An Entropy and MRF Model-Based CNN for Large-Scale Landsat Image Classification
An Entropy and MRF Model-Based CNN for Large-Scale Landsat Image Classification
复制标题
DOI：
10.1109/lgrs.2019.2890996
复制
发表时间：
2019-01
影响因子：
4.8
通讯作者：
Xuemei Zhao;Lianru Gao;Zhengchao Chen;Bing Zhang;Wenzhi Liao;Xuan S. Yang
中科院分区：
文献类型：
--
作者：
Xuemei Zhao;Lianru Gao;Zhengchao Chen;Bing Zhang;Wenzhi Liao;Xuan S. Yang
大比例尺大地卫星图像分类对于制作土地覆盖图至关重要。卷积神经网络的兴起为陆地卫星图像分类的实现提供了新的思路。然而，由于其30米的空间分辨率，Landsat图像中的像素与高分辨率图像相比具有更高的不确定性。此外，当前的深度学习方法往往会丢失详细信息，例如随着卷积层和池化层的堆叠而丢失沿着。为了解决这些问题，我们提出了一种新的方法，称为熵和MRF模型（EMM）-CNN基于金字塔场景解析网络。EMM-CNN使用熵来降低像素的不确定性。然后，马尔可夫随机场（MRF）模型被用来构建相邻像素之间的连接，并定义了一个先验分布，以防止交叉熵牺牲细节信息的整体精度。最后，引入了基于预训练ImageNet的迁移学习，以克服训练样本不足的问题，提高训练过程的速度。实验结果表明，所提出的EMM-CNN是能够获得的分类结果与精细结构，通过减少不确定性和保留细节信息的检测图像。
Large-scale Landsat image classification is essential for the production of land cover maps. The rise of convolutional neural networks (CNNs) provides a new idea for the implementation of Landsat image classification. However, pixels in Landsat images have higher uncertainty compared with high-resolution images due to its 30-m spatial resolution. In addition, the current deep learning methods tend to lose detailed information such as boundaries along with the stacking of convolutional and pooling layers. To solve these problems, we propose a new method called entropy and MRF model (EMM)-CNN based on Pyramid Scene Parsing Network. The EMM-CNN uses entropy to decrease the uncertainty of pixels. Then, the Markov random filed (MRF) model is employed to construct the connections between neighboring pixels and defined a prior distribution to prevent the cross entropy from sacrificing detailed information for the overall accuracy. Finally, transfer learning based on the pretrained ImageNet is introduced to overcome the shortage of training samples and boost the speed of the training process. Experimental results demonstrate that the proposed EMM-CNN is able to obtain classification results with fine structure by decreasing the uncertainty and retaining detailed information of the detected image.