SAR Image Classification Based on CRFs With Integration of Local Label Context and Pairwise Label Compatibility

SAR Image Classification Based on CRFs With Integration of Local Label Context and Pairwise Label Compatibility
复制标题

基于局部标签上下文集成和成对标签兼容性的条件随机场的 SAR 图像分类

DOI:
10.1109/jstars.2013.2262038
复制
发表时间:
2014
期刊:
JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
影响因子:
--
通讯作者:
Wenxian Yu
Wenxian Yu
中科院分区:
其他
文献类型:
--
作者:
Yongke Ding;Yuanxiang Li;Wenxian Yu

文献摘要

参考文献

被引文献

相似文献

背景信息在SAR图像分类中起着至关重要的作用,因为高分辨率SAR数据提供了更多关于场景背景和视觉结构的信息。提出了一种新的基于条件随机场(CRF)的SAR图像分类方法,该方法综合了低层特征、局部标签上下文和成对标签兼容性。首先,我们提取低层次的特征用于基于SVM的一元分类器的SAR图像。超纹理是新引入的低层特征之一,用于对图像块之间的纹理上下文进行建模。然后,我们描述了上下文信息,包括局部上下文势和成对势。类别上下文的结合有助于解决一元分类器的歧义。实验证明,该方法在高分辨率SAR图像分类的准确性和视觉外观的性能。
Context information plays a critical role in SAR image classification, as high-resolution SAR data provides more information on scene context and visual structures. This paper presents a novel classification method for SAR images based on conditional random fields (CRFs) with integration of low-level features, local label context, and pairwise label compatibility. First, we extract the low-level features used in the SVM-based unary classifier for SAR images. The supertexture is newly introduced as one of the low-level features to model the texture context between image patches. Then, we describe the context information, including local context potential and pairwise potential. Incorporation of the category context helps to resolve the ambiguities of the unary classifier. The performance of our approach in both accuracy and visual appearance for high-resolution SAR image classification is proved in the experiments.
DOI: 10.1109/tpami.2008.105
发表时间: 2008-08
影响因子: 23.6
作者:
Takahiro Toyoda;O. Hasegawa
通讯作者: Takahiro Toyoda;O. Hasegawa
DOI: 10.1109/lgrs.2010.2089427
发表时间: 2011-05
影响因子: 4.8
作者:
Xin Su;Chu He;Qian Feng;Xinping Deng;Hong Sun
通讯作者: Xin Su;Chu He;Qian Feng;Xinping Deng;Hong Sun
DOI: --
发表时间: 2007-12
期刊: --
影响因子: --
作者:
J. Verbeek;B. Triggs
通讯作者: J. Verbeek;B. Triggs
DOI: --
发表时间: 2008
期刊: --
影响因子: --
作者:
Chih-Wei Hsu;Chih-Chung Chang-;Chih-Jen Lin
通讯作者: Chih-Wei Hsu;Chih-Chung Chang-;Chih-Jen Lin
DOI: 10.1016/j.isprsjprs.2008.09.006
发表时间: 2009-09
影响因子: 12.7
作者:
F. Dell’acqua;P. Gamba;G. Lisini
通讯作者: F. Dell’acqua;P. Gamba;G. Lisini