field of machine
learning, which can adaptively obtain the number of clusters, and the method is rapid
and effective. In this paper, combining with cluster analysis and polarization
characteristics of SAR images, three polarimetric SAR image classification methods are
proposed based on affinity propagation clustering algorithm, which mainly include the
following three aspects:
1. We proposed a new classification method based on the improved Affinity
Propagation Clustering to classify the polarimetric SAR image. The proposed method
uses the Wishart distance between the clusters to replace the Euclidean distance in the
original algorithm as similarity measure for the improved Affinity Propagation
Clustering, and combines with yamaguchi decomposition to obtain the to the initial
segmentation, then Wishart classifier is applied to iterative the whole polarimetric SAR
data to further improve classification accuracy. The proposed method is used to classify
real polarimetric SAR image, it can obtain good classification results and be adaptive to
obtain the number of categories.
2. We presented a polarimetic SAR image classification method using Turbopixel
and Affinity Propagation Clustering. In the proposed method, the polarization
characteristics that are geted by Pauli decomposition are regarded as the input of the
Turbopixel algorithm, and the polarimetric SAR image is implemented by Turbopixel
algorithm to divid the image into non-overlapping areas, and each area as the input data
points to the algorithm to improve the efficiency and perform of the Affinity
Propagation Clustering algorithm. Based on the traditional Turbopixel algorithm, we
introduced characteristics of the pixel and the spatial relationship between points to
万方数据
基于近邻传播聚类的极化 SAR 图像分类
IV
construct a new superpixel feature map, which improve the performance of the
Turbopixel algorithm. Compared with the existing polarimetic SAR image classification
methods, the proposed method has significantly higher classification results and
accuracy.
3. We proposed a polarimetric SAR image classification method based on the
polarization features and the improved Affinity Propagation Clustering. First, according
to the three parameters and data distribution characteristic obtained by the coherent
matrix to get initial division; this is followed by a clustering step performed through an
improved Affinity Propagation Clustering based on Wishart distance. Finally, for all the
pixels in the image, the complex Wishart classifier is performed iteratively. Compared
with several polarimetric SAR classification methods, the proposed method has good
anti-noise performance, the advantages of high classification accuracy.
Keywords: Polarimetric SAR image Affinity Propagation Clustering
Turbopixle Yamaguchi Decomposition Image Classification Superpixel
万方数据
剩余66页未读,继续阅读
资源评论
programyp
- 粉丝: 86
- 资源: 1万+
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功