Gabor Feature Based Unsupervised Change Detection of Multitemporal SAR Images Based on Two-Level Clustering
Gabor Feature Based Unsupervised Change Detection of Multitemporal SAR Images Based on Two-Level Clustering
复制标题
基于Gabor特征的两级聚类多时相SAR图像无监督变化检测
DOI：
10.1109/lgrs.2015.2484220
复制
发表时间：
2015-12-01
影响因子：
4.8
通讯作者：
Emery, William J.
中科院分区：
文献类型：
--
作者：
Li, Heng-Chao;Celik, Turgay;Emery, William J.
在这封信中，我们从聚类的角度提出了一种简单而有效的多时相合成孔径雷达图像无监督变化检测方法。这种方法联合利用强大的Gabor小波表示和先进的级联聚类。首先，从多时间图像生成对数比图像。然后，为了在特征提取过程中整合上下文信息，采用Gabor小波来产生在多个尺度和方向上的对数比图像的表示，其在每个尺度中的所有方向上的最大幅度被连接以形成Gabor特征向量。然后，在此判别特征空间中，将第一级模糊c均值聚类与第二级最近邻规则相结合，设计了一种级联聚类算法。最后，改变的和未改变的结果的两级组合生成最终的改变图。实验结果证明了该方法的有效性。
In this letter, we propose a simple yet effective unsupervised change detection approach for multitemporal synthetic aperture radar images from the perspective of clustering. This approach jointly exploits the robust Gabor wavelet representation and the advanced cascade clustering. First, a log-ratio image is generated from the multitemporal images. Then, to integrate contextual information in the feature extraction process, Gabor wavelets are employed to yield the representation of the log-ratio image at multiple scales and orientations, whose maximum magnitude over all orientations in each scale is concatenated to form the Gabor feature vector. Next, a cascade clustering algorithm is designed in this discriminative feature space by successively combining the first-level fuzzy c-means clustering with the second-level nearest neighbor rule. Finally, the two-level combination of the changed and unchanged results generates the final change map. Experimental results are presented to demonstrate the effectiveness of the proposed approach.