Combined multiscale segmentation convolutional neural network for rapid damage mapping from postearthquake very high-resolution images
Combined multiscale segmentation convolutional neural network for rapid damage mapping from postearthquake very high-resolution images
复制标题
组合多尺度分割卷积神经网络用于震后极高分辨率图像的快速损伤映射
DOI：
10.1117/1.jrs.13.022007
复制
发表时间：
2019-01-02
影响因子：
1.7
通讯作者：
Ma, Hongzhang
中科院分区：
文献类型：
--
作者：
Huang, Hui;Sun, Genyun;Ma, Hongzhang
摘要。由于地震后地表物体的复杂性，从地震后的高分辨率（VHR）图像中对土地利用进行分类是一项挑战。卷积神经网络（Convolutional neural network， CNN）能够自动提取高级特征，准确识别目标地物，在震后复杂地物的识别中表现出令人满意的效果。然而，鉴于自然物体的尺度差异，CNN的接受野固定、特征分辨率降低、训练样本不足等问题严重限制了其在快速损伤映射中的应用。多尺度分割技术可以生成均匀区域并提供边界信息，是一种很有前途的分割方法。为此，我们提出了一种结合多尺度分割卷积神经网络（CMSCNN）的震后VHR图像分类方法。首先，根据多尺度分割得到的片段选择多尺度训练样本；然后，直接训练CNN对原始图像进行分类，进一步生成初步分类图。为了提高定位精度，对CNN的输出进一步细化，采用从细到粗的多尺度迭代分割，得到多尺度分类图。因此，该组合策略能够同时捕获物体和图像上下文。实验结果表明，所提出的CMSCNN方法能够反映复杂场景的多尺度信息，对VHR遥感影像的震后震害映射获得满意的分类结果。
Abstract. Classifying land use from postearthquake very high-resolution (VHR) images is challenging due to the complexity of objects in Earth surface after an earthquake. Convolutional neural network (CNN) exhibits satisfied performance in differentiating complex postearthquake objects, thanks to its automatic extraction of high-level features and accurate identification of target geo-objects. Nevertheless, in view of the scale variance of natural objects, the fact that CNN suffers from the fixed receptive field, the reduced feature resolution, and the insufficient training sample has severely contributed to its limitation in the rapid damage mapping. Multiscale segmentation technique is considered as a promising solution as it can generate the homogenous regions and provide the boundary information. Therefore, we propose a combined multiscale segmentation convolutional neural network (CMSCNN) method for postearthquake VHR image classification. First, multiscale training samples are selected based on segments derived from the multiscale segmentation. Then, CNN is directly trained to classify the original image to further produce the preliminary classification maps. To enhance the localization accuracy, the output of CNN is further refined using multiscale segmentations from fine to coarse iteratively to obtain the multiscale classification maps. As a result, the combination strategy is able to capture objects and image context simultaneously. Experimental results show that the proposed CMSCNN method can reflect the multiscale information of complex scenes and obtain satisfied classification results for mapping postearthquake damage using VHR remote sensing images.