Automatic landslide detection from remote-sensing imagery using a scene classification method based on BoVW and pLSA
Automatic landslide detection from remote-sensing imagery using a scene classification method based on BoVW and pLSA
复制标题
使用基于 BoVW 和 pLSA 的场景分类方法从遥感图像中自动检测滑坡
DOI：
10.1080/01431161.2012.705443
复制
发表时间：
2013-01-01
影响因子：
3.4
通讯作者：
Fang, Jun
中科院分区：
文献类型：
--
作者：
Cheng, Gong;Guo, Lei;Fang, Jun
利用遥感影像进行滑坡检测是滑坡制图、滑坡调查和滑坡灾害评估的重要前期工作。针对滑坡自动检测的研究，提出了一种基于遥感图像的滑坡自动检测方法。我们实现了这一目标，结合无监督的概率潜在语义分析（pLSA）模型和k-最近邻（k-NN）分类的视觉词袋（BoVW）表示的基础上使用的场景分类方法。给定一幅遥感图像，我们将其划分为大小相等的正方形子图像，然后将每个子图像描述为BoVW表示。该方法首先利用BoVW表示对子图像进行pLSA建模，发现子图像中描述的对象类别，然后利用k-NN分类器根据对象分布将子图像分为滑坡区和非滑坡区。利用伊犁地区的遥感影像对该方法的性能和适用性进行了研究。结果表明，该方法是鲁棒的，可以产生良好的性能，而无需获取三维（3D）地形。研究结果可为滑坡调查制图和滑坡灾害评估提供参考。
Landslide detection from extensive remote-sensing imagery is an important preliminary work for landslide mapping, landslide inventories, and landslide hazard assessment. Aimed at development of an automatic procedure for landslide detection, a new method for automatic landslide detection from remote-sensing imagery is presented in this study. We achieved this objective using a scene classification method based on the bag-of-visual-words (BoVW) representation in combination with the unsupervised probabilistic latent semantic analysis (pLSA) model and the k-nearest neighbour (k-NN) classifier. Given a remote-sensing image, we divided it into equal-sized square sub-images and then described each sub-image as a BoVW representation. The pLSA model was applied to sub-images by using the BoVW representation to discover the object classes depicted in the sub-images, and then a k-NN classifier was used to classify the sub-images into landslide areas and non-landslide areas based on object distribution. We investigated the performance and applicability of the method using remote-sensing imagery from the Ili area. The results show that the method is robust and can produce good performance without the acquisition of three-dimensional (3D) topography. We anticipate that these results will be helpful in landslide inventory mapping and landslide hazard assessment in landslide-stricken areas.