Metric learning based collapsed building extraction from post-earthquake PolSAR imagery
Metric learning based collapsed building extraction from post-earthquake PolSAR imagery
复制标题
DOI：
10.1109/igarss.2016.7730237
复制
发表时间：
2016-07
期刊：
影响因子：
--
通讯作者：
Hao Dong-;Xin Xu;Rong Gui;Chao Song;H. Sui
中科院分区：
文献类型：
--
作者：
Hao Dong-;Xin Xu;Rong Gui;Chao Song;H. Sui
本文提出了一种基于度量学习的震后PolSAR图像倒塌建筑物提取方法。在该方法中，考虑并分析了8个与建筑物和方位相关的特征，包括熵H、平均散射角α、各向异性A、圆极化相关系数ρ和具有相干矩阵旋转的Yamaguchi 4分量分解的4个散射功率。然后，通过改进的信息理论度量学习（ITML）从倒塌和完整的建筑样本学习转换矩阵。通过这种变换矩阵，特征被投影到低维空间，以减轻地形和建筑物的方位角的影响。最后利用k - NN分类器对倒塌建筑物和完好建筑物进行区分.在2010年青海玉树地震后获取的RadarSAT-2 PolSAR图像上对该方法进行了测试。通过对一幅超高分辨率（VHR）光学图像的人工判读图验证了结果。实验结果表明，该方法可以有效地利用有限的样本和一幅震后PolSAR图像提取倒塌建筑物区域。
In this paper we proposed a metric learning-based method to extract collapsed buildings from post-earthquake PolSAR imagery. In this method, eight building and orientation related features, including entropy H, the average scattering angle α, anisotropy A, the circular polarization correlation coefficient ρ and the four scattering powers of Yamaguchi 4 component decomposition with a rotation of the coherency matrix, are considered and analyzed. Then a transformation matrix is learned from collapsed and intact building samples via an improved informational-theoretic metric learning(ITML). With such a transformation matrix, the features are projected into a low-dimension space to mitigate the impact of topography and building's aspect angle. Finally a k - NN classifier is utilized to distinguish collapsed and intact buildings. The proposed method is tested on one RadarSAT-2 PolSAR image acquired after 2010 Yushu Earthquake in the Qinghai Province of China. Results are validated by the manually interpretation map of a very high resolution (VHR) optical image. It shows that, the method is efficient to extract collapsed building areas using limited samples and only one post-earthquake PolSAR image.