Change Detection Using High Resolution Remote Sensing Images Based on Active Learning and Markov Random Fields
Change Detection Using High Resolution Remote Sensing Images Based on Active Learning and Markov Random Fields
复制标题
基于主动学习和马尔可夫随机场的高分辨率遥感图像变化检测
DOI：
10.3390/rs9121233
复制
发表时间：
2017-11
期刊：
影响因子：
5
通讯作者：
Huang Pingping
中科院分区：
文献类型：
--
作者：
Yu Huai;Yang Wen;Hua Guang;Ru Hui;Huang Pingping
变化检测在遥感中得到了广泛的应用，例如用于灾害评估和城市扩展检测。虽然使用无监督方法来检测来自多时间图像的变化是方便的，但是结果可以进一步改进。在监督方法中，需要繁重的数据标记任务，并且具有真实的类别的样本注释过程是繁琐且昂贵的。为了减轻标签的负担，并获得满意的结果，我们提出了一个互动的变化检测框架的基础上主动学习和马尔可夫随机场（MRF）。更具体地说，在开始时以无监督的方式找到有限数量的代表性对象。然后，将非常有限的样本标记为“变化”或“无变化”以训练简单的二元分类模型，即，高斯过程模型。利用该模型，采用“最简单”的样本选择策略，选择并标记信息量最大的样本，对原有的弱分类模型进行更新，直到检测结果没有明显变化。最后，最大后验概率（MAP）变化检测有效地计算通过最小割为基础的整数优化算法。可以大大减少耗时费力的人工标记过程，并可以获得理想的检测结果。对几幅WorldView-2图像的实验表明了该方法的有效性。
Change detection has been widely used in remote sensing, such as for disaster assessment and urban expansion detection. Although it is convenient to use unsupervised methods to detect changes from multi-temporal images, the results could be further improved. In supervised methods, heavy data labelling tasks are needed, and the sample annotation process with real categories is tedious and costly. To relieve the burden of labelling and to obtain satisfactory results, we propose an interactive change detection framework based on active learning and Markov random field (MRF). More specifically, a limited number of representative objects are found in an unsupervised way at the beginning. Then, the very limited samples are labelled as “change” or “no change” to train a simple binary classification model, i.e., a Gaussian process model. By using this model, we then select and label the most informative samples by “the easiest” sample selection strategy to update the former weak classification model until the detection results do not change notably. Finally, the maximum a posteriori (MAP) change detection is efficiently computed via the min-cut-based integer optimization algorithm. The time consuming and laborious manual labelling process can be reduced substantially, and a desirable detection result can be obtained. The experiments on several WorldView-2 images demonstrate the effectiveness of the proposed method.
登录
查看更多内容
DOI：
10.1109/cvpr.2008.4587630
发表时间：
2008-06
期刊：
2008 IEEE Conference on Computer Vision and Pattern Recognition
影响因子：
--
作者：
Subhransu Maji;A. Berg;Jitendra Malik
通讯作者：
Subhransu Maji;A. Berg;Jitendra Malik
影响因子：
11.8
作者：
Guokang Zhu;Qi Wang;Yuan Yuan-Yuan;Pingkun Yan
通讯作者：
Guokang Zhu;Qi Wang;Yuan Yuan-Yuan;Pingkun Yan
影响因子：
13.5
作者：
Valeska Scharsich;Kupakwashe Mtata;M. Hauhs;H. Lange;C. Bogner
通讯作者：
Valeska Scharsich;Kupakwashe Mtata;M. Hauhs;H. Lange;C. Bogner
DOI：
10.1016/j.jag.2016.08.010
发表时间：
2017-02-01
影响因子：
7.5
作者：
Leichtle, Tobias;Geiss, Christian;Taubenboeck, Hannes
通讯作者：
Taubenboeck, Hannes
DOI：
10.5194/isprs-annals-iii-7-141-2016
发表时间：
2016-06
期刊：
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
影响因子：
--
作者：
Hui Ru;Huai Yu;Pingping Huang;Wen Yang
通讯作者：
Hui Ru;Huai Yu;Pingping Huang;Wen Yang