Structural feature learning-based unsupervised semantic segmentation of synthetic aperture radar image

Structural feature learning-based unsupervised semantic segmentation of synthetic aperture radar image
复制标题

基于结构特征学习的合成孔径雷达图像无监督语义分割

DOI:
10.1117/1.jrs.13.014501
复制
发表时间:
2019-01
影响因子:
1.7
通讯作者:
Gu Jing
Gu Jing
中科院分区:
工程技术4区
文献类型:
--
作者:
Liu Fang;Chen Puhua;Li Yuanjie;Jiao Licheng;Cui Dashen;Cui Yuanhao;Gu Jing

文献摘要

参考文献

被引文献

相似文献

抽象的。区域图是高分辨率合成孔径雷达(SAR)图像在其语义空间中层语义层上的稀疏表示。基于区域图的语义信息,将高分辨率SAR图像分为混合、结构和同质像素子空间。 SAR图像的分割可以分为这三种子空间分割,其中混合子空间的分割由于结构复杂而更具挑战性。混合像素子空间中常常存在许多极其不均匀的区域。这些不相连的区域属于相同类别还是不同类别?为了解决这个问题,提出了一种带有草图特征约束的贝叶斯学习模型和初始化方法,以构造能够反映每个极不均匀区域的本质特征的结构向量。然后,利用本文中这些区域的结构向量可以实现混合像素子空间的无监督分割。理论分析和实验结果表明,本文提出的基于贝叶斯学习模型的结构向量实现的混合像素子空间分割的性能优于仅手工设计特征的方法。
Abstract. Region map is the sparse representation of a high-resolution synthetic aperture radar (SAR) image on the middle-level semantic layer in its semantic space. Based on the semantic information of the region map, the high-resolution SAR image is divided into hybrid, structural, and homogeneous pixel subspaces. The segmentation of SAR images can be divided into these three subspaces segmentation, of which the segmentation of hybrid subspace has more challenge because of complex structures. There are often many extremely inhomogeneous areas in the hybrid pixel subspace. Are these nonconnected areas in the same or different classes? To solve this problem, a Bayesian learning model with the constraint of sketch characteristic and an initialization method is proposed to construct a structural vector that can reflect the essential features of each extremely inhomogeneous area. Then, the unsupervised segmentation of the hybrid pixel subspace can be realized by using the structural vectors of these areas in this paper. Theoretical analysis and experimental results show that the performance of the hybrid pixel subspace segmentation realized by the structural vectors based on the Bayesian learning model proposed in the paper is better than that only used by hand designing features.
基于归一化三变量互信息的半监督亲和力传播用于高光谱波段选择
DOI: 10.1109/jstars.2014.2371931
发表时间: 2015-06
影响因子: 5.5
作者:
Feng, Jie;Liu, Fang;Sun, Tao;Zhang, Xiangrong
通讯作者: Zhang, Xiangrong
DOI: --
发表时间: 2016-02
期刊: --
影响因子: --
作者:
Chongxuan Li;Jun Zhu;Bo Zhang-
通讯作者: Chongxuan Li;Jun Zhu;Bo Zhang-
DOI: 10.18653/v1/p16-1063
发表时间: 2016-06
期刊: ArXiv
影响因子: --
作者:
Shaohua Li;Tat-Seng Chua;Jun Zhu;C. Miao
通讯作者: Shaohua Li;Tat-Seng Chua;Jun Zhu;C. Miao
DOI: 10.1613/jair.251
发表时间: 1996-01-01
影响因子: 5
作者:
Saul, LK;Jaakkola, T;Jordan, MI
通讯作者: Jordan, MI
DOI: 10.1002/9780470611111.ch4
发表时间: 2010-01
期刊: --
影响因子: --
作者:
F. Adragna;S. L. Hégarat-Mascle;J. Nicolas
通讯作者: F. Adragna;S. L. Hégarat-Mascle;J. Nicolas