A post-classification change detection method based on iterative slow feature analysis and Bayesian soft fusion
A post-classification change detection method based on iterative slow feature analysis and Bayesian soft fusion
复制标题
基于迭代慢特征分析和贝叶斯软融合的分类后变化检测方法
DOI：
10.1016/j.rse.2017.07.009
复制
发表时间：
2017-09
影响因子：
13.5
通讯作者：
L. Zhang
中科院分区：
文献类型：
--
作者：
C. Wu;B. Du;X. Cui;L. Zhang
多时相遥感影像的后分类是变化检测中最常用的方法之一，在真实的应用中可以提供详细的“从-到”的变化信息。然而，由于它忽略了在多时间图像中的相应像素之间的时间相关性的事实，后分类方法通常遭受误分类错误的积累。为了解决这个问题，以前的研究已经分离的变化和非变化的候选人与变化向量分析，他们只更新类的变化像素与后分类，但是，这种方法与阈值失去了连续的变化强度信息，其中较大的值表示更高的概率被改变。因此，在本文中，一个新的后分类方法与迭代慢特征分析（ISFA）和贝叶斯软融合的建议，以获得可靠和准确的变化检测地图。该方法包括3个主要步骤：1）对每幅图像进行独立分类，得到每幅图像的类别概率; 2）利用ISFA算法得到多时相图像的连续变化概率图，其中每个像素的值表示变化概率; 3）基于贝叶斯理论，计算耦合像素类别组合的后验概率，将类别概率与变化概率进行整合，这被称为贝叶斯软融合。然后，具有最大后验概率的类别组合被确定为变化检测结果。此外，提出了一种类别概率滤波器，以避免由于同一类别内的光谱变化而引起的虚警。多时相Landsat Thematic Mapper（TM）图像的两个实验表明，所提出的方法实现了明显更高的变化检测精度比当前国家的最先进的方法。基于贝叶斯理论和ISFA的方法也被验证有能力提高变化检测率，同时减少虚警。该方法具有有效性和灵活性，可广泛应用于大尺度土地利用/土地覆被变化的检测和监测。
Post-classification with multi-temporal remote sensing images is one of the most popular change detection methods, providing the detailed “from-to” change information in real applications. However, due to the fact that it neglects the temporal correlation between corresponding pixels in multi-temporal images, the post-classification approach usually suffers from an accumulation of misclassification errors. In order to solve this problem, previous studies have separated the change and non-change candidates with change vector analysis, and they have only updated the classes of the changed pixels with the post-classification; however, this approach with thresholding loses the continuous change intensity information, where larger values indicate higher probability to be changed. Therefore, in this paper, a new post-classification method with iterative slow feature analysis (ISFA) and Bayesian soft fusion is proposed to obtain reliable and accurate change detection maps. The proposed method consists of three main steps: 1) independent classification is implemented to obtain the class probability for each image; 2) the ISFA algorithm is used to obtain the continuous change probability map of multi-temporal images, where the value of each pixel indicates the probability to be changed; and 3) based on Bayesian theory, thea posterioriprobabilities for the class combinations of coupled pixels are calculated to integrate the class probability with the change probability, which is named as Bayesian soft fusion. The class combination with the maximuma posterioriprobability is then determined as the change detection result. In addition, a class probability filter is proposed to avoid the false alarms caused by the spectral variation within the same class. Two experiments with multi-temporal Landsat Thematic Mapper (TM) images indicated that the proposed method achieves a clearly higher change detection accuracy than the current state-of-the-art methods. The proposed method based on Bayesian theory and ISFA was also verified to have the ability to improve the change detection rate and reduce the false alarms at the same time. Given its effectiveness and flexibility, the proposed method could be widely applied in land-use/land-cover change detection and monitoring at a large scale.
登录
查看更多内容
DOI：
10.1007/11941439_114
发表时间：
2006-12
期刊：
--
影响因子：
--
作者：
Marina Sokolova;N. Japkowicz;S. Szpakowicz
通讯作者：
Marina Sokolova;N. Japkowicz;S. Szpakowicz
影响因子：
13.5
作者：
Jian Yang;P. Weisberg;N. Bristow
通讯作者：
Jian Yang;P. Weisberg;N. Bristow
DOI：
10.1016/j.isprsjprs.2006.09.004
发表时间：
2006-11
影响因子：
12.7
作者：
H. Nemmour;Y. Chibani
通讯作者：
H. Nemmour;Y. Chibani
影响因子：
13.5
作者：
R. Bindschadler;T. Scambos;Hyeungu Choi;T. Haran
通讯作者：
R. Bindschadler;T. Scambos;Hyeungu Choi;T. Haran
影响因子：
3.4
作者：
Zhi Huang;X. Jia;L. Ge
通讯作者：
Zhi Huang;X. Jia;L. Ge