Building Damage Assessment Based on the Fusion of Multiple Texture Features Using a Single Post-Earthquake PolSAR Image
Building Damage Assessment Based on the Fusion of Multiple Texture Features Using a Single Post-Earthquake PolSAR Image
复制标题
使用单个震后 PolSAR 图像融合多种纹理特征的建筑物损坏评估
DOI：
10.3390/rs11080897
复制
发表时间：
2019-04
期刊：
影响因子：
5
通讯作者：
Wansheng Pei
中科院分区：
文献类型：
--
作者：
Wei Zhai;Chunlin Huang;Wansheng Pei
破坏性地震发生后，大部分伤亡是由建筑物倒塌造成的。我们的工作重点是使用单一事件后PolSAR（全偏振合成孔径雷达）图像提取建筑物损坏信息，以便有效地进行应急决策。PolSAR数据受阳光影响，包含更丰富的反向散射信息。方向与SAR飞行通道不平行的未损坏建筑物与倒塌建筑物具有相似的主导散射机制，即体散射，因此容易混淆。然而，这两种建筑有着不同的肌理。为了更准确地对受损建筑和未受损建筑进行分类，采用OPCE （optimization of polarization contrast enhancement）算法增强两种建筑纹理的对比度，并提出了精度加权多特征融合（precision weighted multifeature fusion， PWMF）方法合并多个纹理特征。实验结果表明，与传统方法相比，该方法的准确率提高了8.34%。总的来说，所提出的PWMF方法可以有效地融合多个特征，并且可以减少对建筑物倒塌率的过高估计。
After a destructive earthquake, most of the casualties are brought about by building collapse. Our work is focused on using a single postevent PolSAR (full-polarimetric synthetic aperture radar) imagery to extract the building damage information for effective emergency decision-making. PolSAR data is subject to sunlight and contains richer backscatter information. The undamaged buildings whose orientation is not parallel to the SAR flight pass and the collapsed buildings share similar dominated scattering mechanisms, i.e., volume scattering, so they are easily confused. However, the two kinds of buildings have different textures. For a more accurate classification of damaged buildings and undamaged buildings, the OPCE (optimization of polarimetric contrast enhancement) algorithm is employed to enhance the contrast ratio of the textures for the two kinds of buildings and the precision-weighted multifeature fusion (PWMF) method is proposed to merge the multiple texture features. The experiment results show that the accuracy of the proposed novel method is improved by 8.34% compared to the traditional method. In general, the proposed PWMF method can effectively merge the multiple features and the overestimation of the building collapse rate can be reduced using the proposed method in this study.
登录
查看更多内容
影响因子：
3.4
作者：
Balz, Timo;Liao, Mingsheng
通讯作者：
Liao, Mingsheng
DOI：
10.11873/j.issn.1004-0323.2016.5.0975
发表时间：
2016-11
期刊：
Remote Sensing Technology and Application
影响因子：
--
作者：
Zhai Wei;Shen Huanfeng;Huang Chunlin
通讯作者：
Zhai Wei;Shen Huanfeng;Huang Chunlin
DOI：
10.1109/igarss.2016.7730237
发表时间：
2016-07
期刊：
2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
影响因子：
--
作者：
Hao Dong-;Xin Xu;Rong Gui;Chao Song;H. Sui
通讯作者：
Hao Dong-;Xin Xu;Rong Gui;Chao Song;H. Sui
影响因子：
20.6
作者：
Gulab Singh;Y. Yamaguchi;W. Boerner;Sang-Eun Park
通讯作者：
Gulab Singh;Y. Yamaguchi;W. Boerner;Sang-Eun Park
影响因子：
7.4
作者：
D. Peduto;G. Nicodemo;J. Maccabiani;S. Ferlisi
通讯作者：
D. Peduto;G. Nicodemo;J. Maccabiani;S. Ferlisi