当前位置: X-MOL 学术J. Appl. Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Improving stacked-autoencoders with 1D convolutional-nets for hyperspectral image land-cover classification
Journal of Applied Remote Sensing ( IF 1.4 ) Pub Date : 2021-04-01 , DOI: 10.1117/1.jrs.15.026506
Mario Ernesto Jijón-Palma 1 , Jens Kern 2 , Caisse Amisse 1 , Jorge Antonio Silva Centeno 1
Affiliation  

Deep learning opened new possibilities for remote sensing image analysis using multiple neural nets layers. We introduce a hybrid pixel-based model that allows improving the unsupervised training with stacked autoencoders (SAE) by inserting convolutional neural networks (CNN) in the encoding and decoding steps. Inclusion of the convolution in the encoding and decoding steps allows a feature-based description of the pixel’s hyperspectral signature, suitable to perform an initial unsupervised classification. As one-dimensional (1D) filters are applied, the processing effort is lower than when using two-dimensional-CNN. Finally, to adapt the classifier to the desired classes, the parameters of the net are adjusted using training samples and fine-tuning followed by logistic regression using the softmax activation function. This combination explores the potential of both, autoencoders (AE) and convolutional nets, providing an alternative for the classification of hyperspectral data. To evaluate the performance of the proposed approach, it was compared to traditional machine learning algorithms such as support vector machine, artificial neural networks, CNN, and SAE. The results show that the use of the SAE-1DCNN method is more effective in terms of hyperspectral classification accuracy and more efficient in computational complexity and that it can be an alternative for hyperspectral data classification.

中文翻译:

使用一维卷积网络改进堆叠式自动编码器,以实现高光谱图像土地覆盖分类

深度学习为使用多个神经网络层的遥感图像分析开辟了新的可能性。我们介绍了一种基于混合像素的模型,该模型允许通过在编码和解码步骤中插入卷积神经网络(CNN)来改善使用堆叠式自动编码器(SAE)的无监督训练。将卷积包括在编码和解码步骤中,可以对像素的高光谱特征进行基于特征的描述,适合执行初始的无监督分类。由于应用了一维(1D)滤波器,因此与使用二维CNN相比,处理工作量较小。最后,为了使分类器适应所需的类别,使用训练样本和微调来调整网络的参数,然后使用softmax激活函数进行逻辑回归。这种组合探索了自动编码器(AE)和卷积网络的潜力,为高光谱数据的分类提供了另一种选择。为了评估该方法的性能,将其与传统的机器学习算法(如支持向量机,人工神经网络,CNN和SAE)进行了比较。结果表明,在高光谱分类精度方面,使用SAE-1DCNN方法更有效,并且在计算复杂度方面更有效,并且它可以替代高光谱数据分类。它与传统的机器学习算法(如支持向量机,人工神经网络,CNN和SAE)进行了比较。结果表明,在高光谱分类精度方面,使用SAE-1DCNN方法更有效,并且在计算复杂度方面更有效,并且它可以替代高光谱数据分类。它与传统的机器学习算法(如支持向量机,人工神经网络,CNN和SAE)进行了比较。结果表明,在高光谱分类精度方面,使用SAE-1DCNN方法更有效,并且在计算复杂度方面更有效,并且它可以替代高光谱数据分类。
更新日期:2021-04-29
down
wechat
bug